No entries match these filters. Clear filters
Portkey adds a DELETE /v1/secret-references/{SECRET_REFERENCE_ID} endpoint to remove secret references via the Admin API Admin API A dedicated HTTP interface that exposes management and configuration operations separately from the data plane, letting cyber tools automate provisioning, policy changes, or monitoring without touching the main user-facing service. ︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Remove a secret reference you no longer need from Portkey's control plane.
copy
$ curl -X DELETE https://api.portkey.ai/v1/secret-references/SECRET_REFERENCE_ID \
-H 'x-portkey-api-key: PORT…'
Delete a stored secret reference by ID with DELETE https://api.portkey.ai/v1/secret-references/{SECRET_REFERENCE_ID}, authenticated via the x-portkey-api-key header.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
1 detail in Everything
Portkey adds a Retrieve Secret Reference endpoint to fetch secret reference details by ID︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Inspect a specific secret reference — e.g. to verify its manager_type, status, or workspace visibility — before referencing it in a virtual key or config.
copy
$ curl -X GET https://api.portkey.ai/v1/secret-references/SECRET_REFERENCE_ID \
-H "x-portkey-api-key: PORT…"
Retrieve a secret reference by ID via GET /v1/secret-references/{SECRET_REFERENCE_ID}, returning fields including id, organisation_id, name, slug, description, manager_type (e.g.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ aws_sm), secret_path, secret_key, allow_all_workspaces, status, created_by, created_at, last_updated_at, and object. Not checked yet
1 detail in Everything
Portkey adds an API key retrieval endpoint with rate-limit, credit, and expiry metadata fields︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Audit an API key's rate limit, credit budget, and expiry before rotating it in production.
python
copy
from portkey_ai import Portkey
portkey = Portkey(api_key="PORT…")
api_key = portkey.api_keys.retrieve(id="API_KEY_ID")
print(api_key["status"]) # 'active'
print(api_key["unit"]) # 'rpm'
print(api_key["value"]) # 100
print(api_key["credit_limit"]) # 10
print(api_key["alert_threshold"]) # 8
print(api_key["expires_at"]) # '2023-11-07T05:31:56Z'
Retrieve full API key details — including status, creation_mode, config_id, expires_at, credit_limit, alert_threshold, periodic_reset, reset_usage, environment, team, unit, and value — via portkey.api_keys.retrieve(id='API_KEY_ID') in the Python SDK.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet API key rate-limit fields type, unit (e.g. rpm), and value are now returned on retrieval, letting you inspect per-key request throttle settings programmatically. Not checked yet API key credit fields credit_limit, periodic_reset (e.g. monthly), and alert_threshold are now returned on retrieval, enabling automated budget monitoring. Not checked yet
3 details in Everything
Portkey adds an API key rotation endpoint with a configurable key_transition_period_ms overlap window︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Rotate an API key via a POST endpoint, with key_transition_period_ms controlling how long (in milliseconds) the old key remains valid alongside the new one — the diff shows a value of 3600000 (one hour).︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
1 detail in Everything
Portkey adds credit limit and periodic reset controls to virtual key creation︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Create a virtual key with a monthly credit cap and an alert before the budget runs out.
copy
$ curl -X POST https://api.portkey.ai/v1/admin/virtual-keys \
-H 'x-portkey-api-key: <your-admin-api-key>' \
-H 'Content-Type: application/json' \
-d '{
"credit_limit": 100,
"periodic_reset": "monthly",
"alert_threshold": 80
}'
Set a spending cap on a virtual key with the credit_limit field on the Create Virtual Key API, optionally configured to reset monthly via periodic_reset.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Trigger notifications before a virtual key's credit is exhausted using the alert_threshold field on the Create Virtual Key API. Not checked yet
2 details in Everything
Portkey's provider update API now supports credit_limit, periodic_reset, and alert_threshold fields for per-provider budget controls︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Cap a provider's monthly spend and get alerted before the limit is hit, without touching other provider settings.
python
copy
from portkey_ai import Portkey
portkey = Portkey(api_key="PORT…")
updated_provider = portkey.providers.update(
"PROVIDER_SLUG",
name="updated-name",
note="updated-note",
credit_limit="",
periodic_reset="monthly",
alert_threshold=""
)
print(updated_provider)
Portkey adds portkey.integrations.update() method to the Python SDK for updating integration metadata via the Admin API Admin API A dedicated HTTP interface that exposes management and configuration operations separately from the data plane, letting cyber tools automate provisioning, policy changes, or monitoring without touching the main user-facing service. ︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Update the display name and note for an existing integration by its slug.
python
copy
from portkey_ai import Portkey
portkey = Portkey(api_key="PORT…")
integration = portkey.integrations.update(
slug="INTEGRATION_SLUG",
name="updated-name",
note="hello"
)
print(integration)
Update an existing integration's name and notes programmatically using portkey.integrations.update(slug=..., name=..., note=...) in the Python SDK.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
1 detail in Everything
Portkey adds a GET /v1/files endpoint to list uploaded files via the inference API︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Audit all files uploaded to a provider via Portkey to verify their status before triggering a fine-tune or assistant run.
copy
$ curl https://api.portkey.ai/v1/files \
-H "x-portkey-api-key: $PORT…" \
-H "x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY"
Portkey adds a batch cancellation endpoint at POST /v1/batches/{id}/cancel︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Stop a running batch job before it completes to avoid unnecessary processing costs.
copy
$ curl https://api.portkey.ai/v1/batches/batch_abc123/cancel \
-H "x-portkey-api-key: $PORT…" \
-H "x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY" \
-H "Content-Type: application/json" \
-X POST
Portkey adds a GET /v1/batches endpoint to list batch jobs with pagination support︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Retrieve the two most recent batch jobs to monitor their status fields (such as validating , completed counts, and timestamps) across a provider.
copy
$ curl https://api.portkey.ai/v1/batches?limit=2 \
-H "x-portkey-api-key: $PORT…" \
-H "x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY" \
-H "Content-Type: application/json"
Portkey adds a /v1/moderations API endpoint for content moderation across hate, harassment, self-harm, sexual, and violence categories︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Screen user-generated content against all moderation categories before passing it to a downstream LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. .
copy
$ curl https://api.portkey.ai/v1/moderations \
-H 'Content-Type: application/json' \
-H 'x-portkey-api-key: $PORT…' \
-H 'x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY' \
-d '{"model": "text-moderation-latest", "input": "<user message>"}'
Call the POST /v1/moderations endpoint at https://api.portkey.ai/v1/moderations using x-portkey-api-key and x-portkey-virtual-key headers to run content moderation checks through Portkey's inference API.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Moderation results include per-category flagged boolean fields and scores covering hate, hate/threatening, harassment, harassment/threatening, self-harm, self-harm/intent, self-harm/instructions, sexual, sexual/minors, violence, and violence/graphic. Not checked yet
2 details in Everything
Portkey adds a POST /v1/audio/transcriptions API endpoint for audio transcription via the inference API︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Route an audio transcription request through Portkey to a provider like OpenAI Whisper, applying Portkey's observability and gateway features.
copy
$ curl https://api.portkey.ai/v1/audio/transcriptions \
-H "x-portkey-api-key: $PORT…" \
-H "x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY" \
-H "Content-Type: multipart/form-data" \
-F file="@/path/to/file/audio.mp3" \
-F model="whisper-1"
Portkey adds a logs.create() method to insert logs programmatically via the Admin API Admin API A dedicated HTTP interface that exposes management and configuration operations separately from the data plane, letting cyber tools automate provisioning, policy changes, or monitoring without touching the main user-facing service. data plane︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Push a log entry for an external or self-hosted LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. call that never went through Portkey's proxy, so it still appears in the Portkey observability dashboard.
python
copy
from portkey_ai import Portkey
portkey = Portkey(api_key="PORT…")
request = {
"url": "https://api.someprovider.com/model/generate",
"method": "POST",
"headers": {"Content-Type": "application/json"},
"body": {"prompt": "What is AI?"}
}
response = {
"status": 200,
"headers": {"Content-Type": "application/json"},
"body": {"response": "AI stands for Artificial Intelligence..."},
"response_time": 123
}
metadata = {
"user_id": "123",
"user_name": "John Doe"
}
result = portkey.logs.create(request=request, response=response, metadata=metadata)
print(result)
Portkey now publishes an API — 257 endpoints across 56 areas: Assistants, Analytics > Graphs, Vector Stores, …︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Assistants (23 endpoints) — Build Assistants that can call models and use tools.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds Analytics > Graphs API (17 endpoints) to get data points for graphical representation, and Analytics > Groups API (7 endpoints) to get grouped metrics for the selected time bucket. Not checked yet Vector Stores (13 endpoints) — create, read, delete Not checked yet Prompts (11 endpoints) — Given a prompt template ID and variables, will run the saved prompt template and return a response. Not checked yet Guardrails (8 endpoints) — Create, List, Retrieve, Update, and Delete Guardrails for LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. requests and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool calls. Not checked yet
+3 more
show less
Workspaces (8 endpoints) — Create and manage workspaces. Not checked yet Logs Export (7 endpoints) — Exports logs service. Not checked yet 48 more areas: Promptpartials, Usage Limits Policies, Api Keys, Configs, Deployments, Mcp Servers, Access Policies, Batch, Collections, Egress Allowlist, Files, Fine Tuning, Integrations, Labels, Mcp Integrations, Providers, Rate Limits Policies, Secret References, User Invites, Virtual Keys, Workspaces > Members, Responses, Users, Audio, Images, Integrations > Models, Models, Feedback, Integrations > Workspaces, Logs, Mcp Integrations > Capabilities, Mcp Integrations > Workspaces, Mcp Servers > Capabilities, Mcp Servers > Connections, Mcp Servers > User Access, Messages, Analytics > Summary, Audit Logs, Chat, Completions, Embeddings Embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. , Finetune, Mcp Integrations > Metadata, Model Pricing, Moderations, Ocr, Realtime, Rerank Not checked yet
8 details in Everything
Portkey's JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. guardrail now extracts token claims into request headers and metadata when run as a start hook︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Attach the JWT guardrail as a start hook and extract the sub and roles claims into downstream request headers and metadata for conditional routing.
json
copy
{
"type": "guardrail",
"hook": "start",
"config": {
"claimsToExtract": ["sub", "roles"],
"failOpenOnInvalidToken": false
}
}
Extract JWT claims into request headers and metadata by configuring the claimsToExtract array (start hook only), making values available to conditional routing and downstream services as headers like x-jwt-sub.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Run the JWT guardrail as a start hook to enforce token validation on every request in a workspace or organization and enable claim extraction before routing. Not checked yet Arrays extracted from claims are joined with commas, objects are serialized as JSON, and claims with non-printable ASCII or restricted header names (such as authorization, cookie, or any x-portkey-* header) are written to metadata only, never to headers. Not checked yet
Extract JWT claims into request headers and metadata by configuring the claimsToExtract array (start hook only), making values available to conditional routing and downstream services as headers like x-jwt-sub.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Arrays extracted from claims are joined with commas, objects are serialized as JSON, and claims with non-printable ASCII or restricted header names (such as authorization, cookie, or any x-portkey-* header) are written to metadata only, never to headers. Not checked yet
1 more in Everything
└──▷ BREAKING ON UPGRADE
!
Invalid JWT tokens (signature, algorithm, or expiry failures) are now denied by default instead of being allowed through on error. Set `failOpenOnInvalidToken: true` to restore the previous fail-open behavior.
Our best guess
Portkey now supports per-workspace credential overrides for the Palo Alto Prisma AIRS integration, letting workspaces supply their own API key.
Updated integration Override the organisation-level Prisma AIRS API key on a per-workspace basis using the Override Credentials object, so different workspaces can authenticate with their own Prisma AIRS API key. Not checked yet
1 detail in Everything
Portkey adds a pre-model traffic inspection lifecycle stage and expands guardrail coverage to MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool calls︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Portkey now applies guardrails to MCP tool calls, extending coverage beyond standard model request/response traffic.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Portkey adds a new lifecycle stage to inspect traffic before it reaches a model. Not checked yet
2 details in Everything
Portkey adds Decisions API, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. guardrails, startHooks lifecycle stage, and Meta/ElevenLabs provider support︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Call the Decisions API to get a calibrated boolean judgment from a TypeSafe Jev model — useful for automated triage or policy enforcement pipelines.
copy
$ curl -X POST https://api.portkey.ai/v1/decisions \
-H 'x-portkey-api-key: <your-api-key>' \
-H 'Content-Type: application/json' \
-d '{
"model": "jev",
"question": "Does this request contain PII?",
"state": {"text": "My name is Jane Doe and my SSN is 123-45-6789"},
"output_type": "boolean"
}'
Adds startHooks lifecycle stage to screen and normalize traffic before authentication, routing, or other hooks run — including two new checks: Header Check (allow/block by header key-value pairs) and Header Transform (remove, set, or rewrite headers before routing; x-portkey-* headers are protected); existing checks allowedRequestTypes, webhook, and JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. header lookup can also now run as startHooks.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds a Decisions API endpoint for typed-judgment models: send a question with structured state and receive a typed judgment (boolean, choice, or score) with probabilities and a calibrated confidence score, routing through the full gateway stack (auth, routing, retries, caching, logging, cost tracking); initial support covers TypeSafe's Jev model family. Not checked yet Extends MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. guardrails so MCP tool calls pass through the same pre- and post-execution checks available for LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. requests; denied calls return a structured error with the guardrail and check ID. Not checked yet Adds per-attempt retry logging, giving each retry its own log row with its own status and response instead of only surfacing the final result. Not checked yet Adds Meta and ElevenLabs as new providers: Meta supports Chat Completions, Messages API, Responses API, and Files API, while ElevenLabs supports text-to-speech and speech-to-text with full observability and reliability features. Not checked yet
+5 more
show less
Extends xAI provider to support image generation with OpenAI-compatible parameters plus xAI-specific aspect ratio and resolution controls. Not checked yet Adds Anthropic-protocol auto-detection on /v1/models so Claude Code and other Anthropic-native clients receive Anthropic's native model shape instead of the OpenAI-normalized shape. Not checked yet Extends JWT authentication to accept multiple JWKS JWKS A JSON Web Key Set, a published collection of cryptographic keys. Applications use it to find the public key needed to verify a token's signature. URLs and attribute requests to the matching workspace user. Not checked yet Extends conditional routing to read fields from multipart/form-data requests (image edits, audio transcriptions). Not checked yet Messages API reasoning models now stream their thinking phase as a thinking content block. Not checked yet
Adds startHooks lifecycle stage to screen and normalize traffic before authentication, routing, or other hooks run — including two new checks: Header Check (allow/block by header key-value pairs) and Header Transform (remove, set, or rewrite headers before routing; x-portkey-* headers are protected); existing checks allowedRequestTypes, webhook, and JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. header lookup can also now run as startHooks.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds a Decisions API endpoint for typed-judgment models: send a question with structured state and receive a typed judgment (boolean, choice, or score) with probabilities and a calibrated confidence score, routing through the full gateway stack (auth, routing, retries, caching, logging, cost tracking); initial support covers TypeSafe's Jev model family. Not checked yet Adds per-attempt retry logging, giving each retry its own log row with its own status and response instead of only surfacing the final result. Not checked yet Adds Meta and ElevenLabs as new providers: Meta supports Chat Completions, Messages API, Responses API, and Files API, while ElevenLabs supports text-to-speech and speech-to-text with full observability and reliability features. Not checked yet
6 more in Everything
Portkey adds Mistral AI content moderation guardrails with 9 policy categories and multilingual support across 11 languages.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Apply Mistral content moderation to both incoming prompts and outgoing LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. responses by wiring guardrail IDs into a Portkey Config.
json
copy
{
"input_guardrails": ["guardrails-id-xxx"],
"output_guardrails": ["guardrails-id-xxx"]
}
Send a chat completion through Portkey with a Mistral moderation Config attached, so every request and response is checked before delivery.
copy
$ curl https://api.portkey.ai/v1/chat/completions \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer $OPENAI_API_KEY' \
-H 'x-portkey-api-key: $PORTKEY_API_KEY' \
-H 'x-portkey-config: $CONFIG_ID' \
-d '{"model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Hello!"}]}'
Connect your Mistral La Plateforme API key to Portkey and create a Moderate Content guardrail covering PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. and Violence categories before attaching it to a Config.
📍 1. In Portkey, go to Settings › Integrations, click Edit on the Mistral integration, and paste your Mistral La Plateforme API Key.
2. Go to Guardrails › Create, search for Moderate Content , click Add, select the desired Moderation Checks (e.g. PII, Violence and Threats), set Timeout to 5000ms, and save to obtain a Guardrail ID.
3. Create a Config with that Guardrail ID in input_guardrails or output_guardrails and save it to obtain a Config ID for use in requests.
Adds input_guardrails and output_guardrails config params to route requests through Mistral's Moderate Content guardrail check, supporting beforeRequestHook and afterRequestHook.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds Mistral Moderate Content guardrail check with configurable Moderation Checks (array) and Timeout (number, default 5000ms) parameters to detect harmful content across 9 policy categories: Sexual, Hate and Discrimination, Violence and Threats, Dangerous and Criminal Content, Self-harm, Health, Financial, Law, and PII. Not checked yet Supports Mistral's natively multilingual moderation across Arabic, Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, and Spanish. Not checked yet
3 details in Everything
Portkey adds Lakera Guard integration for prompt/response screening with PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. redaction via /v2/guard︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ USE IT
Attach a Lakera Guard guardrail to both input and output of a Portkey config to screen all prompts and responses for policy violations and PII.
json
copy
{
"input_guardrails": ["guardrails-id-xxx"],
"output_guardrails": ["guardrails-id-yyy"]
}
Set up the Lakera integration credentials and configure the Guard check with a specific project and timeout via Admin Settings.
📍 1. Go to Admin Settings → Plugins
2. Edit the Lakera integration, paste your Lakera API Key (from platform.lakera.ai), and optionally set API Base URL to https://api.lakera.ai
3. Go to Guardrails → Create, search for Lakera Guard , click Add
4. Set projectID to your Lakera project, endInclusive to false, and timeout as needed
5. Set guardrail actions and click Create
Adds Lakera Guard integration that screens prompts and responses via Lakera's /v2/guard API, blocking on policy hits and redacting PII spans when pii/* detectors fire.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Exposes projectID, endInclusive, and timeout parameters on the Lakera Guard check, supporting both beforeRequestHook and afterRequestHook positions. Not checked yet Attaches Lakera guardrails to Portkey configs via input_guardrails and output_guardrails fields for SDK and gateway use. Not checked yet Allows an optional API Base URL override on the Lakera integration (defaults to https://api.lakera.ai) configured under Admin Settings → Plugins. Not checked yet
4 details in Everything
Portkey adds a /v1/decisions endpoint for typed model judgments (choice, score, probability) with guardrails on the state field︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Route an incoming support ticket to the right team by getting a structured department classification instead of parsing free text.
copy
$ curl https://api.portkey.ai/v1/decisions \
-H 'x-portkey-provider: typesafe' \
-H 'Authorization: Bearer $TYPESAFE_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "jev-latest",
"state": "My payouts have been failing for 3 days.",
"questions": {
"department": {
"type": "choice",
"instructions": "Which team should handle this?",
"criteria": { "billing": "Payments", "technical": "Bugs" }
}
}
}'
Prioritise a user's own workspace when issuing JWTs JWTs JSON Web Tokens — an open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object. Cyber tools use them for stateless authentication without server-side session storage. , so multi-tenant deployments resolve to the correct workspace without relying on deployment-level defaults.
copy
$ JWT_PREFER_USER_WORKSPACE_RESOLUTION=ON ./portkey-gateway
Adds POST /v1/decisions endpoint that returns typed judgments (noul, choice, or score) instead of free text, accepting a state field and a questions map — currently available through TypeSafe's Jev models (jev-latest, jev-1.13.0).︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds JWT_PREFER_USER_WORKSPACE_RESOLUTION environment variable to the gateway; set to ON to try a user token's own workspace membership before deployment and organisation defaults in the resolution order. Not checked yet Adds guardrails support for /v1/decisions requests, scanning only the caller-supplied state field (never model, questions, or criteria) via input_guardrails at the before-request stage — hard-deny returns 446, soft-deny returns 200 with an empty answers map. Not checked yet Decisions requests participate in the full gateway feature set: retries, fallbacks, load balancing, and circuit breaking via Configs; simple and semantic caching; and observability (logs, cost tracking, analytics). Not checked yet Mutator guardrails (e.g. PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. redaction) can rewrite state before it reaches the provider, with JSON round-trip safety — if redacted output is no longer valid JSON for an object/array state, Portkey preserves the original rather than forwarding corrupted content. Not checked yet
5 details in Everything
DashScope image generation support, user-first workspace resolution via JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. , and Gemini finish_reason reporting.
Adds DashScope as a supported provider on the /v1/images/generations endpoint with region-based pricing attribution in logs. Not checked yet Adds JWT_PREFER_USER_WORKSPACE_RESOLUTION=ON environment variable to resolve workspace defaults from user membership when none is named in the JWT. Not checked yet Improves Google Gemini / Vertex AI streaming responses to report finish_reason: "tool_calls" for tool invocations, matching non-streaming behavior. Not checked yet
3 details in Everything
Portkey Enterprise Gateway 2.25.1 adds Meta provider support, new Responses API operations, and improved MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. auth handling.
Adds Meta as a first-class provider with support for Chat Completions, Anthropic-compatible Messages API, OpenAI-compatible Responses API, and Files API protocols. Not checked yet Introduces cancel and input token counting operations in the Responses API for supported providers. Not checked yet Wires Retrieve, delete, and list input items endpoints for xAI, DashScope, Perplexity, and Azure OpenAI providers via the Responses API. Not checked yet Unstrips interleaved-thinking-2025-05-14 and per-turn-control-2026-07-01 beta headers for Anthropic on Bedrock and Vertex AI. Not checked yet Streams thinking phase as a thinking content block in the Messages API instead of dropping it for routed reasoning models. Not checked yet
+1 more
show less
Enables 401 challenge and immediate re-authorization for revoked tokens in the MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. during mid-refresh. Not checked yet
6 details in Everything
Portkey Backend v1.28.0 improves log export filtering with deployment_slug and optimizes list exports response payload. Model catalog definitions and pricing are updated for Anthropic, Bedrock, Vertex AI, Google, Azure AI, OpenRouter OpenRouter A unified API gateway that routes requests to dozens of LLM providers under one endpoint, letting cyber tools swap or compare models without rewriting provider-specific integration code. , Lightning AI.
└──▷ TRY IT
Generate speech via ElevenLabs through Portkey's unified audio endpoint without any custom host setup.
copy
$ curl -X POST https://api.portkey.ai/v1/audio/speech \
-H "x-portkey-provider: @YOUR_ELEVENLABS_PROVIDER_SLUG" \
-H 'Content-Type: application/json' \
-d '{"model": "eleven_multilingual_v2", "input": "Hello! Welcome to Portkey.", "voice": "21m00Tcm4TlvDq8ikWAM"}'
Transcribe audio using ElevenLabs Scribe via Portkey's unified transcriptions endpoint.
copy
$ curl -X POST https://api.portkey.ai/v1/audio/transcriptions \
-H "x-portkey-provider: @YOUR_ELEVENLABS_PROVIDER_SLUG" \
-F file="@recording.mp3" \
-F model="scribe_v1"
Portkey adds native ElevenLabs TTS and STT routing via unified /v1/audio/speech and /v1/audio/transcriptions endpoints︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
└──▷ TRY IT
Generate speech via ElevenLabs through Portkey's unified audio endpoint without any custom host setup.
copy
$ curl -X POST https://api.portkey.ai/v1/audio/speech \
-H "x-portkey-provider: @YOUR_ELEVENLABS_PROVIDER_SLUG" \
-H "Content-Type: application/json" \
-d '{"model": "eleven_multilingual_v2", "input": "Hello! Welcome to Portkey.", "voice": "21m00Tcm4TlvDq8ikWAM"}'
Transcribe audio using ElevenLabs Scribe through Portkey's unified transcription endpoint.
copy
$ curl -X POST https://api.portkey.ai/v1/audio/transcriptions \
-H "x-portkey-provider: @YOUR_ELEVENLABS_PROVIDER_SLUG" \
-F file="@recording.mp3" \
-F model="scribe_v1"
Routes ElevenLabs text-to-speech through the unified /v1/audio/speech endpoint using x-portkey-provider: @YOUR_ELEVENLABS_PROVIDER_SLUG, accepting any ElevenLabs voice ID (premade, cloned, or custom) via the voice field — forwarded as-is rather than remapped from OpenAI built-in voice names.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Routes ElevenLabs speech-to-text through the unified /v1/audio/transcriptions endpoint using the scribe_v1 model, with no custom host configuration required. Not checked yet Adds providerSlug as an opt-in Prometheus extra label (disabled by default; enable by adding providerSlug to PROMETHEUS_EXTRA_LABELS) to distinguish the Model Catalog provider or virtual key that served a request from the upstream provider name. Not checked yet
3 details in Everything
Enterprise Gateway 2.25.0 adds TypeSafe Decisions API, workspace selection via JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. header, and startHooks for guardrails
Adds /v1/decisions endpoint for typed-judgment models returning boolean, choice, or score with probabilities Not checked yet Adds x-portkey-workspace header support to gateway-local JWT requests to select a workspace at request time Not checked yet Adds startHooks list in guardrail configs to run checks before authentication and routing Not checked yet Adds Header Check and Header Transform guardrail checks available at the startHooks stage Not checked yet
4 details in Everything
Enterprise Gateway 2.24.0 adds per-attempt retry logging, truncated SSE SSE Server-Sent Events, a browser API and HTTP-based protocol where a server pushes a stream of text events to a client over a single long-lived connection, giving tools a lightweight alternative to WebSockets for one-way real-time updates. detection across providers, and Anthropic safeguard forwarding.
