Announcements

Stay informed about Portkey's newest releases, features, and improvements

  1. Conditional Router now supports request parameters ⚡

    Metadata-based routing works well when you have policy-driven or static strategies, for example, routing by tenant, region, or business tier. But what if you want to optimize routing per request?

     

    Portkey now allows you to set up conditional routing on request parameters too.

     

    This gives you more flexibility and better performance, letting you route dynamically based on each request’s conditions (like input length, urgency, or task type).

     

    👉 See how you can set it up here → 

     

  2. Quick updates to improve your experience!

    We’ve rolled out a set of improvements across multiple providers 👇

    • DashScope: Updated supported parameters
    • Vertex AI: Added timeRangeFilter support for Google Search tool
    • OpenAI & Azure OpenAI: New parameters added for GPT-5 compatibility
    • OpenRouter: Now returns reasoning messages when provided by the model
    • Fireworks:
    1. Better handling of non-ASCII characters in file uploads
    2. Removed unnecessary response transforms → faster processing

     

     

     

  3. Palo Alto Networks <> Portkey: you're invited!

    Protecting your AI platform with Palo Alto Networks + Portkey

     

    AI adoption is accelerating across enterprises, but security challenges—from prompt injections to data leakage remain a major hurdle.

    Join Palo Alto Networks and Portkey for a webinar where we’ll cover:

    • The most pressing security and compliance risks in enterprise AI
    • How to achieve end-to-end protection against AI-specific threats
    • Why visibility and monitoring at the gateway level is essential

     

    When: 23rd September, 10AM PT/1PM ET

     🔗 Register here 

    webinar-light (1)
  4. ⚡ Gemini 2.5 Flash Image is live on Portkey!

    Gemini 2.5 Flash Image (Nano-banana) is Google’s next-gen model for image generation and editing. It brings fast, high-quality results with multi-image fusion, natual-language editing and more!

     

    With Portkey, you can bring Gemini 2.5 Flash Image into production with:

    ✅ Unified access via the AI Gateway

    ✅ Full observability: logs, latency, and spend

    ✅ Budget and rate-limit controls across teams and apps

     

    2.5flash

     

  5. ⚡ Portkey now supports OTEL-based auto-instrumentation

    You can now send telemetry data from any OTel-compatible source directly into Portkey’s observability platform.

     

    This gives you:

    ✅ One platform to view LLM calls and app-level events together

    ✅ Correlation between model interactions and system behavior

    ✅ End-to-end insight into performance, cost, and compliance

     

    👉 Set up your OTel endpoint in Portkey

    traces
  6. messages route is live on the Gateway!

    In addition to 𝘤𝘩𝘢𝘵.𝘤𝘰𝘮𝘱𝘭𝘦𝘵𝘪𝘰𝘯𝘴, we now support the 𝘮𝘦𝘴𝘴𝘢𝘨𝘦𝘴 route, available for Anthropic, AWS Bedrock, and Vertex AI.

    What this means for you:

    • Remote MCP for Anthropic now works out of the box on Portkey
    • Complete support for Claude Code
    • Switch to Portkey in the Anthropic SDK by just changing the base URL
    • Use 𝘊𝘩𝘢𝘵𝘈𝘯𝘵𝘩𝘳𝘰𝘱𝘪𝘤 in LangChain without extra setup

    Whether you’re using 𝘤𝘩𝘢𝘵.𝘤𝘰𝘮𝘱𝘭𝘦𝘵𝘪𝘰𝘯𝘴 or 𝘮𝘦𝘴𝘴𝘢𝘨𝘦𝘴, Portkey gives you the same foundation: routing, guardrails, usage tracking, retries, and caching.

     

    Read more about this in our documentation 

     

  7. CRUD Guardrails API is live!

     

    Managing guardrails at scale just got easier. You can now create, update, retrieve, delete, and list guardrails directly via API.

     

    This makes it simple to keep policies consistent across environments, automate changes, and integrate guardrail management into your CI/CD workflows.

     

     Learn more-> 

    crud-guardrails
  8. Day 0 support for Claude Opus 4.1!

    Claude Opus 4.1 is Anthropic’s most capable model yet. It delivers stronger reasoning, better code generation, and agentic task handling, with a native 64K context window.

     

    With Portkey, bring Opus 4.1 into production with:

    ✅ Unified access via Bedrock, Vertex AI & Anthropic providers

    ✅ Guardrails for safe, compliant usage

    ✅ Full observability: logs, latency, spend

    ✅ Budget and rate-limit controls across teams and apps

    claude opus 4.1
  9. ⚡ You can now run GPT‑OSS models on Portkey!

    OpenAI’s new open-weight models, gpt-oss-120b and gpt-oss-20b, deliver strong reasoning, tool use, and long-context capabilities.

     

    With Portkey, get GPT‑OSS into production with:

     

    ✅ Smart routing via OpenAI, Together AI, Nscale, Groq & other providers

    ✅ Use directly in the Prompt Playground

    ✅ Prompt tooling, observability & caching built in

    ✅ Guardrails, retries, and failover out of the box

    gpt-oss (2)