Adds retry_count, response_status, response_headers, and response_body fields to log rows for intermediate retry attempts Not checked yet Enables stream_incomplete error event appending when a stream ends without its terminal event across all unified text routes (/chat/completions, /completions, /messages, /responses) Not checked yet Forwards the safeguards and safeguard_results fields to Anthropic on Claude Code auto-mode requests Not checked yet
3 details in Everything
Backend 1.27.0 adds SCX.ai provider, per-model pricing multipliers, guardrails analytics endpoints, Azure PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. category filtering, and new API key filters.
api — Adds /guardrail/summary, /guardrail/trend, and /guardrail/grouped endpoints for Guardrails analytics. Not checked yet config — Adds piiCategories parameter to Guardrails settings to restrict detection to selected PII categories. Not checked yet api — Adds filter parameters to the API key list endpoint. Not checked yet config — Allows setting pricing multipliers on individual models within an integration. Not checked yet New scx-ai provider support (OpenAI-compatible) in the Model Catalog. Not checked yet
5 details in Everything
Portkey Enterprise Gateway 2.23.0 adds ElevenLabs support, Vertex AI region honor, Prometheus provider label, and OAuth error exposure
Adds native routing for /v1/audio/speech and /v1/audio/transcriptions to ElevenLabs without custom host configuration Not checked yet Makes vertexRegion config key honored for Vertex AI Rerank requests instead of defaulting to global Discovery Engine Not checked yet Adds opt-in Prometheus metrics label providerSlug to identify the Model Catalog provider that served a request Not checked yet Exposes underlying OAuth authorize error on rejection via MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. instead of returning HTTP 500 Not checked yet
4 details in Everything
Frontend 1.10.1 adds guardrail workspace exclusions, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. /A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. grouping and deletion, and API key pagination
Adds UI for organisation-level guardrail workspace exclusions in input and output guardrails Not checked yet Adds MCP and A2A grouping in the integration management UI Not checked yet Adds delete option for MCP servers in the dashboard Not checked yet Adds pagination for API keys listing Not checked yet
4 details in Everything
Portkey MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. gains two-layer authentication with API key, OAuth 2.1 OAuth 2.1 A consolidated draft of the OAuth authorization framework that merges OAuth 2.0 with its most important security BCP updates, dropping unsafe flows so tools can delegate user access without handling credentials directly. , external IdP IdP A service that authenticates users and supplies identity information to other applications. It is the sign-in authority behind many single sign-on systems. , and per-model pricing adjustments︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Adds MCP Gateway authentication via x-portkey-api-key header (API key scoped to workspaces, requires mcp invoke permission, created in Settings > API Keys).︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet Adds OAuth 2 OAuth 2 An open authorization framework (RFC 6749) that lets a service grant limited access to a user's resources on another service without exposing credentials, giving cyber tools a standard way to authenticate against third-party APIs. .1 support for MCP Gateway: when no API key is present Portkey acts as the OAuth provider and initiates a browser-based consent flow for interactive tools such as Claude Desktop or Cursor. Not checked yet Adds External IdP (Bring Your Own Identity) support for MCP Gateway, enabling JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. validation from Okta, Auth0, Azure AD, and Cognito so users without Portkey accounts can access MCP servers. Not checked yet Adds three MCP server authentication methods when configuring an upstream server: OAuth Auto (full OAuth 2.1 with dynamic client registration and automatic token refresh), Client Credentials Client Credentials An OAuth 2.0 grant type where a service authenticates directly with an authorization server using its own ID and secret, with no user involved, to obtain an access token for machine-to-machine API calls. (shared OAuth client ID/secret with auto-refresh), and Custom Headers (static API keys or tokens via configurable headers). Not checked yet Adds identity forwarding from Portkey to upstream MCP servers after gateway authentication, supporting Claims Header (JSON object of user claims), Bearer Passthrough (original token), and Signed JWT (Portkey-signed, cryptographically verifiable JWT). Not checked yet
+3 more
show less
Adds header forwarding from agent requests to MCP servers for distributed tracing, tenant context, or custom metadata. Not checked yet Adds per-model pricing_adjustments on individual models within an Integration (requires Gateway version 2.22.0 or higher); a model-level adjustment fully replaces the Integration-level one for that model. Not checked yet Adds CIE Directory Sync for SCM SCM Source Code Management: version-control systems (Git, SVN, etc.) that track changes to code over time, giving cyber tools reproducible builds, audit trails, and collaborative development workflows. (Strata Cloud Manager) deployments, enabling automatic workspace provisioning by mapping Palo Alto Networks Cloud Identity Engine groups — sourced from Entra ID Entra ID Microsoft's cloud-based identity and access management service, formerly Azure Active Directory, used by cyber tools to authenticate users and enforce access policies in Microsoft 365 and Azure environments. , Okta, or on-premises Active Directory Active Directory Microsoft's directory service for Windows networks that centralises authentication and authorisation; cyber tools target or integrate with it because it controls identity and access across most enterprise environments. — to AI Gateway workspaces. Not checked yet
8 details in Everything
Portkey's Azure Guardrails integration adds PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. category filtering to restrict detection to specific entity types.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄
Adds PII category filtering to Azure Guardrails, supporting entity types Person , Email , PhoneNumber, Address , CreditCardNumber, and PassportNumber — leave empty to detect all default categories.︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄ Not checked yet
1 detail in Everything
Portkey Frontend 1.10.0 adds Meta provider, OAuth UI for OpenAI, Guardrail analytics dashboard, and custom legacy model pricing.
Adds OAuth Client Credentials OAuth Client Credentials An OAuth 2.0 grant type where a service authenticates directly with an authorization server using its own ID and secret, receiving a token to call APIs without any user involved. UI for OpenAI integrations Not checked yet Adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Guardrails support Not checked yet Adds custom pricing for legacy models support Not checked yet
3 details in Everything
Azure context-aware pricing, per-model pricing adjustments, and Claude Code model discovery via /v1/models
Adds id, type, display_name, and created_at fields in the response body for /v1/models calls from clients sending an anthropic-version header. Not checked yet Adds support for the service_tier request parameter to forward Azure service tiers (standard, batch, priority, flex) to providers, replacing dropped values. Not checked yet Adds PII Categories setting in Azure PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. Guardrail configurations to limit detection to specific entity types. Not checked yet
3 details in Everything
└──▷ BREAKING ON UPGRADE
! Automatic anthropic-beta: messages-2023-12-15 header is no longer added to Anthropic requests.! A model-level pricing adjustment fully replaces the integration-level one rather than merging with it.
Portkey Backend 1.26.0 adds ElevenLabs provider support, multi-JWSS JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. validation, webhook proxy guardrails, and log export API.
Adds elevenlabs provider to the Model Catalog for text-to-speech, speech-to-text, dubbing, and voice cloning Not checked yet Allows JWT validation to accept comma-separated JWKS JWKS A JSON Web Key Set, a published collection of cryptographic keys. Applications use it to find the public key needed to verify a token's signature. URIs for multiple identity providers identity providers A service that authenticates users and supplies identity information to other applications. It is the sign-in authority behind many single sign-on systems. , fetching keys in parallel Not checked yet Adds executeOnProxy parameter to webhook guardrails to run on /v1/* pass-through requests with method, path, and content-type metadata Not checked yet Adds DELETE /v1/logs/exports/{id} endpoint to delete log exports (requires cancellation of in-progress exports first) Not checked yet Adds default timeout field for AIRS service requests Not checked yet
+2 more
show less
Routes model fetching for SCM SCM Source Code Management: version-control systems (Git, SVN, etc.) that track changes to code over time, giving cyber tools reproducible builds, audit trails, and collaborative development workflows. through the config proxy Not checked yet Returns usage policy IDs in organisation data responses via the Organisation sync API Not checked yet
7 details in Everything
ElevenLabs provider support, Gateway-Local JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. multi-JWKS JWKS A JSON Web Key Set, a published collection of cryptographic keys. Applications use it to find the public key needed to verify a token's signature. /attribute, and SCX.ai provider added in Portkey Enterprise Gateway v2.21.0
Adds ElevenLabs as a new provider for text-to-speech and speech-to-text requests routed through the gateway Not checked yet Gateway-local JWT auth now accepts a comma-separated list of JWKS URLs via jwks_urls for multi-identity validation Not checked yet Requests authenticated via Gateway-local JWT are attributed to existing Portkey users when their email matches a workspace user Not checked yet Adds SCX.ai as a new OpenAI-compatible provider for chat completions Not checked yet
4 details in Everything
Portkey Frontend 1.9.6 adds Deepgram and Singulr integrations, OCR OCR Optical character recognition, converting text in an image or scanned document into machine-readable characters. It lets software search or process text that was stored as pixels. model support, Owner role, configurable API key scopes, and analytics chart APIs.
Adds Deepgram as a new provider in the dashboard Not checked yet Adds OCR model type support in the Model Catalog UI Not checked yet Adds Singulr guardrail partner logo and plugin UI Not checked yet Adds Headroom plugin Not checked yet Adds Owner role support for administration Not checked yet
+1 more
show less
Adds tokens and request chart token breakup API integration Not checked yet
6 details in Everything
Enterprise Gateway 2.20.0 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. guardrails, unified gateway/MCP mode via SERVER_MODE=unified, and proxy webhook guardrails.
MCP tool calls can now be checked against guardrails before and after execution. Not checked yet Set SERVER_MODE=unified to run the AI Gateway and MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. on a single port. Not checked yet Webhook guardrail can now run on proxy (/v1/*) requests via an opt-in executeOnProxy parameter. Not checked yet
3 details in Everything
Backend 1.25.0 introduces MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. guardrails, WIF WIF Workload Identity Federation is a Google Cloud mechanism that lets external workloads authenticate to Google APIs using short-lived tokens from a trusted identity provider, eliminating the need to manage long-lived service account keys. auth, deployment tags, and expanded Model Catalog integrations.
Adds capability_ids mappings and run_on values (beforeToolCall, afterToolCall) to attach guardrails to MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers Not checked yet Adds new MCP registry endpoint for listing available MCP servers with cursor-based pagination Not checked yet Integrates new partner guardrails for AI security scanning (singulr) and Alibaba Cloud's content moderation service Not checked yet Adds Deepgram (deepgram), Lightning AI (lightning-ai), and Headroom (headroom) to the Model Catalog Not checked yet Adds workload identity federationworkload identity federation A mechanism that lets a workload running in one cloud or platform prove its identity to another service using a trusted token exchange, eliminating the need to store long-lived credentials or secrets. (wif) as a provider authentication type for keyless cloud workload authentication Not checked yet
+9 more
show less
Adds tags (key-value pairs) support for filtering and organisation in Deployments Not checked yet Adds source_type field and MCP Gateway base URL configuration support in Deployments Not checked yet Removes default target filter from the Guardrail list API, returning both LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. and MCP guardrails Not checked yet Adds hook check data (guardrail check results and errors) to generation log responses Not checked yet Adds validation of guardrail slugs at save time for input_guardrails and output_guardrails Not checked yet Adds support for the forwardMetadata parameter in F5 Guardrails Not checked yet Adds log export deletion support via the API Not checked yet Harden API key scope enforcement so users cannot create keys with scopes exceeding their role permissions Not checked yet Adds service-role support for Bedrock plugins in self-hosting configurations Not checked yet
14 details in Everything
Portkey MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. adds Gmail integration for reading, sending, and managing email from AI agents via OAuth 2.1 OAuth 2.1 A consolidated draft of the OAuth authorization framework that merges OAuth 2.0 with its most important security BCP updates, dropping unsafe flows so tools can delegate user access without handling credentials directly.
└──▷ USE IT
Wire a Gmail MCP server into an agent so it can search and send email through Portkey's managed gateway.
json
copy
{
"gmail": {
"url": "https://mcp.portkey.ai/gmail/mcp"
}
}
Register Gmail in Portkey Advanced Configuration with the OAuth credentials from your Google Cloud app, scoped to read and send only.
json
copy
{
"client_id": "YOUR_GOOGLE_CLIENT_ID",
"client_secret": "YOUR_GOOGLE_CLIENT_SECRET",
"scope": "https://www.googleapis.com/auth/gmail.readonly https://www.googleapis.com/auth/gmail.send"
}
Adds https://mcp.portkey.ai/gmail/mcp as a hosted MCP Gateway endpoint for Gmail, enabling AI agents to read, send, and manage email without running a self-hosted binary. Not checked yet Supports Gmail OAuth 2 OAuth 2 An open authorization framework (RFC 6749) that lets a service grant limited access to a user's resources on another service without exposing credentials, giving cyber tools a standard way to authenticate against third-party APIs. .1 with manual OAuth metadata — configure client_id, client_secret, redirect_uri, and scope in Portkey Advanced Configuration using slug gmail and server URL https://gmailmcp.googleapis.com/mcp/v1. Not checked yet Exposes Gmail MCP tools list_messages (with maxResults, labelIds, q, pageToken parameters) and get_message (with id and format parameters) for agent-driven mailbox operations. Not checked yet Supports fine-grained Gmail OAuth scopes: gmail.readonly, gmail.send, gmail.modify, gmail.compose, and gmail.labels — agents only receive access to configured scopes. Not checked yet Portkey stores and automatically refreshes Gmail OAuth tokens after first-use authorization, so agents do not need to re-authenticate on subsequent calls. Not checked yet
5 details in Everything
Portkey adds a Registry API for approved MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers, configurable semantic cache embedding embedding Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. providers, and OAuth metadata controls for MCP integrations.
└──▷ TRY IT
Fetch your organization's full approved MCP server catalog for use with a governance-aware MCP client that restricts users to sanctioned servers.
copy
$ curl https://mcp.portkey.ai/v0.1/servers \
-H "x-portkey-api-key: $PORTKEY_API_KEY"
Register a confidential Google OAuth App in Portkey MCP to obtain refresh tokens refresh tokens A credential used to obtain a new access token without signing in again. It is sent to the authorization service rather than used directly to call the protected API. so sessions survive access token access token A credential that authorizes a client to use a service or API. It usually has limited permissions and a lifetime; anyone holding it may be able to use those permissions. expiry.
json
copy
{
"client_id": "...apps.googleusercontent.com",
"client_secret": "your_google_oauth_client_secret",
"scope": "https://www.googleapis.com/auth/drive.readonly",
"authorization_params": {
"access_type": "offline",
"prompt": "consent"
}
}
Adds GET https://mcp.portkey.ai/v0.1/servers Registry API Beta serving approved MCP servers as a standards-compliant server.json catalog in MCP Registry v0.1 format, authenticated via x-portkey-api-key header with mcp_servers.list scope. Not checked yet Adds query parameters limit (1–100), cursor, search, updated_after (ISO 8601 ISO 8601 An international standard for representing dates and times as text, using formats like 2025-04-23T14:00:00Z. Tools adopt it to ensure timestamps are unambiguous and sortable across systems and locales. ), and workspace_id (UUID UUID A universally unique identifier, usually a 128-bit value used to identify an object across systems. It is designed to make independently generated identifiers unlikely to collide. or slug) to the GET /v0.1/servers endpoint for pagination, filtering, and incremental syncs. Not checked yet Adds SEMANTIC_CACHE_EMBEDDING_PROVIDER environment variable supporting openai, azure-openai, google (Gemini embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. ), and vertex-ai to configure which provider generates embeddings for semantic caching. Not checked yet Adds SEMANTIC_CACHE_EMBEDDINGS_URL, SEMANTIC_CACHE_EMBEDDING_MODEL, SEMANTIC_CACHE_EMBEDDING_DIMENSIONS, and SEMANTIC_CACHE_EMBEDDING_API_KEY environment variables to configure the chosen embedding provider for semantic cache. Not checked yet Adds client_id, client_secret, and authorization_params fields to the OAuth Metadata configuration in the MCP Registry, allowing pre-registered OAuth clients and disabling Dynamic Client Registration. Not checked yet
+3 more
show less
Adds token_endpoint_auth_method field to OAuth metadata, accepting client_secret_post or client_secret_basic for confidential OAuth app clients (default is none). Not checked yet Adds authorization_params object to OAuth metadata for appending extra string-valued query parameters to upstream authorization URLs, enabling provider-specific flows such as Google's access_type=offline and prompt=consent for refresh token refresh token A credential used to obtain a new access token without signing in again. It is sent to the authorization service rather than used directly to call the protected API. acquisition. Not checked yet Exposes Portkey's OAuth callback URL at https://mcp.portkey.ai/oauth/upstream-callback (or <MCP_GATEWAY_BASE_URL>/oauth/upstream-callback for self-hosted deployments) for MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. App registration. Not checked yet
8 details in Everything
Portkey Prometheus metrics gain PROMETHEUS_EXTRA_LABELS to expose API key and config name as metric labels.
└──▷ USE IT
Break down Prometheus metrics by Portkey API key name and gateway config name to isolate costs or latency per team or workflow.
.env
copy
PROMETHEUS_EXTRA_LABELS=apiKeyName,configName
Adds PROMETHEUS_EXTRA_LABELS environment variable (comma-separated string, default empty) to attach apiKeyName and/or configName as labels on every custom Prometheus metric, enabling per-key and per-config filtering in dashboards. Not checked yet
1 detail in Everything
Portkey adds MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. , Agent Gateway, Coding Agent governance, gRPC gRPC An open-source remote procedure call framework from Google that uses HTTP/2 and Protocol Buffers to let services call each other's functions across a network, giving tools low-latency, strongly typed inter-process communication. transport, OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. observability, and Nitro Mode across its AI gateway platform.
New MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Gateway provides centralized authentication, access control, and governance for MCP servers, with a Registry API Beta to serve approved servers as a standard endpoint. Not checked yet Adds OAuth 2.1 OAuth 2.1 A consolidated draft of the OAuth authorization framework that merges OAuth 2.0 with its most important security BCP updates, dropping unsafe flows so tools can delegate user access without handling credentials directly. built-in authentication (OAuth ), external identity-provider support (Bring Your Own Auth ), JWT Validation , Identity Forwarding , Forwarding Headers , Custom Auth , and Authorization controls for MCP Gateway. Not checked yet Adds Tool Provisioning to control which tools, resources, and prompts are exposed to which workspaces and users through the MCP Gateway. Not checked yet Adds Team Provisioning (access control) to control which workspaces and users can access specific MCP servers. Not checked yet Adds Rate Limits and Circuit Breakers for MCP tool call requests and token consumption within the MCP Gateway. Not checked yet
+30 more
show less
Supports adding internal and external MCP servers (e.g. Linear) to a managed MCP Registry with add/manage/govern workflows. Not checked yet New Remote MCP support in the AI Gateway routes requests to MCP servers directly through the gateway. Not checked yet New Agent Gateway provides centralized authentication, access control, and observability for AI agents. Not checked yet New Coding Agents feature adds a governance layer for Claude Code, Codex, and similar coding agents. Not checked yet New gRPC Beta transport lets the AI Gateway accept gRPC as an alternative protocol to HTTP. Not checked yet New Nitro Mode Beta forwards the request body directly to the provider, bypassing gateway transformation for maximum performance. Not checked yet Adds OpenTelemetry integration for LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. observability, supporting any OpenTelemetry-compatible instrumentation library. Not checked yet New Auto-Instrumentation [BETA] enables automatic tracing of LLM calls without manual SDK instrumentation. Not checked yet New Open Responses endpoint supports the Responses API format with any LLM provider. Not checked yet New Messages endpoint supports Anthropic's Messages API format with any provider through the Universal API. Not checked yet New Unified Batch Inference (batches) runs large-scale inference jobs through one API across providers, with Guardrails support via Guardrails for Batches . Not checked yet New Files API allows uploading files to Portkey and reusing content across requests. Not checked yet New Fine-tuning support runs fine-tuning jobs through the Portkey Gateway. Not checked yet New Circuit Breaker in the AI Gateway automatically stops routing to unhealthy targets. Not checked yet New Model Catalog provides a single pane to view and manage every AI provider integration, including Integrations (credential store), Adding Custom Models , Adding Pricing Adjustments , and Overriding Model Details . Not checked yet Adds Portkey Models as an open-source pricing and configuration database for LLM models. Not checked yet Adds Budget Limits to set cost limits per integration/provider key. Not checked yet Adds Guardrails for Embedding Requests to apply security and data validation to embedding embedding Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. API calls. Not checked yet Adds PII Redaction guardrail to replace sensitive data in requests before they reach providers. Not checked yet Adds Creating Raw Guardrails (in JSON) mode to define guardrails directly as JSON config. Not checked yet Adds Forwarding Headers for guardrails to pass client request headers through to guardrail services. Not checked yet Adds Bring Your Own Guardrails integration support for custom guardrail providers. Not checked yet New Prompt Partials let practitioners save reusable prompt components and compose them across templates. Not checked yet Adds Sharing Prompts and Partials to share prompt templates and partials across workspaces. Not checked yet Adds Logs Export to access Portkey log data for external analysis. Not checked yet Adds Feedback APIs to attach human or automated feedback signals to logged LLM requests. Not checked yet Adds Metadata support to attach custom context key-value pairs to AI requests for filtering and analysis. Not checked yet Adds Connect Bedrock with Amazon Assumed Role integration for IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. role-based Bedrock authentication. Not checked yet Adds Canary Testing to split traffic across LLM variants for safe rollouts. Not checked yet Adds Realtime API support to use OpenAI's Realtime API with logs and cost tracking through the gateway. Not checked yet
35 details in Everything
Portkey Enterprise Gateway 2.19 adds Deepgram, OAuth client credentials, Vertex AI OCR OCR Optical character recognition, converting text in an image or scanned document into machine-readable characters. It lets software search or process text that was stored as pixels. , MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Registry Proxy and cost tracking for Meshy/Tripo3D.
Adds Deepgram provider integration for speech-to-text and text-to-speech with full observability Not checked yet Allows OpenAI-compatible integrations to authenticate to upstream providers using OAuth Client Credentials OAuth Client Credentials An OAuth 2.0 grant type where a service authenticates directly with an authorization server using its own ID and secret, receiving a token to call APIs without any user involved. grant (RFC 6749) instead of static API keys Not checked yet Extends /v1/ocr endpoint to support Mistral OCR models on Google Vertex AI with per-page pricing Not checked yet Adds Responses and Messages endpoints support for the Qwen provider, along with additional non-OpenAI parameters Not checked yet Introduces Headroom plugin to compress request context before model ingestion, configured via standard guardrails workflow Not checked yet
+4 more
show less
Uses provider-reported cost for billing attribution when available (starting with OpenRouter OpenRouter A unified API gateway that routes requests to dozens of LLM providers under one endpoint, letting cyber tools swap or compare models without rewriting provider-specific integration code. ) Not checked yet Enables MCP Registry Proxy in the MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. to expose registry endpoints like server listings directly through the gateway Not checked yet Adds credit-based cost tracking for Meshy and Tripo3D 3D-generation providers with a 24h duplicate-billing protection window Not checked yet Supports per-request AWS Bedrock STS STS AWS Security Token Service, an Amazon Web Services API that issues short-lived credentials for IAM roles, letting cyber tools authenticate to AWS without storing long-term secrets. session tags via the AWS_BEDROCK_STS_SESSION_TAGS_ENABLED environment variable Not checked yet
9 details in Everything
└──▷ BREAKING ON UPGRADE
! Removed the deprecated temperature handling for Claude 4 models in Amazon Bedrock! MCP Gateway GET and DELETE requests now return 405 because the gateway is stateless
Backend v1.24.2 adds configurable auto-create scopes for user API keys and improves JWKS JWKS A JSON Web Key Set, a published collection of cryptographic keys. Applications use it to find the public key needed to verify a token's signature. fetch resilience.
Adds user_api_key_auto_create_scopes organisation setting to control default data-plane scopes for auto-provisioned workspace-user API keys Not checked yet Improves JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. authentication resilience in hybrid deployments by trying direct JWKS fetching before falling back to private link routing Not checked yet
2 details in Everything
└──▷ BREAKING ON UPGRADE
! The forwardHeaders parameter is removed from Portkey-managed PRO check schemas (portkey.moderateContent, portkey.language, portkey.pii, portkey.gibberish)
Portkey MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. gains rate limiting by request count or token consumption, plus content filters and approval workflows.
Adds rate limiting for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool calls, throttleable by request count or token consumption, scoped to API key, server, or individual tool. Not checked yet Adds content filters and approval workflows configurable per MCP server. Not checked yet
2 details in Everything
Portkey adds MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. rate limiting, per-model custom host/headers, and an OCR OCR Optical character recognition, converting text in an image or scanned document into machine-readable characters. It lets software search or process text that was stored as pixels. inference endpoint
└──▷ TRY IT
Throttle a specific MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool (send_message) on the Slack server to 100 calls per minute to protect downstream API quotas.
copy
$ curl -X POST "https://api.portkey.ai/v1/policies/rate-limits" \
-H "x-portkey-api-key: <admin-api-key>" \
-H "Content-Type: application/json" \
-d '{
"name": "Slack send_message limit",
"description": "Throttle send_message calls on the Slack MCP server",
"target": "mcp_tools",
"limit": { "unit": "rpm", "value": 100 },
"conditions": [
{ "key": "mcp_server", "value": "slack" },
{ "key": "mcp_tool", "value": "send_message" }
]
}'
Pin a custom upstream URL and tenant headers on a single Model Catalog entry so it routes to an internal regional endpoint without affecting other models in the same integration.
copy
$ curl -X PUT "https://api.portkey.ai/v1/integrations/YOUR_INTEGRATION_SLUG/models" \
-H "x-portkey-api-key: <admin-api-key>" \
-H "Content-Type: application/json" \
-d '{
"models": [{
"slug": "my-custom-model-v1",
"is_custom": true,
"base_model_slug": "gpt-4o",
"custom_host": "https://llm.internal.example.com/v1",
"custom_headers": {
"x-tenant-id": "acme-prod",
"x-region": "us-east-1"
}
}]
}'
Cap total token consumption on the GitHub MCP server to 500,000 tokens per day to control costs across all users in a workspace.
copy
$ curl -X POST "https://api.portkey.ai/v1/policies/rate-limits" \
-H "x-portkey-api-key: <admin-api-key>" \
-H "Content-Type: application/json" \
-d '{
"name": "GitHub server token limit",
"target": "mcp_tools",
"limit": { "unit": "tpd", "value": 500000 },
"conditions": [
{ "key": "mcp_server", "value": "github" }
]
}'
Adds target: mcp_tools field to rate limit policies so MCP tool call traffic is governed independently from LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. traffic — scoped to workspace, server, tool, API key, or metadata.*. Not checked yet Adds mcp_server and mcp_tool condition/group-by keys for rate limit policies, enabling per-server and per-tool throttling (e.g. cap the send_message tool to 100 rpm or the GitHub server to 500,000 tokens per day with unit: tpd). Not checked yet Supports rpm, rph, rpd, and rpw (and token equivalents) as rate limit units for mcp_tools policies, with AND-logic multi-condition matching and an excludes modifier to carve out specific tools. Not checked yet Creates MCP rate limit policies via POST https://api.portkey.ai/v1/policies/rate-limits with target set to mcp_tools; requires Gateway v2.18.0+ and Backend v1.24.0+. Not checked yet Adds per-model custom_host and custom_headers fields to Model Catalog entries (set via PUT https://api.portkey.ai/v1/integrations/YOUR_INTEGRATION_SLUG/models under models[].configurations), letting different models in the same integration route to different upstreams or send different headers — model-level custom_headers override integration-level values. Not checked yet
+1 more
show less
Adds an OCR inference endpoint to extract text and structured content from PDFs and images. Not checked yet
6 details in Everything
└──▷ BREAKING ON UPGRADE
! A rate limit policy's target field is immutable after creation — to switch between llm and mcp_tools, you must archive the existing policy and create a new one.
Portkey adds MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. rate limiting and a new OCR OCR Optical character recognition, converting text in an image or scanned document into machine-readable characters. It lets software search or process text that was stored as pixels. inference endpoint for document text extraction.
Adds rate limiting for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool call requests and token consumption via the MCP Gateway, documented under rate-limits. Not checked yet
1 detail in Everything
Portkey Backend adds OAuth Client Credentials OAuth Client Credentials An OAuth 2.0 grant type where a service authenticates directly with an authorization server using its own ID and secret, receiving a token to call APIs without any user involved. auth for OpenAI integrations and Azure workload identity workload identity An identity assigned to software, such as a service or container, rather than a person. It lets the workload authenticate and receive permissions without sharing a user's credentials. for self-hosted log stores.
Adds oauthClientCredentials as a valid value for the provider_auth_type field in integration configs to enable OAuth 2.0 OAuth 2.0 An open authorization framework (IETF RFC 6749) that lets a service grant limited API access to a third party without sharing credentials, giving cyber tools a standard way to authenticate against external platforms. Client Credentials Client Credentials An OAuth 2.0 grant type where a service authenticates directly with an authorization server using its own ID and secret, with no user involved, to obtain an access token for machine-to-machine API calls. grant for upstream providers like OpenAI Not checked yet Adds support for AZURE_AUTH_MODE=workload environment variable to enable Azure Workload Identity authentication for log stores in self-hosted deployments Not checked yet
2 details in Everything
└──▷ BREAKING ON UPGRADE
! The forwardHeaders parameter is removed from 22 local-only guardrail check schemas (regex, model allowlist, word count, etc.) where it had no effect
Portkey Enterprise Gateway v2.18.0 adds native OCR OCR Optical character recognition, converting text in an image or scanned document into machine-readable characters. It lets software search or process text that was stored as pixels. endpoint, Singulr guardrail, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. rate limits, and header forwarding.
Adds POST /v1/ocr endpoint to route OCR requests through gateway retries, fallbacks, load balancing, caching, logging, and pricing with support for Mistral AI and Azure AI Foundry Not checked yet Adds Singulr partner guardrail plugin for request and response scanning via the standard guardrails workflow Not checked yet Enables MCP tool call rate limits to throttle invocation volume per configured limits Not checked yet Adds configurable guardrail header forwarding, allowing client headers like x-session-id and traceparent to be sent to upstream providers Not checked yet
4 details in Everything
Backend 1.24.0 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool call rate limiting, forwardHeaders validation, A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. analytics, and Redis auth for self-hosting
Adds target: mcp_tools to Rate Limit Policies for MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. enforcement via OAuth introspection and LIST filtering Not checked yet Validates Guardrail forwardHeaders at create/update time and defines them in provider schemas for static export Not checked yet Returns separate token, request, and error counters for LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. , MCP, and A2A traffic in Analytics chart APIs Not checked yet Adds IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. authentication for AWS ElastiCache via AWS_REDIS_AUTH_MODE=iam and related env vars Not checked yet Adds workload identity workload identity An identity assigned to software, such as a service or container, rather than a person. It lets the workload authenticate and receive permissions without sharing a user's credentials. support for Azure Cache for Redis via AZURE_REDIS_WORKLOAD_CLIENT_ID Not checked yet
+1 more
show less
Adds gcp-memory-store cache type with GCP workload identity auth via GCP_REDIS_AUTH_MODE Not checked yet
6 details in Everything
Portkey Frontend 1.9.5 adds Lightning AI provider support and model-level custom headers configuration.
└──▷ TRY IT
Ship GCS logs from an AWS-hosted gateway without storing long-lived GCP credentials — set both WIF WIF Workload Identity Federation is a Google Cloud mechanism that lets external workloads authenticate to Google APIs using short-lived tokens from a trusted identity provider, eliminating the need to manage long-lived service account keys. env vars and use the gcs_assume log storage flow.
copy
$ GCP_WIF_AUDIENCE=//iam.googleapis.com/projects/123/locations/global/workloadIdentityPools/my-pool/providers/my-provider \
GCP_WIF_SERVICE_ACCOUNT_EMAIL=portkey-logger@my-project.iam.gserviceaccount.com \
docker run portkey/gateway:latest
Adds Secret References so secret_mappings can point virtual keys and integrations at credentials stored in AWS Secrets Manager, Azure Key Vault, or HashiCorp Vault — Portkey fetches values at runtime instead of storing keys directly. Not checked yet Adds weekly (rpw) budget and usage windows so rate-limit caps align with weekly spend planning, not only per-minute or monthly aggregates. Not checked yet Adds endpoint-scoped rate limits so chat completions, embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. , and admin routes can each carry independent limits instead of one global rule. Not checked yet Adds GCP_WIF_AUDIENCE and GCP_WIF_SERVICE_ACCOUNT_EMAIL environment variables to authenticate GCS log writes through GCP Workload Identity Federation (gcs_assume flow) when the gateway runs in AWS, eliminating long-lived GCP keys in AWS config. Not checked yet Enables analytics for archived workspaces and accepts workspace slugs (alongside IDs) in saved filters, keeping reporting stable as workspaces are wound down or renamed. Not checked yet
+2 more
show less
Integrates Zscaler AI Guard as a guardrail partner via beforeRequestHook and afterRequestHook, requiring a policyId and supporting a configurable timeout (default 10000 ms). Not checked yet Maps Portkey metadata to Vertex AI resource labels; adds enterprise search grounding via enterpriseWebSearch / enterprise_web_search; enables AWS workloads to reach Vertex AI using GCP_WIF_AUDIENCE and GCP_WIF_SERVICE_ACCOUNT_EMAIL. Not checked yet
└──▷ BREAKING ON UPGRADE
! The gateway no longer forwards the x-portkey-forward-headxers header, preventing header-forwarding loops — any setup relying on that header being passed through will stop working.
└──▷ TRY IT
Route GCS log writes through GCP Workload Identity Federation when the Portkey gateway runs in AWS, avoiding static GCP service-account keys.
copy
$ GCP_WIF_AUDIENCE=//iam.googleapis.com/projects/123456/locations/global/workloadIdentityPools/my-pool/providers/my-provider \
GCP_WIF_SERVICE_ACCOUNT_EMAIL=portkey-logs@my-project.iam.gserviceaccount.com \
docker run portkey/gateway:latest
Apply Zscaler AI Guard detection policies to all LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. requests and responses with a custom evaluation timeout.
json
copy
{
"guardrails": [
{
"provider": "zscaler",
"hooks": ["beforeRequestHook", "afterRequestHook"],
"policyId": "your-zscaler-policy-id",
"timeout": 8000
}
]
}
Adds Secret References so credentials stored in AWS Secrets Manager, Azure Key Vault, or HashiCorp Vault are fetched at runtime via secret_mappings, keeping plaintext keys out of Portkey config. Not checked yet Adds weekly budget/usage windows (rpw) and endpoint-scoped rate limits, letting teams cap spend per API surface (chat completions, embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. , admin routes) independently. Not checked yet Adds Zscaler AI Guard guardrail integration applying Zscaler Detection Policies via beforeRequestHook / afterRequestHook, with required policyId and optional timeout (default 10 000 ms). Not checked yet Adds required metadata key–value guardrails that block requests missing or carrying invalid required metadata fields before they reach the model. Not checked yet Adds tools, tool_choice, and stream_options for deepseek-chat; maps reasoning_effort to thinking mode and surfaces reasoning_content in streams for deepseek-reasoner. Not checked yet
+2 more
show less
Adds Vertex AI enterprise search grounding via enterpriseWebSearch / enterprise_web_search (with separate cost attribution) and AWS-to-Vertex connectivity using GCP_WIF_AUDIENCE / GCP_WIF_SERVICE_ACCOUNT_EMAIL. Not checked yet Adds Vertex AI resource label support by mapping Portkey metadata to Vertex resource labels. Not checked yet
Portkey Backend 1.23.0 introduces hardened SSRF SSRF Server-side request forgery, an attack that tricks a server into making requests chosen by an attacker. Those requests can reach internal services the attacker cannot access directly. checks for gateway URLs and a new DB index.
Adds hardened SSRF checks for prompt playground and proxy calls by blocking IMDS, metadata endpoints, and private DNS-rebind targets for admin-supplied gateway URLs Not checked yet Auto-adds env-configured gateway hostnames to the trusted host set Not checked yet Adds index on api_keys.last_updated_at for improved query performance Not checked yet
3 details in Everything
Portkey March 2026 adds vault-backed Secret References, weekly/endpoint-scoped rate limits, cross-cloud GCS log delivery, and four new guardrail integrations.
└──▷ USE IT
Keep LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. provider credentials out of Portkey by pointing a virtual key at a secret already stored in AWS Secrets Manager.
json
copy
{
"virtual_key": "my-openai-key",
"secret_mappings": {
"api_key": "arn:aws:secretsmanager:us-east-1:123456789012:secret:prod/openai-api-key"
}
}
Route GCS log writes through GCP Workload Identity Federation when the Portkey gateway runs in AWS, avoiding long-lived GCP credentials in your AWS environment.
copy
$ GCP_WIF_AUDIENCE=//iam.googleapis.com/projects/123456/locations/global/workloadIdentityPools/my-pool/providers/my-provider \
GCP_WIF_SERVICE_ACCOUNT_EMAIL=portkey-log-writer@my-project.iam.gserviceaccount.com \
docker run portkey/gateway ...
Adds Secret References so credentials stored in AWS Secrets Manager, Azure Key Vault, or HashiCorp Vault can be mapped to integrations and virtual keys via secret_mappings, with Portkey fetching values at runtime instead of storing them directly. Not checked yet Adds rpw (requests-per-week) budget and usage windows so rate limits can align with weekly planning cycles, alongside endpoint-scoped limits that let chat completions, embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. , and admin routes carry independent caps. Not checked yet Adds GCP_WIF_AUDIENCE and GCP_WIF_SERVICE_ACCOUNT_EMAIL environment variables to enable GCP Workload Identity Federation (gcs_assume style) for GCS log delivery when the gateway runs in AWS, eliminating static cross-cloud credentials. Not checked yet Adds Zscaler AI Guard guardrail integration using beforeRequestHook and afterRequestHook hooks, requiring a policyId and supporting a configurable timeout (default 10000 ms) to apply Zscaler Detection Policies to LLM inputs and outputs. Not checked yet Adds Akto Agentic Security as a guardrails partner to scan LLM inputs and outputs for prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. and sensitive data leakage via hooks with a configurable timeout (default 5000 ms). Not checked yet
+9 more
show less
Adds customHost configuration to the Bedrock guardrail plugin so evaluations can target private or regional Bedrock-compatible endpoints instead of the default public Bedrock URLs. Not checked yet Adds required metadata key–value guardrails that block requests at the gateway before they reach the model if required metadata fields are missing or invalid. Not checked yet Extends analytics so organization admins and owners can include archived workspaces in graphs and summaries; saved filters now accept workspace slugs alongside IDs. Not checked yet Adds DeepInfra provider support with tool calling tool calling A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. via tools, tool_choice, and parallel_tool_calls, plus completions and embeddings endpoints. Not checked yet Adds stream_options support for DeepSeek deepseek-chat, and maps reasoning_effort to thinking mode for deepseek-reasoner, returning reasoning_content in streams. Not checked yet Extends Bedrock batch inference to support embeddings in addition to chat completions. Not checked yet Adds Vertex AI enterprise web search grounding via enterpriseWebSearch / enterprise_web_search with separate cost attribution, Portkey metadata mapping to Vertex resource labels, and AWS-to-Vertex access via GCP_WIF_AUDIENCE and GCP_WIF_SERVICE_ACCOUNT_EMAIL. Not checked yet Adds Azure AI Foundry rerank support for Cohere rerank models (e.g. cohere.Cohere-rerank-v4.0-pro), with the gateway stripping the cohere. prefix for the provider. Not checked yet OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. GenAI semantic spans now follow semconv 1.40.0 for inference and embeddings, with OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. exporter support for guardrail flows and custom resource attributes. Not checked yet
14 details in Everything
Enterprise Gateway 2.17.0 adds Databricks Responses API support, new Anthropic beta parameters, and a beta flag for Responses API 2026-07-30
Databricks provider now supports the Responses API, enabling OpenAI-compatible Responses format for Databricks-served models Not checked yet New Anthropic beta parameters can now be passed through to the Anthropic provider: inference_geo, diagnostics, fallbacks, and context_management Not checked yet Beta flag use-responses-api-2026-07-30 enables the latest Responses API schema version via the x-portkey-beta header Not checked yet
3 details in Everything
Portkey Backend 1.22.0 adds organisation guardrail defaults, workspace exclusions via API, and new OAuth scopes.
Adds GET /v1/workspace-exclusions/input-guardrails and /v1/workspace-exclusions/output-guardrails to exempt workspaces from org-level defaults. Not checked yet Adds PUT /v1/admin/organisation/defaults to set organisation-wide input_guardrails and output_guardrails. Not checked yet New API scopes organisation_settings.*, organisation_guardrails.*, and organisation_exclusions.* for fine-grained access control. Not checked yet OIDC OIDC OpenID Connect, a sign-in protocol built on OAuth 2.0. An application uses identity information from a trusted provider instead of maintaining a separate password for each user. settings now accept token_endpoint_auth_method and jwks key set, enabling private_key_jwt authentication. Not checked yet Model Catalog GET provider details accepts include_configurations=true to retrieve system auth configs with masked secrets. Not checked yet
5 details in Everything
Portkey Enterprise adds configurable custom Gateway URLs for self-hosted AI and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. gateway deployments.
└──▷ HOW TO FIND IT
Point the Portkey dashboard at your self-hosted AI gateway so all generated code snippets and playground completions route through your own infrastructure.
📍 In the dashboard, go to Settings › Organisation › General, scroll to the Gateway URLs section, enter your base URL in the Gateway URL field (e.g. https://gateway.yourcompany.com), then click outside the field to save.
Register a self-hosted MCP gateway so MCP server endpoint URLs (e.g. https://mcp.yourcompany.com/my-server/mcp) are constructed from your own domain.
📍 In the dashboard, go to Settings › Organisation › General, scroll to the Gateway URLs section, enter your MCP gateway base URL in the MCP Gateway URL field (e.g. https://mcp.yourcompany.com), then click outside the field to save.
Adds organisation-level Gateway URL setting so self-hosted AI gateway deployments replace Portkey's cloud endpoint (https://api.portkey.ai/v1) in code snippets, Model Catalog, and playground completions. Not checked yet Adds organisation-level MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. URL setting to point MCP server endpoint construction at a self-hosted MCP gateway instead of https://mcp.portkey.ai. Not checked yet Dashboard auto-normalises trailing /v1 on the Gateway URL field, saving automatically on focus-out with no separate save button. Not checked yet
3 details in Everything
Portkey adds vault-backed secret references, weekly/endpoint-scoped rate limits, two new guardrail integrations, and broader provider coverage.
└──▷ USE IT
Apply Zscaler Detection Policies to all LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. traffic by wiring Zscaler AI Guard into your Portkey config as a guardrail hook.
json
copy
{
"guardrails": [
{
"type": "zscaler",
"hooks": ["beforeRequestHook", "afterRequestHook"],
"policyId": "<your-zscaler-policy-id>",
"timeout": 10000
}
]
}
Set a weekly spend cap scoped only to the embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. endpoint so it doesn't share budget with chat completions.
📍 In the Portkey console, go to Budget & Rate Limit Policies, create a new policy, set the window to rpw (weekly), set the endpoint scope to embeddings, and enter your desired token or cost limit.
Introduces weekly rate/budget windows (rpw) and endpoint-scoped rate limits, letting teams cap spend per API surface (chat completions, embeddings, admin routes, etc.) independently. Not checked yet
1 detail in Everything
Portkey forwards request metadata as AWS STS AWS STS AWS Security Token Service, an Amazon Web service that issues short-lived credentials for IAM roles, letting tools authenticate to AWS APIs without storing long-term secrets. session tags, enabling per-app Bedrock cost attribution in Cost Explorer and CloudTrail CloudTrail AWS service that records API calls and account activity across an AWS environment, giving cyber tools an audit log to detect anomalous or malicious actions. .
└──▷ TRY IT
Attribute Bedrock LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. costs to a specific app, team, and environment in AWS Cost Explorer by tagging requests at the gateway level.
copy
$ curl https://api.portkey.ai/v1/chat/completions \
-H "x-portkey-provider: $PROVIDER_SLUG" \
-H 'x-portkey-metadata: {"app": "chatbot", "team": "platform", "env": "prod"}' \
-d '{ "model": "anthropic.claude-3-5-sonnet-20240620-v1:0", "messages": [{"role": "user", "content": "Hello"}] }'
Supports AWS STS STS AWS Security Token Service, an Amazon Web Services API that issues short-lived credentials for IAM roles, letting cyber tools authenticate to AWS without storing long-term secrets. session tags for Bedrock: metadata sent via x-portkey-metadata is forwarded as STS session tags, enabling spend segregation in AWS Cost Explorer and CloudTrail without separate IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. roles per application. Not checked yet Clarifies that model conditions and group_by keys use the request model name (e.g. gpt-4.1), not the provider's response model name (e.g. gpt-4.1-2025-06-01), which matters for Azure OpenAI and similar providers. Not checked yet
2 details in Everything
Portkey forwards request metadata as AWS STS AWS STS AWS Security Token Service, an Amazon Web service that issues short-lived credentials for IAM roles, letting tools authenticate to AWS APIs without storing long-term secrets. session tags, enabling per-app Bedrock cost attribution in Cost Explorer and CloudTrail CloudTrail AWS service that records API calls and account activity across an AWS environment, giving cyber tools an audit log to detect anomalous or malicious actions. .
└──▷ TRY IT
Attribute Bedrock LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. costs to a specific app, team, and environment in AWS Cost Explorer by tagging requests at the gateway level.
copy
$ curl https://api.portkey.ai/v1/chat/completions \
-H "x-portkey-provider: $PROVIDER_SLUG" \
-H 'x-portkey-metadata: {"app": "chatbot", "team": "platform", "env": "prod"}' \
-d '{ "model": "anthropic.claude-3-5-sonnet-20240620-v1:0", "messages": [{"role": "user", "content": "Hello"}] }'
Supports AWS STS STS AWS Security Token Service, an Amazon Web Services API that issues short-lived credentials for IAM roles, letting cyber tools authenticate to AWS without storing long-term secrets. session tags for Bedrock: metadata sent via x-portkey-metadata is forwarded as STS session tags, enabling spend segregation in AWS Cost Explorer and CloudTrail without separate IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. roles per application. Not checked yet Clarifies that model conditions and group_by keys use the request model name (e.g. gpt-4.1), not the provider's response model name (e.g. gpt-4.1-2025-06-01), which matters for Azure OpenAI and similar providers. Not checked yet
2 details in Everything
Portkey adds support for configuring custom gateway endpoints for organizations.
Portkey adds support for configuring custom gateway endpoints for organizations.
Portkey March 2026: vault-backed credentials, weekly rate limits, cross-cloud GCS logging, and four new guardrail integrations.
└──▷ USE IT
Apply Zscaler AI Guard detection policies to all LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. inputs and outputs by wiring in your existing policyId.
json
copy
{
"guardrails": [
{
"type": "zscaler",
"hooks": ["beforeRequestHook", "afterRequestHook"],
"policyId": "<your-zscaler-policy-id>",
"timeout": 10000
}
]
}
Adds Secret References to pull credentials from AWS Secrets Manager, Azure Key Vault, or HashiCorp Vault at runtime via secret_mappings, keeping secrets out of Portkey config. Not checked yet Supports weekly budget and usage windows (rpw) for rate limits, enabling caps aligned to weekly planning and review cycles. Not checked yet Adds endpoint-scoped rate limits so chat completions, embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. , and admin routes can carry independent limits instead of a single global rule. Not checked yet Enables GCP Workload Identity Federation log delivery from AWS-hosted gateways to GCS via GCP_WIF_AUDIENCE and GCP_WIF_SERVICE_ACCOUNT_EMAIL, eliminating long-lived cross-cloud keys. Not checked yet Allows organization admins to include archived workspaces in analytics graphs and summaries; saved filters now accept workspace slugs alongside IDs. Not checked yet
+11 more
show less
Integrates Zscaler AI Guard as a guardrail partner, applying Zscaler Detection Policies to LLM inputs and outputs via beforeRequestHook and afterRequestHook with a required policyId. Not checked yet Integrates Akto Agentic Security as a guardrail partner for scanning LLM inputs and outputs for prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. and sensitive data leakage. Not checked yet Adds customHost to the Bedrock Guardrails plugin, routing guardrail evaluation to private or regional Bedrock-compatible endpoints. Not checked yet Adds required metadata key–value guardrails that block requests missing specified metadata fields before they reach the model. Not checked yet Adds DeepInfra provider support with tool calling tool calling A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. (tools, tool_choice, parallel_tool_calls), completions, and embeddings endpoints. Not checked yet Expands DeepSeek support: deepseek-chat gains tools, tool_choice, and stream_options; deepseek-reasoner maps reasoning_effort to thinking mode and returns reasoning_content in streams. Not checked yet Extends Bedrock batch inference to support embeddings jobs alongside existing chat completions batch patterns. Not checked yet Maps Portkey metadata to Vertex AI resource labels and adds enterprise search grounding via enterpriseWebSearch / enterprise_web_search with separate cost attribution. Not checked yet Enables AWS workloads to reach Vertex AI through AWS–GCP WIF WIF Workload Identity Federation is a Google Cloud mechanism that lets external workloads authenticate to Google APIs using short-lived tokens from a trusted identity provider, eliminating the need to manage long-lived service account keys. using GCP_WIF_AUDIENCE and GCP_WIF_SERVICE_ACCOUNT_EMAIL. Not checked yet Adds Azure AI Foundry rerank support for Cohere rerank models (e.g., cohere.Cohere-rerank-v4.0-pro), with the gateway stripping the cohere. prefix for the provider. Not checked yet Updates OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. GenAI semantic spans to semconv 1.40.0 for inference and embeddings, with OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. exporter support for guardrail flows and custom resource attributes. Not checked yet
16 details in Everything
Portkey Enterprise Gateway 2.16 adds Responses API routing, Lightning AI provider, Akto guardrails, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. user attribution.
Routes Anthropic Messages API requests to OpenAI Responses API models (e.g. codex) with automatic transformation Not checked yet Adds Lightning AI provider integration for chat completions Not checked yet Enables Akto guardrail scanning for both request and response payloads Not checked yet Attributes MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. log entries to specific users via OAuth claims or API key name Not checked yet
4 details in Everything
Portkey Frontend 1.9.4 adds SSO SSO Single sign-on, using one identity provider to sign in to multiple applications. It reduces separate passwords and centralizes account and access management. client ID login, SSO auto-provisioning toggle, Soft Deny guardrails mode, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. transparency UI.
Adds SSO Client ID login support with improved redirect flow when organisation_id is present Not checked yet Adds UI toggle for SSO auto user provisioning Not checked yet Adds Soft Deny (200) toggle for guardrails, allowing denied requests to return a 200 response instead of a hard block Not checked yet MCP consent page now displays the redirect URI for transparency Not checked yet Adds org and workspace details on the MCP consent no access page Not checked yet
+1 more
show less
Adds Databricks to the provider list in the dashboard Not checked yet
6 details in Everything
Portkey adds Prisma AIRS agentic scan controls, soft-deny guardrails, provider-backed model listing, and Continue.dev integration
└──▷ USE IT
Reduce Prisma AIRS false positives when using agentic clients (Claude Code, Cursor, Cline) by scanning only the last user message and stripping scaffolding wrappers.
json
copy
{
"scan_scope": "last_user_message",
"strip_scaffolding": true
}
Keep an agentic session alive when a guardrail fires by returning a soft deny as HTTP 200 instead of HTTP 446.
json
copy
{
"soft_deny_200": true
}
Adds scan_scope and strip_scaffolding parameters to the Palo Alto Networks Prisma AIRS guardrail, enabling fine-grained control over which messages are scanned and reducing false positives for agentic clients like Claude Code, Cursor, and Cline. Not checked yet Adds soft_deny_200 flag on guardrail checks: denials return HTTP 200 with the error as a chat completion response instead of HTTP 446, keeping sessions alive for clients that treat 4xx as fatal. Not checked yet GET /v1/models now routes through the gateway's provider-backed model listing handler, calling the upstream provider and returning a normalized model list with response transforms applied. Not checked yet Anthropic cost attribution now differentiates batch (50% discount), fast, and standard pricing tiers for multidimensional cost tracking. Not checked yet xAI server-side tool invocation costs (file search, web search) are now tracked for cost attribution. Not checked yet
+1 more
show less
New integration guide for Continue.dev: adds enterprise-grade observability, cost tracking, and governance to the open-source AI coding assistant via Portkey as an OpenAI-compatible endpoint. Not checked yet
6 details in Everything
└──▷ BREAKING ON UPGRADE
! Configs exceeding the new fan-out limits (100 root-level targets, 1,000 for conditional strategy, 50 nested targets per root target) will be rejected at request time; override with MAX_ROOT_CONFIG_TARGETS, MAX_NESTED_CONFIG_TARGETS, or MAX_CONDITIONAL_ROOT_CONFIG_TARGETS environment variables before upgrading.
Portkey adds Prisma AIRS agentic scan controls, soft-deny guardrails, provider-backed model listing, and Continue.dev integration
└──▷ USE IT
Reduce Prisma AIRS false positives when using agentic clients (Claude Code, Cursor, Cline) by scanning only the last user message and stripping scaffolding wrappers.
json
copy
{
"scan_scope": "last_user_message",
"strip_scaffolding": true
}
Keep an agentic session alive when a guardrail fires by returning a soft deny as HTTP 200 instead of HTTP 446.
json
copy
{
"soft_deny_200": true
}
Adds scan_scope and strip_scaffolding parameters to the Palo Alto Networks Prisma AIRS guardrail, enabling fine-grained control over which messages are scanned and reducing false positives for agentic clients like Claude Code, Cursor, and Cline. Not checked yet Adds soft_deny_200 flag on guardrail checks: denials return HTTP 200 with the error as a chat completion response instead of HTTP 446, keeping sessions alive for clients that treat 4xx as fatal. Not checked yet GET /v1/models now routes through the gateway's provider-backed model listing handler, calling the upstream provider and returning a normalized model list with response transforms applied. Not checked yet Anthropic cost attribution now differentiates batch (50% discount), fast, and standard pricing tiers for multidimensional cost tracking. Not checked yet xAI server-side tool invocation costs (file search, web search) are now tracked for cost attribution. Not checked yet
+1 more
show less
New integration guide for Continue.dev: adds enterprise-grade observability, cost tracking, and governance to the open-source AI coding assistant via Portkey as an OpenAI-compatible endpoint. Not checked yet
6 details in Everything
└──▷ BREAKING ON UPGRADE
! Configs exceeding the new fan-out limits (100 root-level targets, 1,000 for conditional strategy, 50 nested targets per root target) will be rejected at request time; override with MAX_ROOT_CONFIG_TARGETS, MAX_NESTED_CONFIG_TARGETS, or MAX_CONDITIONAL_ROOT_CONFIG_TARGETS environment variables before upgrading.
Portkey adds MCP Server MCP Server A process that exposes tools, resources, and prompts over Anthropic's Model Context Protocol, letting an AI agent call external APIs or local services through a standardised interface. management, SCIM SCIM A standard for creating, updating and removing user accounts and groups across applications. It helps an identity provider keep access in sync when people join, change roles or leave. workspace mappings, rate/usage limit policies, and expanded Admin APIs for guardrails, models, and prompts.
New Admin API Admin API A dedicated HTTP interface that exposes management and configuration operations separately from the data plane, letting cyber tools automate provisioning, policy changes, or monitoring without touching the main user-facing service. endpoints to create, list, and test MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Server connections for workspace instances. Not checked yet New Admin API endpoints to manage SCIM group-to-workspace mappings (create, list, delete) for enterprise identity provisioning. Not checked yet New Admin API endpoints to create and list Rate Limits Policies and Usage Limits Policies, with entity tracking for usage limits. Not checked yet New Admin API endpoint to rotate existing API keys and retrieve a new key. Not checked yet New Admin API endpoints to list and retrieve individual Guardrail configurations. Not checked yet
+8 more
show less
New Admin API endpoints for custom model management: delete custom models, list model access, and update model access and pricing configuration. Not checked yet New Admin API endpoints to list and update workspace access permissions and usage limits per integration. Not checked yet New Admin API endpoints to create and list Prompt Collections, update prompt metadata, and update prompt version metadata. Not checked yet New Skills Registry for creating versioned, team-shared skills usable by AI coding agents via Portkey. Not checked yet New guide for converting local STDIO MCP servers to remote Streamable HTTP MCP Streamable HTTP MCP A transport variant of the Model Context Protocol (MCP) that carries tool-call messages over HTTP with optional streaming, letting cyber tools expose AI-callable functions without maintaining a persistent connection. servers via Portkey's MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. . Not checked yet New integration support for AWS AgentCore, Agno AI, enabling Portkey-powered agents inside Amazon Bedrock and Agno. Not checked yet New use-case guide for using private MCP Servers with the Responses API via client-side tool handling. Not checked yet New C# (.NET) SDK support for integrating Portkey in .NET applications. Not checked yet
13 details in Everything
Portkey adds MCP Server MCP Server A process that exposes tools, resources, and prompts over Anthropic's Model Context Protocol, letting an AI agent call external APIs or local services through a standardised interface. management, SCIM SCIM A standard for creating, updating and removing user accounts and groups across applications. It helps an identity provider keep access in sync when people join, change roles or leave. workspace mappings, rate/usage limit policies, and expanded Admin APIs for guardrails, models, and prompts.
New Admin API Admin API A dedicated HTTP interface that exposes management and configuration operations separately from the data plane, letting cyber tools automate provisioning, policy changes, or monitoring without touching the main user-facing service. endpoints to create, list, and test MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Server connections for workspace instances. Not checked yet New Admin API endpoints to manage SCIM group-to-workspace mappings (create, list, delete) for enterprise identity provisioning. Not checked yet New Admin API endpoints to create and list Rate Limits Policies and Usage Limits Policies, with entity tracking for usage limits. Not checked yet New Admin API endpoint to rotate existing API keys and retrieve a new key. Not checked yet New Admin API endpoints to list and retrieve individual Guardrail configurations. Not checked yet
+8 more
show less
New Admin API endpoints for custom model management: delete custom models, list model access, and update model access and pricing configuration. Not checked yet New Admin API endpoints to list and update workspace access permissions and usage limits per integration. Not checked yet New Admin API endpoints to create and list Prompt Collections, update prompt metadata, and update prompt version metadata. Not checked yet New Skills Registry for creating versioned, team-shared skills usable by AI coding agents via Portkey. Not checked yet New guide for converting local STDIO MCP servers to remote Streamable HTTP MCP Streamable HTTP MCP A transport variant of the Model Context Protocol (MCP) that carries tool-call messages over HTTP with optional streaming, letting cyber tools expose AI-callable functions without maintaining a persistent connection. servers via Portkey's MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. . Not checked yet New integration support for AWS AgentCore, Agno AI, enabling Portkey-powered agents inside Amazon Bedrock and Agno. Not checked yet New use-case guide for using private MCP Servers with the Responses API via client-side tool handling. Not checked yet New C# (.NET) SDK support for integrating Portkey in .NET applications. Not checked yet
13 details in Everything
Portkey adds vault-backed Secret References, weekly rate limits, cross-cloud GCS log delivery, and four new guardrail integrations.
└──▷ USE IT
Apply Zscaler Detection Policies to all LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. traffic through Portkey so your existing Zscaler policy class governs both inputs and outputs.
json
copy
Add Zscaler AI Guard as a guardrail with your policyId:
{
"guardrails": {
"beforeRequestHook": {
"provider": "zscaler",
"policyId": "<your-zscaler-policy-id>",
"timeout": 10000
},
"afterRequestHook": {
"provider": "zscaler",
"policyId": "<your-zscaler-policy-id>",
"timeout": 10000
}
}
}
Adds Secret References so virtual keys and integrations can pull credentials at runtime from AWS Secrets Manager, Azure Key Vault, or HashiCorp Vault via secret_mappings, keeping secrets out of Portkey config. Not checked yet Supports weekly budget and usage windows (rpw) for rate-limit policies so spend caps align with weekly planning cycles. Not checked yet Adds endpoint-scoped rate limits so chat completions, embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. , and admin routes can each carry independent limits instead of a single global cap. Not checked yet Enables GCS log storage from AWS-hosted gateways via GCP Workload Identity Federation (GCP_WIF_AUDIENCE, GCP_WIF_SERVICE_ACCOUNT_EMAIL), eliminating long-lived cross-cloud credentials. Not checked yet Lets organization admins include archived workspaces in analytics graphs and filters, with workspace slugs now accepted alongside IDs in saved filters. Not checked yet
+11 more
show less
Integrates Zscaler AI Guard as a guardrail partner, applying Zscaler Detection Policies to LLM inputs and outputs via beforeRequestHook/afterRequestHook with a required policyId. Not checked yet Integrates Akto Agentic Security as a guardrail partner to scan LLM traffic for prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. and sensitive data leakage. Not checked yet Adds customHost support for the Bedrock Guardrails plugin so evaluations route to private or regional Bedrock-compatible endpoints. Not checked yet Adds required metadata key–value guardrails that block requests missing specified fields before they reach the model. Not checked yet Adds DeepInfra provider support with tool calling tool calling A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. (tools, tool_choice, parallel_tool_calls), chat completions, and embeddings. Not checked yet Extends DeepSeek support: deepseek-chat gains tools, tool_choice, and stream_options; deepseek-reasoner maps reasoning_effort to thinking mode and surfaces reasoning_content in streams. Not checked yet Extends Bedrock batch inference to cover embeddings in addition to chat completions. Not checked yet Maps Portkey metadata to Vertex AI resource labels and adds enterprise web search grounding via enterpriseWebSearch/enterprise_web_search. Not checked yet Enables AWS workloads to reach Vertex AI through AWS–GCP Workload Identity Federation (GCP_WIF_AUDIENCE, GCP_WIF_SERVICE_ACCOUNT_EMAIL). Not checked yet Adds Azure AI Foundry rerank support for Cohere rerank models (e.g. cohere.Cohere-rerank-v4.0-pro), with the gateway stripping the cohere. prefix for the provider. Not checked yet Updates OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. GenAI semantic spans to semconv 1.40.0, adds OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. exporter support for guardrail flows, and supports custom resource attributes for downstream APM APM Application Performance Monitoring — a category of software that collects metrics, traces, and logs from running applications so developers can detect slowdowns and diagnose their root cause. and tracing. Not checked yet
16 details in Everything
Portkey's GET /v1/models now supports provider-backed proxying and a new header to force Model Catalog results.
└──▷ TRY IT
Show end users only your workspace's approved Model Catalog models, even when the request carries provider auth for downstream routing.
copy
$ curl https://api.portkey.ai/v1/models \
-H "x-portkey-api-key: <your-portkey-key>" \
-H "x-portkey-provider: @anthropic-prod" \
-H "x-portkey-fetch-integrated-models: true"
Adds provider-backed mode to GET /v1/models: pass x-portkey-provider: @<provider-slug> or a config with provider/targets to proxy the request to the upstream provider's /v1/models and receive a response normalized to OpenAI models list format. Not checked yet Adds x-portkey-fetch-integrated-models: true header (and fetch_integrated_models: true config field) to force GET /v1/models to return your workspace's Model Catalog models even when a provider header or config is present. Not checked yet Model Catalog results are automatically filtered to only the provider slugs referenced in your routing config when fetch_integrated_models is active; passthrough: true targets return the full unfiltered list. Not checked yet
3 details in Everything
Portkey adds a Models API endpoint to retrieve the list of available models.
└──▷ TRY IT
Query the Models endpoint to discover which models are available to your account before routing requests.
copy
$ curl https://api.portkey.ai/v1/models -H "x-portkey-api-key: <your-api-key>"
Portkey adds vault-backed credentials, weekly rate limits, cross-cloud GCS logging, and four new guardrail integrations in March 2026.
└──▷ HOW TO FIND IT
Pull API keys from your own vault at request time instead of storing them in Portkey — critical for orgs with strict secrets governance.
📍 In the Portkey console, go to your Virtual Key or Integration settings and add a secret_mappings block pointing to your AWS Secrets Manager, Azure Key Vault, or HashiCorp Vault path. Portkey will resolve the credential at runtime.
Cap a team's weekly LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. spend and keep chat completions under a separate limit from embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. calls.
📍 In the Portkey console, open Budget & Rate Limit Policies, set a rpw (requests-per-week) budget window for the relevant virtual key or config, then add an endpoint-scoped limit targeting the chat completions route independently from embeddings.
Route Bedrock guardrail evaluation to a private regional endpoint instead of the default public Bedrock URL.
📍 In the Portkey console, open the Bedrock guardrail plugin configuration and set customHost to your private or regional Bedrock-compatible endpoint URL.
Introduces weekly rate and budget windows (rpw) so spend caps align with team planning cycles, not just per-minute or monthly aggregates. Not checked yet Adds endpoint-scoped rate limits so chat completions, embeddings, and admin routes can each carry independent limits instead of a single global rule. Not checked yet Enables GCP Workload Identity Federation log storage (gcs_assume) from AWS-hosted gateways via GCP_WIF_AUDIENCE and GCP_WIF_SERVICE_ACCOUNT_EMAIL, eliminating static GCP keys in AWS. Not checked yet Allows organization admins to include archived workspaces in analytics graphs and filters; saved filters now also accept workspace slugs alongside IDs. Not checked yet Integrates Zscaler AI Guard as a guardrails partner, applying Zscaler Detection Policies to LLM inputs and outputs via beforeRequestHook/afterRequestHook with a required policyId. Not checked yet
+6 more
show less
Integrates Akto Agentic Security as a guardrails partner to scan LLM traffic for prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. and sensitive data leakage via configurable hooks and timeout. Not checked yet Adds required metadata key–value guardrails that block requests missing or carrying invalid metadata fields before they reach the model. Not checked yet Supports DeepInfra tool calling tool calling A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. (tools, tool_choice, parallel_tool_calls) plus completions and embeddings endpoints. Not checked yet Adds DeepSeek deepseek-chat tool calling (tools, tool_choice, stream_options) and deepseek-reasoner reasoning effort mapping with reasoning_content in streams. Not checked yet Extends Bedrock batch inference to support embeddings in addition to chat completions. Not checked yet Adds Azure AI Foundry rerank support for Cohere rerank models (e.g., cohere.Cohere-rerank-v4.0-pro), with the gateway stripping the cohere. prefix for the provider. Not checked yet
11 details in Everything
Portkey adds hybrid deployment architecture option.
Supports hybrid deployment architecture, enabling mixed on-premises and cloud configurations. Not checked yet
1 detail in Everything
└──▷ USE IT
Gate every agentic request through Zscaler AI Guard so your existing Zscaler Detection Policies apply to LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. inputs and outputs.
json
copy
In your Portkey config, add the Zscaler AI Guard guardrail with your policyId:
{
"guardrails": {
"beforeRequestHook": {
"provider": "zscaler",
"policyId": "<your-zscaler-policy-id>",
"timeout": 10000
},
"afterRequestHook": {
"provider": "zscaler",
"policyId": "<your-zscaler-policy-id>",
"timeout": 10000
}
}
}
Route GCP Cloud Storage log writes from an AWS-hosted gateway through Workload Identity Federation to avoid storing long-lived GCP service account keys in AWS.
copy
$ Set these environment variables on your gateway deployment:
GCP_WIF_AUDIENCE=<your-wif-audience>
GCP_WIF_SERVICE_ACCOUNT_EMAIL=<your-sa>@<project>.iam.gserviceaccount.com
Adds Secret References so Portkey fetches credentials at runtime from AWS Secrets Manager, Azure Key Vault, or HashiCorp Vault via secret_mappings, keeping keys out of Portkey config entirely. Not checked yet Enables GCP Workload Identity Federation log delivery from AWS-hosted gateways to Google Cloud Storage via GCP_WIF_AUDIENCE and GCP_WIF_SERVICE_ACCOUNT_EMAIL, eliminating long-lived GCP keys in AWS. Not checked yet Adds customHost support on the Bedrock Guardrails plugin so guardrail evaluation hits private or regional Bedrock-compatible endpoints instead of default public URLs. Not checked yet Adds tool_choice, stream_options, and streaming usage reporting to DeepSeek deepseek-chat; maps reasoning_effort to thinking mode and surfaces reasoning_content in streams for deepseek-reasoner. Not checked yet Maps Portkey metadata to Vertex AI resource labels and adds enterprise search grounding via enterpriseWebSearch / enterprise_web_search with separate cost attribution. Not checked yet
+2 more
show less
Enables AWS workloads to reach Vertex AI through AWS–GCP WIF WIF Workload Identity Federation is a Google Cloud mechanism that lets external workloads authenticate to Google APIs using short-lived tokens from a trusted identity provider, eliminating the need to manage long-lived service account keys. using GCP_WIF_AUDIENCE and GCP_WIF_SERVICE_ACCOUNT_EMAIL. Not checked yet Updates OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. GenAI semantic spans to semconv 1.40.0, adds OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. exporter support for guardrail flows, and supports custom resource attributes for downstream APM APM Application Performance Monitoring — a category of software that collects metrics, traces, and logs from running applications so developers can detect slowdowns and diagnose their root cause. standardization. Not checked yet
Portkey adds vault-backed credentials, weekly rate limits, cross-cloud GCS logging, and four new guardrail integrations in March 2026.
└──▷ HOW TO FIND IT
Pull LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. provider credentials from your existing vault at runtime instead of storing keys in Portkey directly.
📍 In the Portkey console, go to Settings › Integrations (or Virtual Keys) and add a secret_mappings entry pointing to your AWS Secrets Manager, Azure Key Vault, or HashiCorp Vault secret ARN/path. Portkey fetches the value at request time.
Route Zscaler AI Guard policy checks across all LLM traffic to enforce your org's existing detection policies on inputs and outputs.
json
copy
{
"guardrails": [
{
"type": "zscaler",
"beforeRequestHook": true,
"afterRequestHook": true,
"policyId": "<your-zscaler-policy-id>",
"timeout": 10000
}
]
}
Ship gateway logs from AWS to GCS using Workload Identity Federation — no long-lived GCP keys required.
copy
$ GCP_WIF_AUDIENCE=<your-wif-audience>
GCP_WIF_SERVICE_ACCOUNT_EMAIL=<your-service-account>@<project>.iam.gserviceaccount.com
# Set log storage mode to gcs_assume in your gateway config
New Secret References let you point Portkey at credentials stored in AWS Secrets Manager, Azure Key Vault, or HashiCorp Vault via secret_mappings, so keys are fetched at runtime from vaults you already control. Not checked yet Adds weekly rate and budget windows (rpw) so spend caps align with weekly planning cycles rather than only per-minute or monthly aggregates. Not checked yet Adds endpoint-scoped rate limits so chat completions, embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. , and admin routes can each carry independent limits instead of a single global rule. Not checked yet GCP Workload Identity Federation log delivery: configure GCP_WIF_AUDIENCE and GCP_WIF_SERVICE_ACCOUNT_EMAIL so an AWS-hosted gateway writes logs to GCS without long-lived GCP keys (gcs_assume style). Not checked yet Organization admins can now include archived workspaces in analytics graphs and filters; saved filters also accept workspace slugs alongside IDs. Not checked yet
+9 more
show less
New Zscaler AI Guard integration applies Zscaler Detection Policies to LLM inputs and outputs via beforeRequestHook / afterRequestHook with a required policyId. Not checked yet New Akto Agentic Security guardrail scans LLM inputs and outputs for prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. and sensitive data leakage with configurable hook and timeout. Not checked yet Bedrock Guardrails plugin now accepts a customHost field to route guardrail evaluation to private or regional Bedrock-compatible endpoints. Not checked yet New required metadata key–value guardrails block requests missing specified metadata fields before they reach the model. Not checked yet DeepInfra provider adds tool calling tool calling A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. (tools, tool_choice, parallel_tool_calls) plus completions and embeddings endpoints. Not checked yet DeepSeek deepseek-chat gains tools, tool_choice, and stream_options; deepseek-reasoner maps reasoning_effort to thinking mode and returns reasoning_content in streams. Not checked yet Bedrock batch inference now supports embeddings in addition to chat completions. Not checked yet Vertex AI: Portkey metadata maps to Vertex resource labels; enterprise search grounding via enterpriseWebSearch / enterprise_web_search; AWS workloads reach Vertex via AWS–GCP WIF WIF Workload Identity Federation is a Google Cloud mechanism that lets external workloads authenticate to Google APIs using short-lived tokens from a trusted identity provider, eliminating the need to manage long-lived service account keys. . Not checked yet Azure AI Foundry gains Cohere rerank model support (e.g. cohere.Cohere-rerank-v4.0-pro); gateway strips the cohere. prefix for the provider. Not checked yet
14 details in Everything
Portkey adds vault-backed credentials, weekly rate limits, cross-cloud log delivery, and four new guardrail integrations in March 2026.
└──▷ USE IT
Keep LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. provider keys out of Portkey by pointing a virtual key at a secret stored in AWS Secrets Manager — Portkey fetches the value at request time.
json
copy
{
"virtual_key": "my-openai-key",
"secret_mappings": {
"api_key": "arn:aws:secretsmanager:us-east-1:123456789012:secret:openai-api-key-AbCdEf"
}
}
Gate every request so it must carry a user_id metadata field — the gateway blocks the call before it hits the model if the field is absent.
json
copy
{
"guardrails": [
{
"type": "required_metadata",
"required_keys": ["user_id", "session_id"]
}
]
}
Apply your existing Zscaler Detection Policy to LLM inputs and outputs by wiring AI Guard into the gateway's request/response hooks.
json
copy
{
"guardrails": [
{
"type": "zscaler",
"hooks": ["beforeRequestHook", "afterRequestHook"],
"policyId": "<your-zscaler-policy-id>",
"timeout": 10000
}
]
}
Adds Secret References so Portkey fetches credentials at runtime from AWS Secrets Manager, Azure Key Vault, or HashiCorp Vault via secret_mappings, keeping keys out of Portkey directly. Not checked yet Supports weekly budget/usage windows (rpw) and endpoint-scoped rate limits, letting teams cap chat completions, embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. , and admin routes independently. Not checked yet Enables GCS log delivery from AWS-hosted gateways via GCP Workload Identity Federation (GCP_WIF_AUDIENCE / GCP_WIF_SERVICE_ACCOUNT_EMAIL), eliminating long-lived cross-cloud keys. Not checked yet Allows organization admins to include archived workspaces in analytics graphs and filters, with workspace slugs accepted alongside IDs in saved filters. Not checked yet Integrates Zscaler AI Guard as a guardrail partner, applying Zscaler Detection Policies to LLM inputs and outputs via beforeRequestHook / afterRequestHook with a required policyId. Not checked yet
+8 more
show less
Integrates Akto Agentic Security as a guardrail partner to scan for prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. and sensitive data leakage on agentic traffic. Not checked yet Adds customHost on the Bedrock Guardrails plugin so guardrail evaluation can target private or regional Bedrock-compatible endpoints. Not checked yet New required metadata key–value guardrails block requests at the gateway before they reach the model if required metadata fields are missing or invalid. Not checked yet Adds DeepInfra provider support with tool calling tool calling A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. (tools, tool_choice, parallel_tool_calls), completions, and embeddings endpoints. Not checked yet Expands DeepSeek support: deepseek-chat gains tools, tool_choice, and stream_options; deepseek-reasoner maps reasoning_effort to thinking mode and returns reasoning_content in streams. Not checked yet Extends Bedrock batch inference to support embeddings jobs alongside existing chat completion batch patterns. Not checked yet Adds Vertex AI enterprise web search grounding via enterpriseWebSearch / enterprise_web_search with separate cost attribution, Portkey metadata mapped to Vertex resource labels, and AWS-to-Vertex access via WIF WIF Workload Identity Federation is a Google Cloud mechanism that lets external workloads authenticate to Google APIs using short-lived tokens from a trusted identity provider, eliminating the need to manage long-lived service account keys. . Not checked yet Supports Azure AI Foundry rerank with Cohere rerank models (e.g. cohere.Cohere-rerank-v4.0-pro), with the gateway stripping the cohere. prefix automatically. Not checked yet
13 details in Everything
Portkey Backend 1.20.0 adds Scenario AI provider, Prisma AIRS profile params, SSO SSO Single sign-on, using one identity provider to sign in to multiple applications. It reduces separate passwords and centralizes account and access management. domain restriction and atomic OAuth exchange.
Adds profile_id, app_name, scan_scope parameters to PANW Prisma AIRS guardrails configuration Not checked yet Makes profile_name optional for PANW Prisma AIRS when using the API key linked profile in Strata Cloud Manager Not checked yet Adds scenario-ai to the Model Catalog for AI-powered image, video, and asset generation Not checked yet Adds disable_auto_provision_user auth setting to restrict SSO login to invited users with verified allowed domains Not checked yet Accepts optional sso_client_id parameter to target specific SSO configurations when linked to multiple setups Not checked yet
+2 more
show less
Raises credit_limit in usage limit policies to reactivate already-exhausted keys immediately Not checked yet Enforces single-use atomicity for OAuth authorization-code exchange Not checked yet
7 details in Everything
Enterprise Gateway 2.14.1 adds scan_scope and strip_scaffolding for Prisma AIRS agentic support
Adds scan_scope parameter to Palo Alto Networks Prisma AIRS guardrail for controlling which messages are scanned (last_message, last_user_message, user_messages, or all_messages) Not checked yet Adds strip_scaffolding parameter to remove known agent-harness wrappers before scanning, reducing false positives for agentic clients Not checked yet
2 details in Everything
Portkey Enterprise Gateway 2.14.0 adds HTTP 200 soft deny for guardrails and environment variable limits for config target fan-out.
Adds GET /v1/models endpoint to route through the gateway’s provider-backed model listing handler, returning normalized lists with response transforms. Not checked yet Adds soft_deny_200 flag on guardrail checks to return HTTP 200 with error messages formatted as chat completion responses. Not checked yet Adds environment variables MAX_ROOT_CONFIG_TARGETS, MAX_NESTED_CONFIG_TARGETS, and MAX_CONDITIONAL_ROOT_CONFIG_TARGETS to override default config target fan-out limits. Not checked yet
3 details in Everything
└──▷ BREAKING ON UPGRADE
! Config target fan-out is now capped at 100 root-level targets (1,000 for conditional strategy) and 50 nested targets per root target; configs exceeding these limits will be rejected at request time unless overridden by MAX_ROOT_CONFIG_TARGETS, MAX_NESTED_CONFIG_TARGETS, or MAX_CONDITIONAL_ROOT_CONFIG_TARGETS environment variables.
Portkey Backend 1.19.0 adds Databricks provider support, user-attributed log exports, and stricter workspace security setting overrides.
Adds databricks to the Model Catalog with model and pricing configs Not checked yet Rejects workspace security_settings changes for sections not enabled for override Not checked yet Returns next usage-reset timestamp for API key details in Usage Limit Policies Not checked yet Record user-id attribution in log-export routes; User API Keys filter exports by that user Not checked yet Migrates org-level workspace security settings down to workspaces Not checked yet
5 details in Everything
Enterprise Gateway 2.13.0 adds server-side MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. execution, Alibaba Cloud AI Guardrails, and tenant-scoped OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. attributes.
Adds @portkey-mcp prefix support in the tools array of Responses API and Messages API requests for server-side MCP execution, gated behind the x-portkey-beta: server-side-mcp-2026-06-01 header Not checked yet Adds the alibaba-cloud-ai guardrail plugin for content safety checks, configurable through the standard guardrails workflow Not checked yet Enables MCP gateway request logs to be exported to an OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. collector alongside LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateway logs Not checked yet Attaches Portkey tenant attributes (org_id, workspace, environment) to Gen AI and guardrail OTel spans for per-tenant filtering Not checked yet Passes through the thinking.display parameter to the upstream Anthropic API Not checked yet
5 details in Everything
Redis multi-auth and discovery URL support; SSRF SSRF Server-side request forgery, an attack that tricks a server into making requests chosen by an attacker. Those requests can reach internal services the attacker cannot access directly. checks for external calls in Portkey Data Service 1.9.0
Adds REDIS_CLUSTER_DISCOVERY_URL environment variable to enable Redis connection through Discovery URL. Not checked yet Adds support for multiple auth modes in Redis improvements for Azure Redis. Not checked yet Adds SSRF checks for external calls. Not checked yet
3 details in Everything
Portkey Enterprise Gateway 2.12.0 adds OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. guardrail spans, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. /Agent token metering, Azure MAI image gen, and Vertex MoonshotAI support
Guardrail checks now emit dedicated OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. spans under the portkey.guardrail.* namespace for phase, verdict, action, deny, async, and per-check events. Not checked yet Token usage from MCP requests (prompts, completions, tools) is tracked and reported in analytics and logs alongside LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. usage. Not checked yet Token usage from agent endpoints (messages and tasks) is tracked and reported in analytics and logs alongside LLM usage. Not checked yet Image generation and editing are supported for MAI models (e.g., MAI-Image-2.5) on Azure AI Inference. Not checked yet Vertex AI integration now supports the moonshotai model provider. Not checked yet
+1 more
show less
The /dataservice/metrics endpoint is gated behind the ENABLE_PROMETHEUS env flag, matching the behavior of the /metrics endpoint. Not checked yet
6 details in Everything
Portkey Backend 1.18.0 adds saved-only mode, MiniMax provider, SCIM SCIM A standard for creating, updating and removing user accounts and groups across applications. It helps an identity provider keep access in sync when people join, change roles or leave. multi-workspace mapping, unified /models endpoint, and JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. agents.invoke scope.
Enables block_inline_config data-plane security setting to reject inline provider/endpoint/config selections in favor of admin-curated resources Not checked yet Adds BLOCK_INLINE_CONFIG=true environment variable for self-hosted Gateways to force saved-only mode Not checked yet Adds MiniMax (minimax) model provider to the Model Catalog with model and pricing configs Not checked yet Expands SCIM integration: GET /v1/scim/workspaces now supports pagination (page, page_size, total_count) and groups can map to multiple workspaces Not checked yet Removes include_mapped_groups filter from GET /v1/scim/groups as groups can now map to many workspaces Not checked yet
+2 more
show less
Adds fetch_integrated_models config flag and x-portkey-models-endpoint request header to fetch the integrated catalog model list through the Gateway Not checked yet Adds agents.invoke data-plane scope for JWT tokens Not checked yet
7 details in Everything
└──▷ BREAKING ON UPGRADE
! The include_mapped_groups filter is removed from GET /v1/scim/groups endpoint responses
Portkey Frontend v1.9.3 adds org-level Data Plane Security controls and Anthropic streaming retry support.
Added dashboard controls for Data Plane Security Settings at the organization and workspace levels Not checked yet Added Catch Overloaded Errors on Stream to Anthropic advanced configuration to convert streaming overloaded_error responses to retriable 529 errors Not checked yet
2 details in Everything
Adds x-portkey-fetch-integrated-models header to override models API routing, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. metrics-only logging, and S3 log store circuit breaker via env vars.
Adds the x-portkey-fetch-integrated-models HTTP header and fetch_integrated_models config field to force GET /v1/models to return gateway-configured models regardless of routing signals Not checked yet Introduces metrics-only logging mode for the MCP gateway, dropping request/response bodies from persisted logs while retaining span info and preserving response bodies on failures Not checked yet
2 details in Everything
v2.11.1 updates Bedrock Guardrails action handling, cost attribution, and SSRF SSRF Server-side request forgery, an attack that tricks a server into making requests chosen by an attacker. Those requests can reach internal services the attacker cannot access directly. validation.
Guardrails now only block requests when the action field is explicitly blocked, allowing non-blocking actions to pass through. Not checked yet
1 detail in Everything
Portkey Enterprise Gateway 2.11 adds MiniMax support, Enforce Inline Config flag, and OAuth forwarding for Claude Code.
Adds minimax provider for chat completions with MiniMax’s hosted models Not checked yet Modal integration now supports /v1/embeddings alongside chat completions Not checked yet Anthropic chat completions pass context_management through to the upstream API Not checked yet Enforces inline configs with a new flag that rejects requests passing an inline config JSON object instead of a saved config slug Not checked yet
4 details in Everything
Enterprise Gateway 2.10.0 adds Claude Platform on AWS, Cato guardrail, multi-dimensional pricing, Prometheus labels, and SSRF SSRF Server-side request forgery, an attack that tricks a server into making requests chosen by an attacker. Those requests can reach internal services the attacker cannot access directly. hardening.
Adds claude-platform-aws provider with accessKey, assumedRole, and serviceRole auth modes for Anthropic’s full-platform capabilities through AWS Not checked yet Adds Cato Networks guardrail plugin for AI security inspection of LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. prompts and responses via Cato’s analyze API Not checked yet Adds PROMETHEUS_INCLUDE_CONFIG_NAME_LABEL and PROMETHEUS_INCLUDE_API_KEY_NAME_LABEL environment flags to attach config slug and API key name as labels on custom metrics Not checked yet default.allowedRequestTypes guardrail now runs as a beforeRequestHook on proxy requests Not checked yet Adds otel to the plugin manifest allow list to permit OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. export via guardrail config Not checked yet
+3 more
show less
guard_chat_completions requests to CrowdStrike AIDR now forward user_id, user_name, llm_provider, and model metadata Not checked yet Vertex AI integration adds support for the zai-org model provider on chat completions Not checked yet Forwarding OpenAI-style service_tier as the upstream Vertex header for tiered inference usage attribution Not checked yet
8 details in Everything
Portkey Frontend 1.9.2 improves self-hosting configuration via a new environment variable and reorganizes default workspace API key settings to the organisation level.
Adds VITE_PRESELECT_LOGIN_PERMISSION environment variable to pre-select the login permission checkbox on private deployments Not checked yet
1 detail in Everything
Adds Cato Networks guardrail, prompt sharing APIs, and org-level API key auto-create settings
Introduces Cato Networks guardrail with cato.analyze action supporting monitor, anonymize, or block with userEmail, keyAlias, and timeout options. Not checked yet Adds guardrails.invoke scope for workspace-service and workspace-user API keys. Not checked yet Exposes prompt sharing via new workspace-scoped APIs: POST/PUT/DELETE /v2/prompts/:id/share, /fork, and /unshare. Not checked yet Lists endpoints now support type=shared and show_prompt_share query parameters for filtering shared prompts. Not checked yet Config create/update schema validates default_params and drop_params on targets in addition to override_params. Not checked yet
+2 more
show less
Adds org-only setting default_workspace_user_api_key_auto_create to control auto-provisioning of workspace-user API keys. Not checked yet API key rotation enforcement user_api_key_rotation_period now accepts days only (integer 1–365), normalizing old weekly/monthly values. Not checked yet
7 details in Everything
└──▷ BREAKING ON UPGRADE
! Deprecated organisation-level prompt/partial routes removed; use workspace-scoped APIs instead.
Enterprise Gateway 2.9.0 adds default/drop params, new providers, Lakera guardrails, and native Azure Responses API
Adds default_params and drop_params config fields to Config Targets for conditional injection and removal of request parameters by dot-notation path. Not checked yet Integrates Fal AI provider (fal-ai) for image, video, and audio generation models. Not checked yet Integrates BytePlus provider (byteplus) for chat completions. Not checked yet Integrates Scenario AI provider (scenario-ai) with proxy passthrough support for Basic auth using apiKey and optional scenarioApiSecret. Not checked yet Adds Lakera Guard as a guardrails partner via /v2/guard API, supporting beforeRequestHook/afterRequestHook, PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. redaction, and optional project_id/apiBase. Not checked yet
+4 more
show less
Enables per-region Vertex AI endpoints for batches, Gemini Embedding Embedding Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. 2 embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. , Anthropic Claude on Vertex, and Gemini models. Not checked yet Adds support for Anthropic Claude models via the unified /v1/batches API on Vertex AI. Not checked yet Unlocks Azure AI Foundry native Responses API (/v1/responses) behind a flag for agent references and transformations. Not checked yet Supports OpenAI-style service_tier parameter in Amazon Bedrock provider requests with correct usage attribution. Not checked yet
9 details in Everything
Frontend 1.9.1 adds Azure Workload Identity configuration via dashboard and improves API key rotation UX.
Adds azureWorkloadClientId and azureWorkloadTenantId config fields in the dashboard to enable Azure Workload Identity for OpenAI and AI Foundry integrations Not checked yet Improves input field and validation error messaging for Org service API key rotation Not checked yet
2 details in Everything
Frontend 1.9.0 adds org workspace publishing, CSV variable import/export, Scenario AI provider support, and a Shared with me tab.
Publish to org or selected workspaces for prompt and partial sharing to control visibility Not checked yet Shared with me tab displays org-wide shared prompts and partials Not checked yet Export prompt variables as CSV (name, type, value) and import from CSV in bulk Not checked yet New provider Scenario AI added Not checked yet
4 details in Everything
Data Service 1.8.0 adds provider batch guardrails and opt-in Bull Board dashboard.
Adds input_guardrails and output_guardrails config keys inside portkey_options to enable redaction/filtering on provider batches. Not checked yet Adds BULL_BOARD_ENABLED=true environment variable to enable the Bull Board queue dashboard (disabled by default). Not checked yet
2 details in Everything
Portkey Backend 1.16.2 adds Lakera Guard support, workspace API key defaults, batch API key lookup, and SSRF SSRF Server-side request forgery, an attack that tricks a server into making requests chosen by an attacker. Those requests can reach internal services the attacker cannot access directly. hardening.
Adds Lakera Guard integration via /v2/guard endpoint for prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. , policy violation, and PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. detection with projectID, endInclusive, and timeout config options Not checked yet Adds fal.ai provider to the Model Catalog under the fal-ai identifier for OpenAI-compatible inference across LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. , image, video, and audio models Not checked yet Allows setting defaults.user_api_key_config via PUT /v2/workspaces/:id to define a default config slug for auto-created or fallback workspace-user API keys, with validation preventing deletion of the active default Not checked yet Extends isValidCustomHost validation across organisation settings, deployments, providers, virtual keys, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. integrations, integration-model custom_host, and SAML SAML A standard for passing signed identity assertions between a sign-in provider and an application. It lets a user sign in through their organization's identity provider. ACS URLs to block private/reserved IPs, metadata endpoints, non-HTTP(S) schemes, URL fragments, and other unsafe targets Not checked yet Enables hardening of OIDC OIDC OpenID Connect, a sign-in protocol built on OAuth 2.0. An application uses identity information from a trusted provider instead of maintaining a separate password for each user. PKCE PKCE Proof Key for Code Exchange, an OAuth safeguard that binds an authorization code to the client that requested it. An intercepted code cannot be redeemed without the client's matching verifier. flows for SSO SSO Single sign-on, using one identity provider to sign in to multiple applications. It reduces separate passwords and centralizes account and access management. authentication and ensures JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. user attribution correctly resolves user email and enforces workspace membership Not checked yet
+2 more
show less
Adds ids query parameter support to GET /v2/api-keys for batch lookup via comma-separated UUIDs UUIDs A universally unique identifier, usually a 128-bit value used to identify an object across systems. It is designed to make independently generated identifiers unlikely to collide. Not checked yet Validates byteplus_region in the integrations API for the BytePlus provider integration Not checked yet
7 details in Everything
Portkey Enterprise Gateway 2.8.0 adds Tavily guardrails, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. CORS CORS A browser mechanism that lets a server declare which foreign origins may read its HTTP responses, enforced by the browser to block unauthorized cross-site requests from JavaScript. controls, Azure Workload Identity, and Vertex AI TTS support.
Adds Tavily Online Guardrail Plugin for web-grounded checks in guardrail pipelines Not checked yet Enables Vertex AI Gemini TTS via unified speech APIs (createSpeech / generateSpeech) through gateway routes Not checked yet Updates Bedrock Mantle prompt cache pricing to include 1-hour cached context cost path Not checked yet Extends Workload Identity support for Azure OpenAI, Azure AI Foundry routes and adds it as an authentication option for Azure Cache for Redis Not checked yet Introduces a new usage limit policy type for finer-grained consumption control Not checked yet
+4 more
show less
Adds environment flags to tune CORS response headers for MCP endpoints in self-hosted deployments Not checked yet Extends Prompt Security checks with additional coverage and provider-specific configuration hooks Not checked yet Refreshes Beta header forwarding and filtering across providers Not checked yet Supports provider slug references for circuit breaker target resolution Not checked yet
9 details in Everything
Portkey 1.16.1 adds SSRF SSRF Server-side request forgery, an attack that tricks a server into making requests chosen by an attacker. Those requests can reach internal services the attacker cannot access directly. -hardened Agent Gateway fetching, batches output file ID support, and service-to-service config auth
POST /v2/agent-integrations/fetch-agent-card now validates upstream endpoints against SSRF vectors (private IPs, cloud metadata, non-HTTP(S), fragments) and enforces valid JSON {url, name} responses under 1 MB Not checked yet Agent card discovery is restricted to /.well-known/agent-card.json and /.well-known/agent.json, removing the previous fallback to the raw base endpoint Not checked yet PUT /v2/batches/:id now accepts internal_output_file_id for the guardrails-on-batches pipeline, supported by a new internal column on batches records Not checked yet GET /v2/configs now supports data-service token authentication for service-to-service configuration reads Not checked yet
4 details in Everything
Portkey Backend 1.16.0 adds Tavily guardrail, Azure Workload Identity, requests usage-limit policy type, and configurable API key rotation.
Adds Tavily Online Search guardrail with configurable search parameters to inject web results into prompts Not checked yet Adds workload auth mode for Azure OpenAI and Azure AI Foundry integrations requiring azure_workload_client_id and azure_workload_tenant_id Not checked yet Adds entraFederated auth mode for Azure AI Foundry integrations Not checked yet Adds requests as a new usage-limits policy type alongside cost and tokens Not checked yet Allows PUT /v2/policies/usage-limits/:id and PUT /v2/policies/rate-limits/:id to accept conditions in the request body Not checked yet
+3 more
show less
Adds rotation_period_days (1–365) to API key rotation policies alongside existing rotation_period Not checked yet Honours NO_PROXY environment variable for outbound LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. , OIDC OIDC OpenID Connect, a sign-in protocol built on OAuth 2.0. An application uses identity information from a trusted provider instead of maintaining a separate password for each user. , and Mailgun calls Not checked yet Adds REQUEST_TIMEOUT config for outbound fetch timeout in milliseconds Not checked yet
8 details in Everything
└──▷ BREAKING ON UPGRADE
! GET /v1/auth/self now requires a session/JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. and rejects requests authenticated only with an API key! Legacy endpoints /users/firebase-custom-token and /utils/oidc-client-id have been removed
Portkey Frontend 1.8.2 adds auto API key creation, budget reset, and policy condition updates.
Adds the ability to automatically create an API key for an organisation and workspace Not checked yet Adds the ability to reset usage for budget allocation Not checked yet Enables conditions update for policy updates Not checked yet
3 details in Everything
Portkey Data Service adds Azure Blob Storage Azure Blob Storage Microsoft's object-storage service for unstructured data in Azure, offering scalable, cheap storage for files of any size; cyber tools use it to store logs, artifacts, or large datasets without managing infrastructure. backend and FIPS FIPS A set of US federal standards published by NIST that define approved cryptographic algorithms and modules; cyber tools use it to meet compliance requirements in government and regulated environments. -compliant Dockerfile variant in v1.7.1
Adds Azure Blob Storage as a log-export storage backend alongside existing S3 options. Not checked yet Adds FIPS-compliant Dockerfile variant for data-service with FIPS mode enabled and SHA-256 SHA-256 A cryptographic hash function that turns data into a fixed 256-bit fingerprint. It is used to check integrity; hashing does not encrypt the original data. signing. Not checked yet
2 details in Everything
Portkey Backend v1.15 adds auto-generated API keys, custom key rotation, passthrough configs, and granular agent RBAC RBAC Role-based access control, where permissions are assigned to roles such as reader or administrator and users receive those roles. It makes access easier to manage than individual permission lists. .
Adds user_api_key_auto_create organization setting to automatically provision default workspace-user API keys on member join or invite acceptance Not checked yet Adds user_api_key_rotation_period organization setting to enforce automatic API key rotation for workspace-user keys Not checked yet Adds rotation_period_days column to rotation_policies and exposes periodic_reset_days, next_usage_reset_at, and last_reset_at fields on usage limit policies Not checked yet Adds API_KEY_PREFIX environment variable to prefix all newly-generated Portkey API keys in self-hosted deployments Not checked yet Adds pricing_adjustments.multiplier config to integrations for per-token markup/discount multipliers Not checked yet
+13 more
show less
Allows setting models[].configurations.custom_host per integration model via PUT /integrations/:id/integration-models Not checked yet Supports value_format: json in secret_mappings to parse stringified JSON values Not checked yet Adds support for secret_mappings on MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. integrations with resolution at request time Not checked yet Adds azure_auth_mode: entraFederated mode for Azure OpenAI integrations, requiring azure_entra_tenant_id and azure_entra_client_id without a client secret Not checked yet Seeds new bedrock-mantle provider for AWS's OpenAI-compatible Bedrock inference engine Not checked yet Adds allow_subdomains flag to SSO SSO Single sign-on, using one identity provider to sign in to multiple applications. It reduces separate passwords and centralizes account and access management. settings to resolve users from subdomains of an allowed root domain Not checked yet Extends POST /v1/scim/workspaces to accept scim_group_name in addition to scim_group_id Not checked yet Adds organisationAdminsViewLogs and organisationAdminsViewLogMetadata organization settings to control org admin access to request logs and metadata Not checked yet Allows configs to set passthrough: true to mark requests as passthrough mode without provider transformation Not checked yet Adds matchType parameter (exact, contains, containsAll, regex) for guardrails metadata key-value comparison Not checked yet Makes /models route accessible to all workspace roles and renames output field total to total_count Not checked yet Adds granular RBAC scopes: organisation_agent_integrations.*, workspace_agent_integrations.*, agent_servers.*, agent_server_skills.*, agent_integration_skills.*, agent_server_user_access.*, and agents.invoke Not checked yet Adds GET /v1/agent-servers/:id/agent-card endpoint to fetch the upstream agent card Not checked yet
18 details in Everything
Portkey Enterprise Gateway 2.7.1 adds anthropicInspectStreamForOverloadedError to handle Anthropic streaming errors.
Adds anthropicInspectStreamForOverloadedError configuration key to inspect the first chunk of an Anthropic streaming response and return HTTP 529 on overloaded_error, enabling proper retry/fallback logic Not checked yet
1 detail in Everything
Portkey Gateway v2.7 adds Vertex AI Rerank, Bedrock Mantle provider, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. secret support, and Sigstore image signing
Adds bedrock-mantle provider for AWS OpenAI-compatible Bedrock inference with apiKey, assumedRole, and serviceRole auth modes via /v1/chat/completions, /v1/responses, and /v1/messages Not checked yet Supports Vertex AI Rerank on the unified /v1/rerank endpoint using semantic-ranker-default, semantic-ranker-fast, or semantic-ranker-512 models Not checked yet Adds matchType parameter to Required Metadata Key-Value Pairs guardrail supporting exact, contains, containsAll, and regex comparison behaviors Not checked yet Enables MCP integrations to reference centrally-managed secrets via secret_mappings in the integration config, resolved at connection time Not checked yet Adds value_format: json support for Secret Mappings to parse stringified JSON into target fields for structured credentials Not checked yet
+3 more
show less
Allows integration-level cost multipliers via pricing_adjustments.multiplier config key for per-integration markup or discount pricing Not checked yet Outputs signed Docker images using Sigstore Cosign, verifiable against Portkey’s public key before deployment Not checked yet Extends SEMANTIC_CACHE_EMBEDDING_PROVIDER to accept google and vertex-ai values alongside openai for semantic cache population Not checked yet
8 details in Everything
Frontend 1.7.6 adds guardrail pagination, Azure OpenAI/Foundry secret reference integration, and performance fixes
Guardrail List page now supports pagination to handle large numbers of guardrails. Not checked yet Secret Reference Integration support for Azure OpenAI and Azure Foundry setup inside LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. Integrations. Not checked yet
2 details in Everything
Frontend 1.7.5 adds Org/Workspace log management permissions and granular guardrail view/write toggles
Adds Org-Admin permissions for Logs Management at both Org level and Workspace level Not checked yet Adds per-role view and write toggles for Guardrail Management security settings with workspace-level override Not checked yet
2 details in Everything
Portkey Gateway 2.6.2 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. header renaming, Azure Entra federated auth, and Gemini Embedding Embedding Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. 2 support
forward_headers entries now accept { from, to } objects to rename client headers before they reach the upstream. Not checked yet Adds entraFederated auth mode for Azure OpenAI/AI Foundry to exchange AWS web identity tokens for Entra ID Entra ID Microsoft's cloud-based identity and access management service, formerly Azure Active Directory, used by cyber tools to authenticate users and enforce access policies in Microsoft 365 and Azure environments. access tokens access tokens A credential that authorizes a client to use a service or API. It usually has limited permissions and a lifetime; anyone holding it may be able to use those permissions. . Not checked yet gemini-embedding-2-preview is now available on the unified /v1/embeddings route for Vertex AI. Not checked yet
3 details in Everything
Portkey Frontend 1.7.4 adds Logs Path variable in UI, Metadata to Vertex Labels mapping, custom model host provisioning, and Entra-Auth federated support for Azure.
Logs Path variable is now available in the UI Not checked yet Maps Portkey Metadata to Vertex Labels for better observability Not checked yet Enables federated auth support for Entra-Auth for Azure Integrations Not checked yet
3 details in Everything
Adds UI support for Integrations-specific Security Settings and Policy type exclusion in Frontend 1.7.3
Updates UI to support excluding Policy types Not checked yet
1 detail in Everything
Adds Anthropic Batch API support, sensitive header masking, Bedrock reasoning effort, and Agent Gateway preview
Adds /v1/batches endpoint for running asynchronous Claude jobs via the Anthropic Batch API Not checked yet Adds x-portkey-sensitive-headers request header to mask matching values in logs and traces Not checked yet Adds support for reasoning_effort parameter (minimal/low/medium/high/none) for Bedrock Claude reasoning models, mapped to thinking.budget_tokens on earlier models Not checked yet Adds experimental /v1/agent/:agentServerId/* proxy route for Agent Gateway preview with A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. -registry support Not checked yet
4 details in Everything
Portkey Backend 1.14.0 introduces API key rotation, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connection APIs, Lasso classifier, and HADB MySQL support
API Key Rotation is generally available; use *.rotate scope for organization-service, workspace-service, and workspace-user API key types to enable rotation Not checked yet Added organization security settings managersWriteWsIntegrations, managersWriteWsMcpIntegrations, and managersWriteMcpServers with default enabled and workspace-level overrides to control manager write access Not checked yet New GET /v1/mcp-servers/:mcpServerId/connections API for paginated list of user connections to an MCP server Not checked yet New DELETE /v1/mcp-servers/:mcpServerId/connections API to revoke a specific user's connection to an MCP server Not checked yet Added configurable MySQL reader with HADR mode using new env vars DB_READER_HOST, DB_READER_USER, DB_READER_PASS, DB_READER_PORT and MYSQL_WRITER_HADR_MODE=ON for writer failover Not checked yet
+1 more
show less
Added new lasso.classify check to Guardrails Lasso integration with optional apiEndpoint field for self-hosted deployments Not checked yet
6 details in Everything
Portkey Enterprise Gateway v2.6.0 adds Vertex AI label mapping, custom model host routing, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. timeout/env vars, and data URL support.
Adds automatic mapping of Portkey metadata to Vertex AI resource labels across chat/completions, embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. , batches, and fine-tuning with configurable METADATA_MAP_KEY_PREFIX environment variable Not checked yet Enables custom_host routing in model config for custom models, allowing different upstreams per model under the same integration while respecting header-level priority Not checked yet Adds support for base64 data URLs (format: data:<media_type>;base64,<data>) in file.file_data via /chat/completions to forward as Anthropic document content Not checked yet Enables passthrough of top-level cache_control parameter to Anthropic in /chat/completions and adds automatic additionalProperties: false for strict structured outputs structured outputs Forcing a model's response to match a given format or JSON schema, so software can parse it reliably instead of hoping the text is well formed. Not checked yet Adds configurable outbound timeout for MCP calls via MCP_REQUEST_TIMEOUT_MS environment variable and updates MCP_POOL_* env var precedence with new log attributes gateway_version and mcp.auth.upstream_token_refreshed Not checked yet
5 details in Everything
Output guardrails now apply to streaming responses for /chat/completions, /completions, and /messages endpoints.
Adds output_guardrails and after_request_hooks support for streaming responses via SSE SSE Server-Sent Events, a browser API and HTTP-based protocol where a server pushes a stream of text events to a client over a single long-lived connection, giving tools a lightweight alternative to WebSockets for one-way real-time updates. chunks at stream end Not checked yet
1 detail in Everything
Frontend 1.7.0 adds Gateway Registration, API Key Rotation UIs, Anthropic Cache TTL TTL Time to live, a limit on how long data remains valid or how far a packet can travel. Caches use a time limit; IP packets use a hop limit. support, Akto AI plugin, and enhanced Trace View filtering.
Gateway Registration UI added for configuring gateway connections Not checked yet API Key Rotation UI added for managing key lifecycle Not checked yet New Last Reset Date field displayed in Integrations, Providers, API Keys, and Workspace Budgets views Not checked yet Trace View now supports displaying spans without active filters via a new toggle UI element Not checked yet Added configuration option for Anthropic Cache TTL from Playground/Prompts settings Not checked yet
+2 more
show less
Organisation-level maximum session time setting now supported for user management Not checked yet Akto AI added as a supported plugin within the system Not checked yet
7 details in Everything
Portkey Backend v1.13.0 adds API key rotation, organization session management, Required Metadata guardrails, and Agent Gateway CRUD CRUD The four basic database operations — Create, Read, Update, Delete — used as shorthand for any system that manages persistent data records, giving cyber tools a standard model for interacting with stored information. APIs.
Adds automatic and manual API key rotation with rotation_policy config (rotation_period, next_rotation_at, key_transition_period_ms) and new POST /api-keys/:apiKeyId/rotate endpoint Not checked yet Adds session_settings organization-level auth configuration with max_session_ttl to reject expired user sessions Not checked yet Adds Required Metadata Key-Value Pairs guardrail (default.requiredMetadataKeyPairs) with metadataPairs and operator parameters in beforeRequestHook Not checked yet Adds rpw (requests per week) rate limit unit and endpoint_type condition key for granular rate limiting Not checked yet Adds Agent Gateway with full CRUD APIs, agent skills management, workspace-level access control, and RBAC RBAC Role-based access control, where permissions are assigned to roles such as reader or administrator and users receive those roles. It makes access easier to manage than individual permission lists. support Not checked yet
5 details in Everything
Gateway-Local JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. auth via JWT_ENABLED, HEADERS_TO_METADATA injection, weekly rate limits, metadata guardrail, Lasso v3 API, HEIC/HEIF images
Adds JWT_ENABLED=ON environment variable to enable gateway-local JWT validation and support resolving Organisation ID from portkey_oid or organisation_id claims. Not checked yet Adds HEADERS_TO_METADATA environment variable to inject request headers into metadata for observability enrichment without client-side x-portkey-metadata changes. Not checked yet Adds weekly window rate limiting via rpw and endpoint type targeting via endpoint_type condition key in rate limit policies. Not checked yet Adds native metadataPairs guardrail check with all, any, and none operators to validate metadata before request processing. Not checked yet Upgrades Lasso Security integration to v3 API Classify, enabling structured findings-based detection, session/user tracking via sessionId/userId, and configurable apiEndpoint. Not checked yet
+1 more
show less
Adds support for image/heic and image/heif MIME types in multimodal multimodal Able to work with more than one type of input or output, such as text, images and audio. A multimodal model can combine information across those formats. requests and the Inline Image URLs guardrail. Not checked yet
6 details in Everything
Portkey introduces Agent Gateway CRUD CRUD The four basic database operations — Create, Read, Update, Delete — used as shorthand for any system that manages persistent data records, giving cyber tools a standard model for interacting with stored information. , Lasso v3 structured findings, streaming output guardrails, and several gateway/model provider updates for April 2026.
Adds Agent Gateway with CRUD APIs for agent integrations, agent servers, skills, and RBAC RBAC Role-based access control, where permissions are assigned to roles such as reader or administrator and users receive those roles. It makes access easier to manage than individual permission lists. access control Not checked yet Enables API key rotation on schedule or demand, including an explicit manual rotate endpoint and usage reset alongside rotation Not checked yet Introduces Organization session policy with the max_session_ttl setting to enforce idle session expiration Not checked yet Enables local JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. validation in the gateway by setting the environment variable JWT_ENABLED=ON Not checked yet Adds HEADERS_TO_METADATA config key to copy inbound headers into request metadata for tracing and analytics Not checked yet
+17 more
show less
Supports weekly rate limit windows via the rpw policy type and endpoint-scoped limits by type (e.g., chat vs. embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. ) Not checked yet Adds gateway routing configs: passthrough targets, sticky session strategy (strategy.sticky), forward header mapping (forward_headers), and subdomain allowance (allow_subdomain) Not checked yet Enables streaming output guardrails that return a final chunk with the check outcome on the same stream Not checked yet Adds capability to require specific metadata key-value pairs on every LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. request, rejecting mismatches before forwarding Not checked yet Upgrades Lasso security checks to v3 API, returning structured findings (block, auto-mask, warn) and supporting sessionId/userId ties across endpoints Not checked yet Adds Model Rules to tie model access to request metadata and a request-params check to govern tools and parameters before traffic leaves Portkey Not checked yet Separates guardrail definition permissions from execution permissions and clarifies org-level full request log access controls Not checked yet Adds Partner guardrails for building guardrails as partner integrations with built-in step-by-step guidance Not checked yet Guides semantic cache setup directly in the Portkey app UI with in-product policy checks Not checked yet Adds support for Anthropic Files API and batch workloads, including service_tier mapping to speed/priority tiers Not checked yet Enables calling the rerank endpoint through the same Portkey path as chat and embeddings Not checked yet Adds routing for Gemini embedding models embedding models Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. (including 2-preview) using standard OpenAI-compatible shapes Not checked yet Adds support for image/heic and image/heif in multimodal multimodal Able to work with more than one type of input or output, such as text, images and audio. A multimodal model can combine information across those formats. requests, with Inline Image URL guardrail support Not checked yet Preserves the response_format field for Mistral structured JSON outputs through the gateway Not checked yet Adds dedicated connection flows for Claude Cowork, Hermes Agent, Pi, and Slack MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. integrations Not checked yet Surfaces Skills Registry across Portkey in place of the previous Agent Skills naming Not checked yet Updates self-hosted deployment images and provisioning for GCP, AWS, Azure, and Azure Container Apps Not checked yet
22 details in Everything
Portkey Enterprise Gateway 2.4.4 adds Anthropic Files API support via /v1/files, cache TTL TTL Time to live, a limit on how long data remains valid or how far a packet can travel. Caches use a time limit; IP packets use a hop limit. , and OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. semconv alignment.
Adds EXPERIMENTAL_GEN_AI_OTEL_RESOURCE_ATTRIBUTES environment variable for custom OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. resource attributes Not checked yet Supports the /v1/files endpoint for Anthropic Files API integration Not checked yet Adds optional ttl field to cache_control (values 5m or 1h ) for Prompt Caching Not checked yet
3 details in Everything
Portkey Enterprise Gateway 2.4.3 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. event observability and Prometheus env var support
Adds PROMETHEUS_INCLUDE_MODEL_LABEL, PROMETHEUS_INCLUDE_METADATA_LABELS, PROMETHEUS_HISTOGRAM_BUCKETS, PROMETHEUS_HTTP_DURATION_BUCKETS, and PROMETHEUS_GC_BUCKETS environment variable support for configuring Prometheus metrics. Not checked yet Enhances MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. logging to capture all MCP events, including caller identity, authorization scope, decision, and gateway trace_id. Not checked yet
2 details in Everything
Enterprise Gateway v2.4.2 adds native Bedrock structured output structured output Forcing a model's response to match a given format or JSON schema, so software can parse it reliably instead of hoping the text is well formed. enforcement via Converse API's json_schema.
Bedrock structured outputs structured outputs Forcing a model's response to match a given format or JSON schema, so software can parse it reliably instead of hoping the text is well formed. now use outputConfig with json_schema text format via the Converse API for Claude models on Bedrock Not checked yet
1 detail in Everything
Portkey Backend v1.12.1 adds Akto Agentic Security guardrail, inline image URL processing, and Bedrock Custom Host support.
Adds Akto Agentic Security guardrail integration for advanced threat detection and security scanning of LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. inputs and outputs Not checked yet Adds Inline Image URLs guardrail that fetches external image URLs and converts them to Base64 inline data, with configurable providers, maxSizeBytes (default: 20MB), timeoutMs (default: 30000), and failOnError (default: false) Not checked yet Adds optional Custom Host field to the AWS Bedrock guardrail integration schema Not checked yet
3 details in Everything
Portkey Enterprise Gateway 2.4.0 adds DeepInfra tool calling tool calling A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. and Vertex AI metadata forwarding
Adds tool_choice and parallel_tool_calls parameters to the DeepInfra integration for function calling function calling A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. workflows Not checked yet Adds support for the completions and embeddingsembeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. endpoints in the DeepInfra provider configuration Not checked yet Forwards Portkey request metadata as Vertex AI resource labels to enable enterprise governance Not checked yet
3 details in Everything
Portkey Backend 1.12.0 adds Secret Manager integrations, Zscaler guardrail, and GCP WIF WIF Workload Identity Federation is a Google Cloud mechanism that lets external workloads authenticate to Google APIs using short-lived tokens from a trusted identity provider, eliminating the need to manage long-lived service account keys. log storage.
Adds secret_mappings config key and full CRUD CRUD The four basic database operations — Create, Read, Update, Delete — used as shorthand for any system that manages persistent data records, giving cyber tools a standard model for interacting with stored information. API for managing external secret references to AWS Secrets Manager, Azure Key Vault, and HashiCorp Vault Not checked yet Adds new Zscaler AI Guard integration via beforeRequestHook and afterRequestHook with policyId and timeout parameters Not checked yet Adds GCP Workload Identity Federation support for cross-cloud log storage using gcs_assume type and env vars GCP_WIF_AUDIENCE / GCP_WIF_SERVICE_ACCOUNT_EMAIL Not checked yet
3 details in Everything
└──▷ BREAKING ON UPGRADE
! Requires Helm chart upgrade to app-1.6.0 or higher to function correctly
Portkey Enterprise Gateway 2.3.0 adds Akto guardrails, DeepSeek tool calling tool calling A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. /reasoning, Azure rerank, Vertex web search, AWS-to-GCP WIF WIF Workload Identity Federation is a Google Cloud mechanism that lets external workloads authenticate to Google APIs using short-lived tokens from a trusted identity provider, eliminating the need to manage long-lived service account keys. , and Bedrock batch embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. .
beforeRequestHook and afterRequestHook now support the Akto Agentic Security guardrail with a configurable timeout (default 5000ms) for prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. and data leakage protection Not checked yet deepseek-chat provider gains support for tools, tool_choice, and stream_options parameters, enabling tool calling capabilities Not checked yet deepseek-reasoner provider adds reasoning mode via the reasoning_effort parameter and returns reasoning_content in streaming responses Not checked yet Azure AI Foundry now supports reranking reranking A model that re-scores a first batch of search results against the query and reorders them, more accurately than the fast first-stage search. via Cohere models (e.g., cohere.Cohere-rerank-v4.0-pro) with automatic stripping of the cohere. prefix Not checked yet Vertex AI provider accepts enterpriseWebSearch or enterprise_web_search in the tools array to enable enterprise web search grounding with distinct cost attribution Not checked yet
5 details in Everything
Portkey Frontend 1.6.8 introduces Zscaler integration and Policy v2.0.0 support.
Introduced Zscaler integration Not checked yet Upgraded Policy to version 2.0.0 Not checked yet
2 details in Everything
Adds conditional redirection and new security reference feature to Playground UI
Added conditional redirection support Not checked yet Added summary tables for improved data visibility Not checked yet Added new security reference feature Not checked yet
3 details in Everything
Portkey March 2026 adds secret references, zscaler/akto guardrails, GCP WIF WIF Workload Identity Federation is a Google Cloud mechanism that lets external workloads authenticate to Google APIs using short-lived tokens from a trusted identity provider, eliminating the need to manage long-lived service account keys. logs, and new model support
Adds secret_mappings configuration to reference credentials from AWS Secrets Manager, Azure Key Vault, or HashiCorp Vault instead of storing keys directly. Not checked yet Adds rpw weekly budget windows for rate limiting, allowing spend caps aligned with weekly review cycles. Not checked yet Adds endpoint-scoped rate limits by endpoint type (e.g., chat completions, embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. ) to apply different limits to different API surfaces. Not checked yet Adds support for Zscaler AI Guard as a guardrails partner via beforeRequestHook and afterRequestHook with required policyId. Not checked yet Adds support for Akto Agentic Security as a guardrails partner for scanning LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. inputs/outputs, with configurable timeout (default 5000 ms). Not checked yet
+10 more
show less
Adds customHost field to Bedrock guardrail plugin configuration to direct checks to private or regional endpoints. Not checked yet Adds required metadata key–value enforcement in guardrails to block requests missing specified fields before model reach. Not checked yet Adds GCS log storage capability from AWS using GCP_WIF_AUDIENCE and GCP_WIF_SERVICE_ACCOUNT_EMAIL for cross-cloud authentication without static keys. Not checked yet Adds workspace slug support in analytics filters alongside IDs for archived workspaces. Not checked yet Adds DeepInfra provider support with tools, tool_choice, and parallel_tool_calls for tool calling tool calling A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. , plus completions and embeddings endpoints. Not checked yet Adds DeepSeek (deepseek-chat, deepseek-reasoner) provider support including stream_options handling and reasoning content mapping. Not checked yet Adds Vertex AI enterprise web search grounding via enterpriseWebSearch/enterprise_web_search with separate cost attribution. Not checked yet Adds AWS–GCP WIF support for Vertex AI access using GCP_WIF_AUDIENCE and GCP_WIF_SERVICE_ACCOUNT_EMAIL. Not checked yet Adds Azure AI Foundry rerank support for Cohere models, stripping the cohere. provider prefix. Not checked yet Adds Bedrock batch inference support for embeddings alongside chat completions. Not checked yet
15 details in Everything
Portkey Backend 1.11.2 adds grouped analytics endpoints, archived workspace filtering, and API enhancements for integrations, prompts, and gateway config.
Added GET /v1/analytics/groups/:groupBy and GET /v1/logs/groups/:groupBy generic grouped analytics endpoints with configurable columns Not checked yet Added status query parameter to the workspace list API (GET /workspaces) to filter by active or archived status Not checked yet Added create_default_provider and default_provider_slug fields to the integration creation API for workspace integrations Not checked yet Added patch flag to PUT /prompts/{promptId} to enable partial version field updates Not checked yet Added azure_entra_scope option to the gateway config schema for specifying custom Azure Entra ID Entra ID Microsoft's cloud-based identity and access management service, formerly Azure Active Directory, used by cyber tools to authenticate users and enforce access policies in Microsoft 365 and Azure environments. authentication scopes at the config level Not checked yet
5 details in Everything
Enterprise Gateway 2.2.5 adds secondary Redis for workers and configurable Prometheus metrics.
Adds REDIS_WORKERS_URL, REDIS_WORKERS_HOST, REDIS_WORKERS_PORT, REDIS_WORKERS_USERNAME, REDIS_WORKERS_PASSWORD, REDIS_WORKERS_TLS_ENABLED, and REDIS_WORKERS_AUTH_MODE environment variables to route BullMQ workers to a dedicated Redis instance. Not checked yet Adds PROMETHEUS_INCLUDE_MODEL_LABEL, PROMETHEUS_INCLUDE_METADATA_LABELS, and PROMETHEUS_LABELS_METADATA_ALLOWED_KEYS environment variables to configure Prometheus metric cardinality. Not checked yet Adds native Responses API support for the Perplexity provider. Not checked yet Adds embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. endpoint support for the OpenRouter OpenRouter A unified API gateway that routes requests to dozens of LLM providers under one endpoint, letting cyber tools swap or compare models without rewriting provider-specific integration code. provider. Not checked yet
4 details in Everything
Portkey Backend 1.11.1 introduces configuration capabilities for airgapped environments, specifically allowing custom OpenID Connect OpenID Connect OpenID Connect, a sign-in protocol built on OAuth 2.0. An application uses identity information from a trusted provider instead of maintaining a separate password for each user. scopes via a new environment variable.
Adds OIDC_CUSTOM_SCOPES environment variable to configure additional custom OIDC OIDC OpenID Connect, a sign-in protocol built on OAuth 2.0. An application uses identity information from a trusted provider instead of maintaining a separate password for each user. scopes (comma-separated) for airgapped deployments Not checked yet
1 detail in Everything
Portkey Frontend adds API key filtering by type and column sorting
Adds the ability to filter API keys by API Key Type (User, Service) in the frontend interface Not checked yet Adds the ability to sort API keys by column name in the frontend table view Not checked yet
2 details in Everything
Portkey Backend 1.11.0 adds data_visibility workspace settings for scoped observability data access.
Adds membersViewAllData setting to restrict workspace members' view of logs and analytics to their own keys Not checked yet Adds managersViewAllData setting to restrict managers' view of logs and analytics to the keys they manage Not checked yet Supports data_visibility override category for workspace-level configuration Not checked yet
3 details in Everything
Portkey Enterprise Gateway 2.2.4 adds Anthropic Bedrock citations, Zscaler AI Guard integration, SSE SSE Server-Sent Events, a browser API and HTTP-based protocol where a server pushes a stream of text events to a client over a single long-lived connection, giving tools a lightweight alternative to WebSockets for one-way real-time updates. streaming for TTS, and ZhipuAI image generation support.
Adds stream_format: "sse" to OpenAI and Azure OpenAI text-to-speech requests for Server-Sent Events Server-Sent Events An HTTP-based protocol where a server pushes a continuous stream of text events to a client over a single long-lived connection, giving cyber tools a lightweight alternative to WebSockets for one-way real-time data feeds. audio streaming with usage logging Not checked yet Adds Zscaler AI Guard as a new guardrails partner for DLP DLP Data Loss Prevention: a category of controls that inspect and block sensitive data from leaving an organisation via email, web, or removable media, giving cyber tools a policy enforcement layer over data in motion and at rest. and prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. protection on inbound prompts and outbound responses Not checked yet Adds Anthropic’s citations feature support on Bedrock for chat completions API Not checked yet Adds ZhipuAI image generation support through the CogView model family (e.g., cogview-4-250304) with parameters prompt, model, n, size, response_format, and user Not checked yet Adds x-portkey-vertex-auth-type provider option for Vertex AI to configure authentication type (e.g., workload identity workload identity An identity assigned to software, such as a service or container, rather than a person. It lets the workload authenticate and receive permissions without sharing a user's credentials. ) Not checked yet
+1 more
show less
Automatically records user_id in analytics from the API key’s associated user Not checked yet
6 details in Everything
Backend 1.10.0 adds prompt access control settings, custom budget reset intervals via new API fields, and SCIM SCIM A standard for creating, updating and removing user accounts and groups across applications. It helps an identity provider keep access in sync when people join, change roles or leave. group management for AirGapped environments.
membersViewPrompts and membersWritePrompts config keys to control workspace member prompt permissions Not checked yet managersViewPrompts and managersWritePrompts config keys to control workspace manager prompt permissions Not checked yet Custom periodic reset intervals for workspace budget limits via the periodic_reset_days field (1–365 days) Not checked yet The next_usage_reset_at field (ISO 8601 ISO 8601 An international standard for representing dates and times as text, using formats like 2025-04-23T14:00:00Z. Tools adopt it to ensure timestamps are unambiguous and sortable across systems and locales. ) to specify the first custom reset date for budgets Not checked yet SCIM User-Based Group Management in AirGapped mode using the SCIM /Users endpoint when SCIM_MEMBERSHIP_USER_MODE=ON is set Not checked yet
+2 more
show less
groups attribute included in user SCIM responses to expose current group memberships Not checked yet New authentication type Workload Identity Federation for Vertex AI integrations Not checked yet
7 details in Everything
└──▷ BREAKING ON UPGRADE
! periodic_reset_days is mutually exclusive with the existing periodic_reset (weekly / monthly) option
Frontend 1.6.3 adds API key filtering, prompts security settings, and workspace budget resets
Adds support for User and Service key filter in API Key List page Not checked yet Adds Security setting for Prompts View and Management Not checked yet Adds support for Workspace Budget periodic reset by date Not checked yet
3 details in Everything
Portkey Backend 1.9.0 adds per-role analytics access control, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. metadata APIs, and self-hosted feature flags.
Added managersViewAnalytics config setting to control workspace manager analytics visibility Not checked yet Added membersViewAnalytics config setting to control workspace member analytics visibility Not checked yet Added GET /mcp-servers/:id/metadata endpoint for fetching detailed MCP server metadata Not checked yet
3 details in Everything
Enterprise Gateway 2.2.3 adds Databricks provider, Together AI reasoning models, and native Responses API for Groq/OpenRouter OpenRouter A unified API gateway that routes requests to dozens of LLM providers under one endpoint, letting cyber tools swap or compare models without rewriting provider-specific integration code. /xAI
Adds Databricks as a new provider for chat completions, completions, and embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. . Not checked yet Enables Together AI reasoning/thinking model support via the reasoning_effort parameter and content_blocks in responses when strictOpenAiCompliance is set to false. Not checked yet Routes Groq, OpenRouter, and xAI Responses API requests to their native /responses endpoints. Not checked yet
3 details in Everything
Portkey Enterprise Gateway 2.2.2 adds Claude 4.6 support, native Responses API providers, and reasoning controls
Adds thinking: { type: 'adaptive' } with reasoning_effort for Claude 4.6 Not checked yet Adds output_config.format passthrough for structured outputs structured outputs Forcing a model's response to match a given format or JSON schema, so software can parse it reliably instead of hoping the text is well formed. in Anthropic/Bedrock/Azure Not checked yet Adds cache_control preservation on content items and tools in the Responses API adapter Not checked yet Adds native provider support for x-ai (Grok), Groq, OpenRouter OpenRouter A unified API gateway that routes requests to dozens of LLM providers under one endpoint, letting cyber tools swap or compare models without rewriting provider-specific integration code. , and Azure AI Foundry in Responses API Not checked yet
4 details in Everything
Portkey Data Service adds dedicated batch pricing configurations via Gateway integration.
└──▷ BREAKING ON UPGRADE
! Requires Enterprise Gateway version v2.1.0 or higher to support dedicated batch pricing.
Responses API now works with all providers via /v1/responses; batch pricing configs and Vertex cost attribution skip added
Adds support for the OpenAI Responses API (/v1/responses) with all 70+ providers , not just OpenAI and Azure OpenAI. Not checked yet Adds vertex_skip_ptu_cost_attribution config key in Model Catalog settings to skip cost attribution for Vertex AI Provisioned Throughput deployments. Not checked yet Adds dedicated batch pricing configurations via the Data Service, defaulting to 50% of standard pricing when specific pricing is unavailable. Not checked yet Adds vertexSkipPtuCostAttribution field to the Virtual Key API for Vertex AI. Not checked yet
4 details in Everything
Portkey Backend 1.8.0 introduces Gateway Deployments with RBAC RBAC Role-based access control, where permissions are assigned to roles such as reader or administrator and users receive those roles. It makes access easier to manage than individual permission lists. , new CrowdStrike integration, and workspace manager API key creation.
Adds production and non-production deployment types with separate limits Not checked yet Adds deployment slugs for human-readable identifiers in the Gateway Deployments system Not checked yet Adds dedicated RBAC permissions (deployments:create, deployments:read, deployments:update, deployments:delete, deployments:list) for Gateway Deployments Not checked yet Adds support for filtering deployments by type in the list endpoint Not checked yet Adds CrowdStrike AIDR partner integration for scanning LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. inputs and outputs Not checked yet
+4 more
show less
Enhances Usage & Rate Limit Policies with new conditions (refer to Documentation) Not checked yet Routes alert emails to workspace admins and managers in addition to organization admins Not checked yet Enables Workspace managers to create API keys on behalf of other users by specifying a user_id Not checked yet Adds optional skipPtuCostAttribution field for Vertex AI integrations and virtual keys Not checked yet
9 details in Everything
Frontend 1.6.1 adds multi-org SSO SSO Single sign-on, using one identity provider to sign in to multiple applications. It reduces separate passwords and centralizes account and access management. , workspace-level MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. access control, and saved filter search.
Adds SSO login support for multiple SSO enabled Organisations in the security settings UI Not checked yet Adds Policy management UI Updates to support Organisation level multiple guardrails Not checked yet Adds MCP capabilities support for the MCP Gateway and MCP access control support at Workspace level Not checked yet Adds Search support for Saved Filters in the UI Not checked yet Adds Logs Table column resize support Not checked yet
5 details in Everything
Portkey adds gRPC gRPC An open-source remote procedure call framework from Google that uses HTTP/2 and Protocol Buffers to let services call each other's functions across a network, giving tools low-latency, strongly typed inter-process communication. transport, universal Messages/Responses APIs, Zscaler Guard integration, and default config in JWTs JWTs JSON Web Tokens — an open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object. Cyber tools use them for stateless authentication without server-side session storage.
└──▷ HOW TO FIND IT
Install the official Portkey skills to teach Cursor or Copilot how to use the SDK.
📍 npx add-skill portkey-ai/skills
/v1/responses endpoint now routes to any provider (not just OpenAI). Not checked yet /v1/messages adapter now works with non-Anthropic providers. Not checked yet gRPC transport support added to the Gateway alongside HTTP/REST. Not checked yet JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. defaults claim allows embedding embedding Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. default configs per-token. Not checked yet npx add-skill portkey-ai/skills installs Portkey skills for AI coding assistants. Not checked yet
+8 more
show less
ZscalerAI Guard guardrail integration supports detection policies and DLP DLP Data Loss Prevention: a category of controls that inspect and block sensitive data from leaving an organisation via email, web, or removable media, giving cyber tools a policy enforcement layer over data in motion and at rest. blocking. Not checked yet New reasoning_effort parameter supported on Claude 4.6 and Together AI models. Not checked yet output_config structured output structured output Forcing a model's response to match a given format or JSON schema, so software can parse it reliably instead of hoping the text is well formed. format available via Claude 4.6 adapter. Not checked yet Veo model support on Vertex AI enables text-to-video generation. Not checked yet Passthrough provider sends raw requests without Portkey parameter mapping. Not checked yet stream_format: "sse" enables Server-Sent Events Server-Sent Events An HTTP-based protocol where a server pushes a continuous stream of text events to a client over a single long-lived connection, giving cyber tools a lightweight alternative to WebSockets for one-way real-time data feeds. streaming for OpenAI/Azure TTS. Not checked yet ZhipuAI cogview-4-250304 image generation supported. Not checked yet media_resolution, vertex_skip_ptu_cost_attribution, and x-portkey-vertex-auth-type headers added for Vertex AI control. Not checked yet
13 details in Everything
Enterprise Gateway 2.0.0 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. GA, unified rerank API, new budget condition keys, inline images plugin, and dynamic pricing.
MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. is now Generally Available with centralized server management, OAuth 2.1 OAuth 2.1 A consolidated draft of the OAuth authorization framework that merges OAuth 2.0 with its most important security BCP updates, dropping unsafe flows so tools can delegate user access without handling credentials directly. /API key auth, workspace-level provisioning, and full observability Not checked yet /rerank unified endpoint provides consistent reranking reranking A model that re-scores a first batch of search results against the query and reorders them, more accurately than the fast first-stage search. across Cohere, Jina, and Voyage AI without code changes Not checked yet New condition keys for budget/rate limit policies: virtual_key, provider, config, prompt, and model (with wildcard support) Not checked yet Inline Image URLs Plugin converts external image URLs to inline base64 data for VPC VPC A logically isolated virtual network inside a public cloud provider's infrastructure, letting tools deploy resources with private addressing, controlled routing, and firewall rules without managing physical hardware. -SC environments Not checked yet MODEL_CONFIGS_PROXY_FETCH_ENABLED=ON environment variable enables dynamic model pricing fetch in Air-Gapped deployments via Backend service Not checked yet
+1 more
show less
GCP Workload Identity support for keyless authentication in GKE GKE Google Kubernetes Engine, Google's managed Kubernetes service, which lets cyber tools run containerized workloads without managing the underlying cluster infrastructure. environments accessing GCS and VertexAI Not checked yet
6 details in Everything
Adds CrowdStrike AIDR partner plugin integration for LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. input/output scanning in Enterprise Gateway 1.17.15
Portkey Backend 1.7.3 adds tag support for integrations/providers, MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. email/username fields, and JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. scopes.
Adds tags parameter support when creating or updating integrations/providers and allows filtering by tags in list endpoints Not checked yet MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. OAuth token introspection endpoint now returns email and username fields for richer user context Not checked yet Added read and list scopes to control plane resources for JWT-authenticated requests Not checked yet
3 details in Everything
Portkey Enterprise Gateway 1.17.12 adds Responses API Hooks, Azure Shield Prompt/Protected Material guardrails, and sequential execution.
Apply input/output guardrails and custom webhooks to /v1/responses endpoint via new Responses API Hooks support Not checked yet Detect jailbreak and prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. attacks using Shield Prompt Azure AI Content Safety integration Not checked yet Detect copyrighted or protected text content in LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. outputs using Protected Material Azure AI Content Safety integration Not checked yet Execute guardrails sequentially using the new sequential flag instead of parallel execution Not checked yet Add real-time voice interaction support for xAI via Realtime Voice Agent API (Grok Voice API) with WebSocket WebSocket A protocol that upgrades an HTTP connection into a persistent, full-duplex channel, letting a server push data to a client without repeated polling. Cyber tools use it for real-time event streaming and live command output. connections Not checked yet
+5 more
show less
Add Google Maps grounding support for Gemini/Vertex AI models Not checked yet Support new parameters for gpt-image-1: moderation, output_format, output_compression, background, partial_images, and stream Not checked yet Specify custom authentication scopes for Azure OpenAI Entra ID Entra ID Microsoft's cloud-based identity and access management service, formerly Azure Active Directory, used by cyber tools to authenticate users and enforce access policies in Microsoft 365 and Azure environments. auth using the x-portkey-azure-entra-scope header Not checked yet Support output_expires_after parameter for batch creation, plus input_blob and output_folder for Azure OpenAI blob-based inputs Not checked yet Enable Anthropic citations feature via native Messages API format on Bedrock /v1/messages route Not checked yet
10 details in Everything
Portkey Backend v1.7.0 adds workspace deployment restrictions, SSO SSO Single sign-on, using one identity provider to sign in to multiple applications. It reduces separate passwords and centralizes account and access management. auto-provisioning, OCI OCI Open Container Initiative standard, maintained by the Linux Foundation, defining the image format and runtime spec that container tools share so images built once run anywhere OCI-compliant. provider support, and new model configuration environment variables.
Adds workspace-based deployment restrictions to gateways for multi-tenant isolation Not checked yet Adds endpoints to assign workspaces during gateway create/update operations Not checked yet Adds a new API endpoint to retrieve entities (API keys, workspaces, users) associated with usage and rate limit policies Not checked yet Enables automatic provisioning of first-time SSO users via OIDC OIDC OpenID Connect, a sign-in protocol built on OAuth 2.0. An application uses identity information from a trusted provider instead of maintaining a separate password for each user. or SAML SAML A standard for passing signed identity assertions between a sign-in provider and an application. It lets a user sign in through their organization's identity provider. Not checked yet Adds Oracle Cloud Infrastructure (OCI) Generative AI as a supported provider Not checked yet
+2 more
show less
Adds MODEL_CONFIGS_PROXY_FETCH_ENABLED, MODEL_CONFIGS_PROXY_URL, MODEL_CONFIGS_PRICING_LOG_STORE_PATH, MODEL_CONFIGS_CAPABILITIES_LOG_STORE_PATH, MODEL_CONFIGS_CAPABILITIES_LOCAL_PATH, and MODEL_CONFIGS_PRICING_LOCAL_PATH environment variables for model config sourcing Not checked yet Enables automatic reactivation of exhausted workspace budgets when credit limits are increased Not checked yet
7 details in Everything
Frontend 1.6.0 adds per-key expiration (next reset date) and model capability sync in UI.
Added configuration changes to sync with the models list and model capabilities specific to provider Not checked yet
1 detail in Everything
Portkey Backend 1.6.2 adds auto-expiry for API keys and MySQL SSL SSL A cryptographic protocol for encrypting network connections, now deprecated in favor of TLS but whose name persists colloquially. Cyber tools reference it when handling HTTPS or other encrypted-channel inspection and termination. configuration via env vars.
Expired API keys are now automatically marked as expired by a background worker process Not checked yet Added support for external MySQL SSL connection modes via the DB_SSL environment variable Not checked yet
2 details in Everything
Adds nested Prompt folders, Oracle Provider, sequential Guardrails execution, and request/response breakdown to the UI
Added nested Prompt folder support on UI Not checked yet Added Oracle Provider support on UI Not checked yet Added option to execute Guardrails sequentially Not checked yet Added support for breakdown of LLM requests and responses Not checked yet Added UI support for Retry Exhausted state for Logs Not checked yet
5 details in Everything
Portkey introduces MCP Gateway MCP Gateway A server that sits between MCP clients and one or more Model Context Protocol backends, routing tool calls and aggregating context sources so a single endpoint exposes many AI-agent integrations at once. GA, Unified Rerank API, Azure Shield/Protected Material guardrails, and enhanced rate-limit policy matching.
MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Gateway is now generally available for unified MCP tool access with built-in auth support, central registry, RBAC RBAC Role-based access control, where permissions are assigned to roles such as reader or administrator and users receive those roles. It makes access easier to manage than individual permission lists. , and full observability Not checked yet Adds the sequential flag to enable sequential execution of guardrail checks instead of parallel Not checked yet Integrates CrowdStrike AI Detection and Response as a new guardrail integration Not checked yet Adds Azure Shield Prompt guardrail for jailbreak and prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. detection in system prompts and user messages Not checked yet Adds Azure Protected Material guardrail to scan LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. outputs for known copyrighted or protected text Not checked yet
+4 more
show less
Adds the /rerank endpoint for a unified reranking reranking A model that re-scores a first batch of search results against the query and reorders them, more accurately than the fast first-stage search. API supporting Cohere, Jina, and Voyage AI Not checked yet Expands rate limit policy matching to include virtual_key, provider, config, prompt, and model (with wildcard support) Not checked yet Adds support for OpenAI gpt-image-1 parameters including moderation, output_format, output_compression, background, partial_images, stream, and batch creation with output_expires_after Not checked yet Enables Google Maps grounding to add map and location context to Gemini and Vertex AI responses Not checked yet
9 details in Everything
Enterprise Gateway 1.17.11 adds ENABLE_PROMETHEUS env var to disable metrics collection.
Portkey Enterprise Gateway 1.17.9 adds Azure image edits and Gemini image config
Adds image_config parameter with aspect_ratio and image_size fields for Gemini/Vertex AI image generation Not checked yet
1 detail in Everything
Portkey Backend v1.6.1 adds Guardrails config keys, new providers, and SCIM SCIM A standard for creating, updating and removing user accounts and groups across applications. It helps an identity provider keep access in sync when people join, change roles or leave. parsing fixes
Adds guardrails configuration schema with tools (blockedTypes, allowedTypes, blockedFunctionNames, allowedFunctionNames) and params (blockedKeys, allowedKeys, values) sub-keys to control request filtering Not checked yet Adds Javelin, Qualifire, and Walled as new plugin providers Not checked yet Updates /spans endpoint aggregate metrics to include total tokens count Not checked yet
3 details in Everything
Portkey Frontend 1.5.5 adds embedding embedding Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. /completion support, prompt copy, and new guardrail/plugin UI
Added embedding text and completion support on getting started and model integrations Not checked yet Added copy option on Prompt Playground on Each messages Not checked yet Updated new Guardrails and Plugins support Not checked yet
3 details in Everything
Portkey Enterprise Gateway v1.17.7 adds Blocked Tools guardrail, Redis Cluster Redis Cluster A distributed mode of Redis, the open-source in-memory data store, that automatically shards data across multiple nodes and keeps it available if some nodes fail, giving cyber tools low-latency shared state at scale. discovery, and semantic cache config env vars.
REDIS_CLUSTER_ENDPOINTS, REDIS_CLUSTER_DISCOVERY_URL, REDIS_CLUSTER_DISCOVERY_AUTH, and REDIS_CLUSTER_DISCOVERY_REFRESH_INTERVAL environment variables support dynamic Redis cluster discovery and static configuration Not checked yet SEMANTIC_CACHE_EMBEDDING_DIMENSIONS environment variable allows setting custom embedding embedding Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. dimensions for the semantic cache (default: 1536) Not checked yet New Blocked Tools guardrail plugin adds function, web_search_preview, web_search, file_search, code_interpreter, computer_use, and mcp tool type blocking via blocklists or allowlists Not checked yet
3 details in Everything
Adds file_upload_failed and batch_start_failed statuses for LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateway batch jobs.
file_upload_failed status indicates the batch job failed to upload the file to the provider after validation Not checked yet batch_start_failed status indicates the file upload succeeded but the batch job submission to the provider failed Not checked yet
2 details in Everything
Enterprise Gateway 1.17.5 adds SSRF SSRF Server-side request forgery, an attack that tricks a server into making requests chosen by an attacker. Those requests can reach internal services the attacker cannot access directly. protection, configurable vector similarity metrics, and provider auth via query params.
Added request validation to prevent Server-Side Request Forgery (SSRF) attacks via configuration URLs Not checked yet Added configurable similarity metric support for Milvus and Pinecone vector stores vector stores A database built to store embeddings and find the nearest ones to a query quickly. It is the retrieval half of most RAG systems. in Semantic Cache (COSINE, L2, IP) Not checked yet Added support for provider authentication via query parameters in the Realtime API (e.g., model=@provider/model) Not checked yet Set span.kind = SERVER on exported OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. spans Not checked yet
4 details in Everything
Portkey Enterprise Gateway 1.17.4 adds Anthropic Claude models and native messages endpoint via Azure AI Foundry
Adds Azure AI Foundry support for Anthropic Claude models (claude-opus-4-5-20251101, claude-sonnet-4-5-20250929, claude-haiku-4-5-20251001) Not checked yet Enables native /messages endpoint support for Azure AI Foundry Anthropic providers, including extended thinking extended thinking Intermediate reasoning a model writes out before its final answer. Reasoning models generate it automatically and it is often billed as extra output tokens. , prompt caching, and native streaming Not checked yet
2 details in Everything
Adds cost calc for Gemini image models, thought_signature support, and Bedrock AWS region header
Adds cost calculation support for gemini-2.5-flash-image and gemini-3-pro-image-preview models Not checked yet Adds support for the thought_signature parameter. Not checked yet Added support for the x-portkey-aws-region header to set the region for Bedrock and SageMaker integration with serviceRole auth type Not checked yet
3 details in Everything
Frontend 1.5.4 adds SCIM SCIM A standard for creating, updating and removing user accounts and groups across applications. It helps an identity provider keep access in sync when people join, change roles or leave. group workspace mapping, SSO SSO Single sign-on, using one identity provider to sign in to multiple applications. It reduces separate passwords and centralizes account and access management. confirmation modal, and AWS region config for service role auth.
SCIM group workspace mapping management available in UI to configure which SCIM groups map to which workspaces Not checked yet Confirmation modal added before enabling the SSO Only Login flow to prevent accidental lockout Not checked yet Support for specifying an AWS region when using service role-based authentication for Bedrock and Sagemaker Not checked yet
3 details in Everything
Portkey Backend 1.6.0 adds SCIM SCIM A standard for creating, updating and removing user accounts and groups across applications. It helps an identity provider keep access in sync when people join, change roles or leave. group-to-workspace mapping and AWS Bedrock region parameter support
Introduced flexible group-to-workspace mapping for SCIM integrations from Okta or Azure Entra Not checked yet Added support for the aws_region parameter in the Bedrock integration for serviceRole auth type Not checked yet
2 details in Everything
Portkey Enterprise Gateway 1.17.1 adds streaming hook results and F5 Guardrails plugin
Adds hook results in streaming responses for /chat/completions, /completions, /embeddings, and /messages endpoints to enable real-time content policy enforcement. Not checked yet Introduces new F5 Guardrails partner plugin integration for content moderation and PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. detection/rediation. Not checked yet Expands cost calculation support for image generation (TogetherAI), video generation (VertexAI Veo models, OpenAI/Azure Sora models). Not checked yet
3 details in Everything
Portkey Backend v1.5.1 adds F5 Guardrails dependencies and log path support
Added backend dependencies for the new F5 Guardrails Not checked yet Added support to read logs based on the path format identifier released in Gateway v1.17.0 Not checked yet
2 details in Everything
Portkey Frontend 1.5.1 adds OpenAI gpt5.1 support, base64 image download in logs, and integration UI enhancements.
gpt5.1 models are now supported Not checked yet Logs display any base64 URL with a Download option Not checked yet Selected models prominently displayed at the top of the Update Integration Models page Not checked yet
3 details in Everything
Frontend 1.5.0 adds workspace member config management, trace/log UI categories, zhipu models, and non-root container security.
Non-root container image enforcing a non-root securityContext replaces the previous root-user image Not checked yet Traces are highlighted by their category in the UI Not checked yet Logs with Guardrails are improved for visibility in the UI Not checked yet New models added to the zhipu provider integration Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! The container image no longer runs as root; it enforces a non-root securityContext requiring a Helm repo upgrade (>app-1.4.0)
Portkey Backend 1.5.0 introduces usage limits and rate limit policy APIs with dynamic condition support.
Adds usage limits and rate limit policy APIs to allow organizations to apply flexible budget and rate limit controls based on dynamic conditions such as API keys, metadata, or workspace Not checked yet Adds a new column in ClickHouse to store the log object path format identifier Not checked yet
2 details in Everything
Data Service 1.4.0 introduces non-root container enforcement and multi-provider fine-tuning cost logic.
Adds cost calculation logic for fine-tuning operations across OpenAI, Azure OpenAI, and Vertex AI Not checked yet
1 detail in Everything
└──▷ BREAKING ON UPGRADE
! The container image no longer runs as root; processes now run with a non-root UID, requiring Helm repo upgrade (>app-1.4.0)
Portkey Gateway 1.17.0 adds usage limits, OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. tracing, fine-tuning cost tracking, and hourly S3 logs
Adds LOG_STORE_FILE_PATH_FORMAT environment variable to toggle log storage between flat (v1) and time-hierarchical (v2) paths. Not checked yet Introduces usage limits and rate limit policies based on API keys, metadata, workspace, or other dynamic conditions. Not checked yet Adds support for OpenTelemetry W3C trace context headers (traceparent and baggage) to automatically map to internal tracing. Not checked yet Adds cost calculation logic for fine-tuning operations across OpenAI, Azure OpenAI, and Vertex AI. Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! Removed root user from container image. The container image no longer runs as root; it now runs processes with a non-root UID and enforces a non-root container securityContext.
Portkey Backend 1.4.0 introduces API-driven deployment management and customizable branding via environment variables, while enforcing non-root container execution.
└──▷ BREAKING ON UPGRADE
! The container image no longer runs as root; processes now use a non-root UID and enforce a non-root securityContext, requiring Helm repo update.
v1.3.3: List traces API returns more details; JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. guardrail schema updated for new Gateway parameters
Updates JWT Guardrail schema to support new parameters from the latest Gateway build Not checked yet
1 detail in Everything
Enterprise Gateway 1.16.6 adds llm_token_sum metric, Modal provider, JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. plugin claims injection, and skip.auth env var
Adds llm_token_sum Prometheus metric to track total LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. tokens consumed Not checked yet Adds support for Modal as a new LLM provider Not checked yet Adds claim extraction and injection into request context as headers in JWT Plugin Not checked yet Adds flexible claim validation with multiple match types (exact, contains, containsAll, regex) in JWT Plugin Not checked yet Adds token introspection endpoint validation as an alternative to JWKS JWKS A JSON Web Key Set, a published collection of cryptographic keys. Applications use it to find the public key needed to verify a token's signature. in JWT Plugin Not checked yet
+1 more
show less
Adds SKIP_DATAPLANE_CONFIG_CHECK environment variable to allow configs with multiple targets for unified batches file upload endpoints Not checked yet
6 details in Everything
Portkey Frontend v1.4.9 adds JSON mode JSON mode Forcing a model's response to match a given format or JSON schema, so software can parse it reliably instead of hoping the text is well formed. for prompts, workspace search on MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Consent, and Azure/OpenAI transcribe model support.
Adds JSON mode for prompt parameters to enable real-time updates and easier editing Not checked yet Improves MCP Consent page to allow searching by workspaces Not checked yet Supports transcribe models under Azure and OpenAI providers Not checked yet Adds search functionality to the Analytics Filter API key field Not checked yet
4 details in Everything
Portkey Enterprise Gateway 1.16.5 adds VertexAI Computer Use support, WebSocket WebSocket A protocol that upgrades an HTTP connection into a persistent, full-duplex channel, letting a server push data to a client without repeated polling. Cyber tools use it for real-time event streaming and live command output. proxy, and new CORS CORS A browser mechanism that lets a server declare which foreign origins may read its HTTP responses, enforced by the browser to block unauthorized cross-site requests from JavaScript. env vars
Adds anthropic-beta header support (also mapped to x-portkey-anthropic-beta) for VertexAI provider Not checked yet Adds support for conversation and modalities parameters for OpenAI provider Not checked yet Adds HTTP proxy support for WebSockets via the HTTPS_PROXY environment variable Not checked yet Adds four CORS configuration environment variables: CORS_ALLOWED_ORIGINS, CORS_ALLOWED_METHODS, CORS_ALLOWED_HEADERS, and CORS_ALLOWED_EXPOSE_HEADERS Not checked yet
4 details in Everything
Portkey Backend 1.3.2 adds Workspace Grouped Analytics API and Multi-Organization SSO SSO Single sign-on, using one identity provider to sign in to multiple applications. It reduces separate passwords and centralizes account and access management. support
Adds GET /workspaces/analytics API endpoint for workspace-grouped analytics with multi-dimensional grouping and cost-based filtering Not checked yet Enables authentication via SSO across multiple organizations Not checked yet
2 details in Everything
Enterprise Gateway 1.16.4 adds bearer token bearer token A credential that grants access to whoever presents it, without a separate proof of possession. Protecting the token matters because a stolen copy can be used by someone else. auth for AWS Bedrock and EKS EKS Amazon's managed Kubernetes service, run by AWS, that handles control-plane provisioning so teams can deploy containerized workloads without operating the underlying cluster infrastructure themselves. Pod Identity support.
Adds support for bearer tokensbearer tokens A credential that grants access to whoever presents it, without a separate proof of possession. Protecting the token matters because a stolen copy can be used by someone else. authentication in AWS Bedrock provider configuration Not checked yet Adds EKS Pod Identity integration with IRSA IRSA An AWS mechanism that lets a Kubernetes pod assume an IAM role via a service account token, so cyber tools running in EKS can call AWS APIs without storing long-lived credentials. for EKS clusters Not checked yet
2 details in Everything
Portkey Backend 1.3.1 introduces Add Prefix and Allowed Request Types guardrails.
Adds the Add Prefix guardrail to prepend configurable text to user input before model inference Not checked yet Adds the Allowed Request Types guardrail to restrict processing to specific endpoints via allowlist or blocklist Not checked yet
2 details in Everything
Adds configurable request prefixing and request type allowlisting/blocklisting in Enterprise Gateway v1.16.1
Adds the ability to set a configurable prefix on user input before it reaches the model Not checked yet Adds control over Allowed Request Types via allowlist or blocklist filtering Not checked yet
2 details in Everything
Enterprise Gateway 1.16 adds AWS Service Role auth, request timeout and NO_PROXY env vars, TLS for control plane, Bedrock global profile/name mapping.
Adds REQUEST_TIMEOUT environment variable to configure fetch timeouts for outbound LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. requests in milliseconds (default: 300000). Not checked yet Adds NO_PROXY environment variable support to bypass outbound requests to specified hosts. Not checked yet Adds TLS_KEY, TLS_CERT, and TLS_CA environment variables to configure TLS for control plane calls in air-gapped deployments. Not checked yet Adds AWS Service Role authentication support for AWS Bedrock models, allowing the Gateway to use its own service role. Not checked yet Adds global profile support for AWS Bedrock models. Not checked yet
+1 more
show less
Adds name field mapping for the /messages endpoint document object in AWS Bedrock. Not checked yet
6 details in Everything
Portkey Backend 1.3.0 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. APIs, SCIM SCIM A standard for creating, updating and removing user accounts and groups across applications. It helps an identity provider keep access in sync when people join, change roles or leave. org management, workspace key limits, and Budget resets
Adds mcp endpoints for MCP Preview management via new APIs Not checked yet Adds OAuth support to MCP Preview management Not checked yet Adds configs_security_settings in organization settings to control view/edit access by role Not checked yet Adds workspace-level user_api_key_limits to restrict max keys per workspace Not checked yet Adds configurable default_expiry and max_expiry for user API key expiry Not checked yet
+5 more
show less
Adds new SCIM provisioning setting to enforce organization-only user management via SCIM while allowing workspace management via Portkey Not checked yet Adds periodic budget_reset functionality in the update workspaces API Not checked yet Adds strict name filter parameter to list workspaces API Not checked yet Adds aws_service_auth as a new auth type for AWS Bedrock integrations Not checked yet Adds setting to disable the Getting Started page Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! API Key Management API updates list api-keys response to no longer return raw keys for other user API keys
Frontend 1.4.6 adds per-key rate limits, user API key security settings, and new model support for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface.
Added multiple rate limit support: now possible to set both cost-based and token-based rate limits on a single key Not checked yet Introduced a security setting to restrict the maximum number of User API keys that can be created per user Not checked yet Introduced a security setting to configure the default and maximum expiry of User API keys Not checked yet Updated the MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. consent screen to allow selection from eligible workspaces Not checked yet Added better states for consent approval, rejection, and failures in MCP Not checked yet
+6 more
show less
Hide embedding models embedding models Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. in prompt playground Not checked yet Allow updating base models for custom models Not checked yet Made alias a required field for Azure-OpenAI deployment configurations Not checked yet Added gpt-5-codex, gpt-5-pro, and several other OpenAI and Azure-OpenAI models Not checked yet Added new Together AI and Grok models Not checked yet Added AWS Bedrock Titan Embedding Embedding Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. and Titan v1 models Not checked yet
11 details in Everything
└──▷ BREAKING ON UPGRADE
! alias is now a required field for Azure-OpenAI deployment configurations
Data Service 1.3.0 adds KMS KMS A managed service that creates, stores, rotates and controls access to encryption keys, usually backed by HSMs. Applications ask it to encrypt or decrypt rather than holding keys themselves. key support for custom batch file output and batch operation tracking.
v1.3.0 supports KMS keys for encrypting custom batch file output Not checked yet Adds batch operation tracking for provider batch requests sent from Gateway Not checked yet
2 details in Everything
Portkey Enterprise Gateway 1.15.6 adds image editing pricing support, input_audio param for Vertex, and Bedrock batch pass-through
Supports pricing configuration for image editing models on openai, azure-openai, and azure-foundry providers Not checked yet Adds input_audio parameter support for the vertex provider Not checked yet Allows passing through parameters to the Bedrock batch create endpoint Not checked yet
3 details in Everything
Frontend adds Claude Sonnet 4.5 models for Anthropic, AWS Bedrock, and VertexAI base providers.
v1.15.5 enables HTTP protobuf transport for OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. via OTEL_EXPORTER_OTLP_PROTOCOL and fixes guardrail registration.
Portkey Enterprise Gateway 1.15.4 adds max_tool_calls, safety_identifier, and top_logprobs parameters for the /responses API.
Adds support for the max_tool_calls parameter on the /responses API endpoint Not checked yet Adds support for the safety_identifier parameter on the /responses API endpoint Not checked yet Adds support for the top_logprobs parameter on the /responses API endpoint Not checked yet
3 details in Everything
Frontend UI enhancements for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server management traceability and model catalog code generation.
Portkey Enterprise Gateway 1.15.3 adds APAC cross-region inference profiles for AWS Bedrock and streaming token calc for gpt-5
Adds support for APAC cross region inference profiles in the AWS Bedrock provider configuration Not checked yet
1 detail in Everything
Portkey Enterprise Gateway 1.15.2 adds KMS KMS A managed service that creates, stores, rotates and controls access to encryption keys, usually backed by HSMs. Applications ask it to encrypt or decrypt rather than holding keys themselves. for Bedrock uploads and custom Entra scopes.
Adds KMS support for file uploads to bedrock/AWS Not checked yet Supports custom scope for entra auth with deprecated azure serverless models Not checked yet Enables custom header support for OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. Export of analytics data Not checked yet
3 details in Everything
Portkey Enterprise Gateway 1.14.3 introduces a conditional new models endpoint with backward-compatible proxying logic.
Adds a models endpoint that activates only when the request lacks a provider, virtual_key, or config containing those fields Not checked yet
1 detail in Everything
Portkey Enterprise Gateway 1.14.0 adds Vertex AI timeRangeFilter support and OpenAI GPT-5 parameters.
timeRangeFilter support for Google Search tool in Vertex AI provider updates Not checked yet New parameters added for GPT-5 compatibility in OpenAI and Azure OpenAI providers Not checked yet Return reasoning messages if returned by the model in OpenRouter OpenRouter A unified API gateway that routes requests to dozens of LLM providers under one endpoint, letting cyber tools swap or compare models without rewriting provider-specific integration code. Not checked yet
3 details in Everything
Adds the /v1/models unified endpoint compliant with OpenAI API spec
Portkey Enterprise Gateway v1.13.1 adds granular request processing time analytics and optimizes OpenAI Chat Completions latency.
Adds new analytics data point for granular processing time for requests Not checked yet Improves OpenAI Chat Completions by eliminating extra processing time Not checked yet
2 details in Everything
Portkey Enterprise Gateway v1.13 adds a unified messages API following Anthropic's spec for Bedrock, Anthropic, and Vertex AI.
Adds unified messages API endpoint supporting Anthropic’s messages specification Not checked yet Extends the new API to work with AWS Bedrock, Anthropic, and Vertex AI models Not checked yet
2 details in Everything
Enterprise Gateway 1.12.x adds Model Catalog, workspace budget limits, per-strategy circuit breakers, and automatic user attribution.
Adds Model Catalog support with updated API specification for managing model providers Not checked yet Enforces Workspace Budget Limits to control spend and rate limits at the workspace level Not checked yet Introduces Circuit Breaker capability configured per-strategy within tool configurations Not checked yet
3 details in Everything
Data Service 1.2.6 adds Azure Redis cache with Entra/Managed Identity support and HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. proxy for inter-POD communication.
azure cache now supports Entra and Managed Identity auth modes Not checked yet All external calls and HTTPs communication between PODs now route through an HTTPS Proxy Not checked yet Custom logs can include virtual keys via request headers Not checked yet
3 details in Everything
Portkey Enterprise Gateway 1.11.9 adds S3 Object Lock support, new provider parameters and unified finish reason handling
Adds LOG_STORE_OBJECT_LOCK_RETENTION_ENABLED environment variable to enable S3 Object Lock and Retention-enabled buckets for the log store Not checked yet Unifies finish_reason values across Anthropic and Bedrock models, retaining provider-returned values when x-portkey-strict-openai-compliance is set to false Not checked yet Adds support for cost calculation for fine-tuned models on Vertex AI Not checked yet Adds support for the Computer Use tool for Anthropic models on AWS Bedrock Not checked yet Handles backward compatibility for Titan G1 embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. model encoding_format parameter on AWS Bedrock Not checked yet
+2 more
show less
Forwards max_completion_tokens parameter as-is instead of mapping it to max_tokens on Azure AI Not checked yet Adds support for the web_search_options parameter for chat completions endpoint on OpenAI and Azure OpenAI Not checked yet
7 details in Everything
Adds Azure Managed Identity support for Azure Containers in Enterprise Gateway v1.11.7
Improves error logging for Azure Managed Identity errors Not checked yet
1 detail in Everything
Groq service_tier support, Anthropic tool-result prompt caching, and webhook guardrail verdict fixes
Adds service_tier configuration option for the Groq provider to control service tier selection Not checked yet Enables Anthropic prompt caching for tool results and tool use tool use A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. calls in provider configurations Not checked yet
2 details in Everything
Portkey Data Service 1.2.3 adds configurable FINETUNE_STATUS_CHECK_INTERVAL and BATCH_STATUS_CHECK_INTERVAL environment variables for fine-tuning and batch processing
Adds FINETUNE_STATUS_CHECK_INTERVAL configuration to control provider fine-tuning status check frequency Not checked yet Adds BATCH_STATUS_CHECK_INTERVAL configuration to control provider batch processing status check frequency Not checked yet
2 details in Everything
Portkey Enterprise Gateway v1.11.4 adds Bedrock AssumedRole, Anthropic computer use tool, Azure Redis auth, HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. proxy, and more.
Adds AssumedRole support for Bedrock application inference profiles Not checked yet Adds multimodal multimodal Able to work with more than one type of input or output, such as text, images and audio. A multimodal model can combine information across those formats. embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. support for Cohere and Titan providers Not checked yet Adds support for Bedrock createTranscription, createTranslation, imageGeneration, batch, and files endpoints via Azure Foundry Not checked yet Adds Anthropic computer use tool support Not checked yet Adds file_url and mime_type fields for file content parts in Anthropic requests Not checked yet
+7 more
show less
Adds Gemini/Vertex Thinking mode support in VertexAI Not checked yet Adds Azure Redis authentication modes: EntraID and ManagedIdentity Not checked yet Adds separate REDIS_USERNAME and REDIS_PASSWORD environment variables for Redis Cache auth Not checked yet Adds azure-redis value for the CACHE_STORE environment variable to enable Azure Redis Cache Not checked yet Adds AZURE_REDIS_AUTH_MODE, AZURE_REDIS_MANAGED_CLIENT_ID, AZURE_REDIS_ENTRA_CLIENT_ID, AZURE_REDIS_ENTRA_CLIENT_SECRET, and AZURE_REDIS_ENTRA_TENANT_ID environment variables for Azure Redis Cache configuration Not checked yet Adds HTTPS proxy support via the HTTPS_PROXY environment variable for all external calls Not checked yet Adds virtual key inclusion in custom logs when passed via headers Not checked yet
12 details in Everything
Adds OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. traces collector endpoint, Data Plane log exports, and new provider parameters
Adds the /v1/otel/v1/traces endpoint to collect OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. spans as Portkey traces. Not checked yet Enables log exports on the Data Plane, allowing logs to be exported without sending them to the Control Plane (requires Dataservice). Not checked yet Adds support for background and service_tier parameters for OpenAI providers. Not checked yet Adds support for custom hosts and private links for Azure Plugins. Not checked yet
4 details in Everything
Portkey Data Service 1.2.2 adds Prometheus counters for batch processing metrics.
Adds Prometheus metric support for batch processing visibility with eight new counters (batch_count, batch_cost, batch_input_tokens, batch_total_tokens, batch_process_time, batch_success_row_count, batch_failure_row_count, batch_row_count) and provider/type labels. Not checked yet
1 detail in Everything
Adds mTLS mTLS Mutual TLS, an encrypted connection where both client and server present certificates to prove their identity. It helps services verify who they are communicating with. support for Gateway-to-internal-service communication in Enterprise Gateway 1.11.0.
Adds mTLS support for Gateway to internal services in air-gapped deployments Not checked yet
1 detail in Everything
Portkey Enterprise Gateway 1.10.23 adds dimensions param for Vertex multi-modal multi-modal Able to work with more than one type of input or output, such as text, images and audio. A multimodal model can combine information across those formats. embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. and JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. plugin auth
Adds dimensions parameter support in multi-modal embeddings for Vertex provider Not checked yet Adds JWT authentication capability to the Plugins module for runtime validation Not checked yet
2 details in Everything
Portkey Enterprise Gateway 1.10.22 adds Anthropic PDF file support, new env vars for OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. config, and three new AI providers.
Adds file_url and mime_type parameters to request payloads for OpenAI-spec-compatible file content parts in Anthropic-based models Not checked yet Adds OTEL_SERVICE_NAME and OTEL_RESOURCE_ATTRIBUTES environment variables for OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. resource configuration Not checked yet Adds Ncompass, Lepton, and Snowflake Cortex as supported providers for chat completions and other endpoints Not checked yet
3 details in Everything
Portkey Gateway 1.10.20 adds strict metadata enforcement and disables API key config overrides
Adds strict metadata logging hierarchy (Workspace Default > API Key Default > Incoming Request) with admin values preventing override by request-level fields Not checked yet Adds ability to disable default config override for API keys, returning 400 error on conflict Not checked yet
2 details in Everything
└──▷ BREAKING ON UPGRADE
! Request-level metadata fields can no longer override admin-configured values due to strict enforcement hierarchy
Portkey Data Service v1.1.10 adds S3 encryption header support and environment variable secret injection.
Added support for passing encryption headers while uploading stream data to S3 Not checked yet Added support for both file path and direct value from environment variables for secrets like redis connection Not checked yet
2 details in Everything
Enterprise Gateway adds OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. metrics push, Milvus semantic caching, Azure Guardrails, prompts render API, and Vertex AI dimensions support.
Adds OTEL_PUSH_ENABLED and OTEL_ENDPOINT environment variables to push ClickHouse analytics (traces/spans) to an OTel collector Not checked yet Adds Milvus vector store vector store A database built to store embeddings and find the nearest ones to a query quickly. It is the retrieval half of most RAG systems. support for semantic caching via the VECTOR_STORE, VECTOR_STORE_ADDRESS, VECTOR_STORE_API_KEY, and VECTOR_STORE_COLLECTION_NAME environment variables Not checked yet Adds a /v1/prompts/:id/render endpoint to access prompts rendering capabilities within the Gateway Not checked yet Adds PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. detection support using Azure Language Service for Azure Guardrails Not checked yet Adds support for dimensions parameter in Vertex AI embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. Not checked yet
5 details in Everything
Portkey Enterprise Gateway 1.10.17 adds Response API support, use_retry_after_header retry logic, and org-level cache TTL TTL Time to live, a limit on how long data remains valid or how far a packet can travel. Caches use a time limit; IP packets use a hop limit. .
Adds end-to-end support for the OpenAI and Azure OpenAI Response API. Not checked yet Implements caching for stream requests. Not checked yet Introduces cost calculation for tools like web_search, file_search and code_execution. Not checked yet Updates Azure Inference integration to directly accept endpoints from the Azure Foundry dashboard. Not checked yet Adds new retry setting use_retry_after_header that uses provider x-retry-after or x-retry-after-ms headers for 429 wait times. Not checked yet
+5 more
show less
Allows configuring the default max cache TTL at the organisation level. Not checked yet Adds support for logprobs and top_logprobs request parameters in Azure OpenAI. Not checked yet Adds support for response_format and search_recency_filter request parameters in Perplexity. Not checked yet Handles empty assistant tools messages containing only newline characters (\n\n) in AWS Bedrock. Not checked yet Populates the model field in /chat/completions API responses when providers do not natively return it. Not checked yet
10 details in Everything
Enterprise Gateway v1.10.16 enhances the unified batch API's resilience and error visibility by adding error_file_id for OpenAI/Azure upload failures and improving Bedrock error handling.
Returns error_file_id in the batch output payload when file uploads fail for OpenAI and Azure OpenAI providers Not checked yet Handles file upload failures for AWS Bedrock during unified batch processing Not checked yet
2 details in Everything
Enterprise Gateway 1.10.15 adds large file upload support and custom mime-type configuration for providers.
Adds the ability to pass custom mime_type values in the request body for file uploads to Providers and Data Service Not checked yet Enables uploading large files to Providers and Data Service Not checked yet
2 details in Everything
Portkey v1.10.14 adds org/workspace guardrails, Fireworks support, logging updates, and new env var.
Enforces guardrails at the organisation and workspace levels on all requests Not checked yet Extends unified finetuning APIs to support the Fireworks provider Not checked yet Adds cost calculation for Perplexity search and Gemini grounding Not checked yet Preserves custom_id in VertexAI batch output Not checked yet Logs non-OpenAI compliant fields (e.g. groundingMetadata, citations) in stream responses Not checked yet
+2 more
show less
Adds support for logprobs and top_logprobs parameters in Fireworks provider requests Not checked yet Introduces the AWS_ENDPOINT_DOMAIN environment variable to override the default AWS endpoint domain Not checked yet
7 details in Everything
Portkey Data Service v1.1.5 adds custom batch output paths and raises limits to 500k lines / 5MB chunks.
Increased maximum lines for custom batches to 500k Not checked yet Raised chunk size limit to 5MB Not checked yet
2 details in Everything
Portkey Data Service v1.1.4 adds Vertex batch embeddings embeddings Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. , model logging, custom batch outputs, and TLS via env vars
Added TLS_KEY_PATH and TLS_CERT_PATH environment variables to enable internal pod-to-pod HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. communication by mounting a volume with certificate and key files. Not checked yet Added support for Vertex batch embeddings as a new embedding embedding Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. provider capability. Not checked yet Includes model information in log objects, enabling visibility into which model was used for each embedding request. Not checked yet Implemented custom batch processing output generations, allowing users to define specific output formats for batch jobs. Not checked yet
4 details in Everything
Portkey Enterprise Gateway 1.10.12 adds Anthropic Extended Reasoning support, internal POD HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. via env vars, and new Prometheus metrics
Adds unified API signature for single-turn and multi-turn conversations with Anthropic Extended Reasoning across Anthropic, AWS Bedrock, and VertexAI. Not checked yet New Prometheus metric llm_last_byte_diff_duration_milliseconds tracks LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. last byte latency for chunked JSON responses. Not checked yet All Prometheus metrics now include a stream label with possible values of 0 or 1. Not checked yet
3 details in Everything
Portkey Enterprise Gateway 1.10.11 adds S3 encryption key support, webM mimeType, Azure drop param, and streaming usage mapping
Added support for specifying an encryption key when uploading files to S3 for AWS Bedrock providers Not checked yet Added webm mimeType support in VertexAI batches and fine-tune APIs Not checked yet Changed Azure Inference provider to use extra-parameters: drop instead of ignore for extra parameter handling Not checked yet Mapped usage object for streaming responses in Openrouter Not checked yet
4 details in Everything
Portkey Enterprise Gateway 1.10.10 adds VertexAI finetuning APIs and body params in conditional router
Unified Finetuning APIs now support VertexAI for file uploads and transformations. Not checked yet Adds params body field support to conditional router queries, enabling routing based on request body fields. Not checked yet
2 details in Everything
Portkey Data Service adds Vertex provider options for batches.
Added support for Vertex provider options for batches. Not checked yet Implemented cluster mode Redis for queues. Not checked yet
2 details in Everything
Data Service 1.1.1 adds S3 encryption headers, SSE SSE Server-Sent Events, a browser API and HTTP-based protocol where a server pushes a stream of text events to a client over a single long-lived connection, giving tools a lightweight alternative to WebSockets for one-way real-time updates. upload support, and log export filtering with limits.
Adds S3 encryption header support for finetunes and batches Not checked yet Implements SSE file upload support Not checked yet Made S3 bucket optional for Bedrock batches Not checked yet Adds filtering for log exports Not checked yet Implemented end limit for log export records Not checked yet
5 details in Everything
Portkey Enterprise Gateway 1.10.8 adds mutator webhooks and configurable guardrail timeouts
Adds mutation capability to the existing webhook plugin via Mutator Webhooks for BYO-PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. redaction guardrails Not checked yet Introduces timeout parameter for all guardrails that make internal fetch calls, with a default of 5 seconds Not checked yet Enables storing timeout values in the control plane when creating/updating a Guardrail on UI Not checked yet
3 details in Everything
Data Service 1.1.0 adds Bull Board integration for job queue visualization
Adds Bull Board integration to visualize job queues and their status. Not checked yet Adds Prometheus metrics for batch jobs and fine-tuning operations. Not checked yet
2 details in Everything
Portkey Enterprise Gateway 1.10.6 adds AzureOpenAI batching via unified APIs and Deepseek model support.
Extends the Unified Batches APIs to support AzureOpenAI batching. Not checked yet Adds support for Deepseek models across Fireworks, Groq and Together providers. Not checked yet
2 details in Everything
Portkey Enterprise Gateway 1.10.5 adds JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. auth and VertexAI batch support
Adds JWT Auth support with configurable JWKS endpoint or JWKS JSON for authentication and authorization Not checked yet
1 detail in Everything
Portkey Enterprise Gateway 1.10.4 adds PII PII Personally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. Redaction Guardrails, Replicate proxy support, and request-level metadata logging.
Adds PII Redaction Guardrails through Portkey Managed, AWS Bedrock, Pangea, Patronus, and Promptfoo providers with a transformed flag in the guardrail result object Not checked yet Adds Replicate provider support for proxy (passthrough) requests Not checked yet Logs workspace metadata at the individual request level Not checked yet
3 details in Everything
Azure OpenAI finetuning, AWS Bedrock guardrails, Milvus passthrough, Prometheus metric updates
Extended unified finetuning APIs to support the AzureOpenAI provider Not checked yet Added AWS Bedrock Guardrails support for request/response checks Not checked yet Allowed configuring custom host and custom headers directly in virtual keys for custom models/providers Not checked yet Renamed Prometheus label llm_request_duration_seconds to llm_request_duration_milliseconds and added new metric portkey_request_duration_milliseconds Not checked yet Supported Milvus DB as a passthrough provider Not checked yet
+2 more
show less
Added logprobs and top_logprobs support for VertexAI and Google providers compatible with OpenAI format Not checked yet Added support for experimental Gemini Thinking Models in VertexAI/Google provider Not checked yet
7 details in Everything
└──▷ BREAKING ON UPGRADE
! The Prometheus label llm_request_duration_seconds is renamed to llm_request_duration_milliseconds, which may break dashboards or alerts relying on the old label name.
Portkey Enterprise Gateway 1.10.1 adds unified finetune APIs and code detection guardrail updates.
Adds unified finetune APIs for OpenAI, AzureOpenAI, Bedrock, and Fireworks Not checked yet Adds checks for verbose identifiers to detect Python and JavaScript markdown code blocks in Code Detection Guardrails Not checked yet
2 details in Everything
Portkey Enterprise Gateway 1.10.0 adds unified batch APIs, new partner guardrails, VertexAI self-deployed model support, and configurable guardrail fields.
Adds input_guardrails and output_guardrails config fields accepting arrays of slugs for shorthand guardrail application Not checked yet Adds explanation property to guardrail responses clarifying pass/fail reasons for default checks Not checked yet Adds unified batching APIs for OpenAI, AWS Bedrock, and Cohere providers Not checked yet Adds support for self-deployed VertexAI models (Endpoints) including Vertex-Huggingface configurations Not checked yet Adds new partner guardrails for Mistral mistral.moderateContent and Pangea pange.textGuard Not checked yet
+2 more
show less
Enables mapping of OpenAI developer role to system role on non-OpenAI/AzureOpenAI providers Not checked yet Reduces Docker image size from ~275MB to ~75MB through build process updates Not checked yet
7 details in Everything
└──▷ BREAKING ON UPGRADE
! Removed unsupported stream parameter from Bedrock-Cohere integration
Portkey Enterprise Gateway 1.9.5 adds Gemini Grounding Mode support in OpenAI compatible format
Portkey Gateway v1.9.4 adds comprehensive request/response logging and standardizes Prometheus labels.
Adds Prometheus metric labels for method, route, code, custom_labels, provider, model, and source Not checked yet Adds support for the tools capability in Ollama and Groq providers Not checked yet
2 details in Everything
Portkey Enterprise Gateway 1.9.3 adds S3_CUSTOM log stores and AWS Sagemaker passthrough support.
Adds LOG_STORE_BASEPATH config key to support the new S3_CUSTOM LOG_STORE type for arbitrary S3-compatible S3-compatible An object-storage API that mirrors Amazon S3's HTTP interface, so any client or cyber tool written for AWS S3 works unchanged against any compliant storage backend. storage providers Not checked yet Adds support for passing requests through to AWS SageMaker models as a new provider Not checked yet
2 details in Everything
Enterprise Gateway 1.9.2 adds prompt label cache invalidation, S3 log sub-paths, and Proxy virtual key support.
Add prompt_labels support for cache key invalidation on control plane updates Not checked yet Allow sub-paths in S3 bucket names for logs Not checked yet
2 details in Everything
Enterprise Gateway 1.9.1 adds new parameters for Realtime APIs and fixes Bedrock response formatting.
Adds prediction, store, metadata, audio and modalities parameters support for OpenAI and AzureOpenAI Realtime APIs Not checked yet Retains the original close reason from the provider in the socket close event for Realtime APIs Not checked yet
2 details in Everything
Enterprise Gateway v1.9.0 adds dynamic budgets, auto-expiry for keys, and Realtime API support for OpenAI/Azure.
Adds Realtime APIs integration capability for OpenAI and AzureOpenAI providers Not checked yet
1 detail in Everything
Adds control_plane log/analytics store option to reduce ClickHouse dependency
Adds LOG_STORE and ANALYTICS_STORE environment variable options with value control_plane to route logs and analytics without a ClickHouse connection. Not checked yet Introduces the new internal log store backend named control_plane. Not checked yet
2 details in Everything
Enterprise Gateway 1.8.0 adds Bedrock Converse API, Vertex Imagen, Stable Diffusion v2, Pydantic SDK structured outputs structured outputs Forcing a model's response to match a given format or JSON schema, so software can parse it reliably instead of hoping the text is well formed. , Lambda provider, and prompt cache pricing.
Bedrock chat completions now use the Converse API instead of /chat/completions, enabling tool calls and vision for supported models while removing manual chat templating logic. Not checked yet Adds Vertex Imagen image generation support via the Gateway. Not checked yet Adds support for Stable Image Ultra , Core , 3.0, and 3.5 models through stability-ai and bedrock providers, handling internal API signature transformations between v1 and v2. Not checked yet Adds Pydantic SDK integration for structured outputs in GoogleAI and VertexAI providers by dereferencing JSON schemas to ensure Google compatibility. Not checked yet Adds support for prompt caching pricing calculations for OpenAI and AzureOpenAI models that require it. Not checked yet
+1 more
show less
Adds lambda provider with support for chat completions and completions endpoints. Not checked yet
6 details in Everything
Portkey Data Service 1.0.3 adds vision fine-tuning validation and S3 storage for fine-tunes
Adds support for vision fine-tuning validation for OpenAI. Not checked yet Implements S3 bucket support to store fine-tunes. Not checked yet
2 details in Everything