Announcements

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

  1. New Cookbook - Optimizing Prompts using LLama Prompt Ops

    Need to try out or switch to the latest Llama models? There's an easier way to do it.

    Llama Prompt Ops transforms prompts that work well with other LLMs into ones that are optimized specifically for Llama models. This helps you get better performance and more reliable results without having to rewrite everything yourself.

    If you work in customer support, we've put together a helpful guide that will show you how to build a system that analyzes support messages for urgency and sentiment, and helps categorize them properly.

     

    Check it out here 

     

    image
  2. Making governance better for you!

    Here are two updates on the platform that will strengthen granular observability and governance for your organization:

    • Metadata with each API request: Portkey allows organisation owners to define mandatory metadata fields for API keys and workspaces.

    When the same key appears at multiple levels, the precedence order is:

     Workspace metadata > API key metadata > Request metadata  

    • Default configs with API Keys: With default configs, each API call made with the key will have the configs, without adding the Config ID to the code, with an option to override the config.

     

    Note: Existing API keys and Workspaces will not be affected by the new metadata schema and configs

     

    For more information and implementation steps, read our detailed docs.

     Enforcing metadata 

     Enforce default config 

     

  3. Centralized control over cache expiration

    Org admins can now define a default cache TTL for all API keys and workspaces within the organization.

    This means:

    ✅ Consistent cache retention policies

    ✅ Flexibility to override TTL at the request level when needed

     

    To implement this, check out the docs here 

  4. Build a Customer Support AI Agent!

     Nerding I/O recently dropped a tutorial on How to build a Customer Support AI Agent using Langraph for agent orchestration and Portkey's Prompt Render API for flexible, dynamic prompt management.

     

    Here's the full video tutorial!

     

     

  5. 🚨Model Deprecation Alert

    OpenAI is deprecating these models.

    image

     

    Quick action items:

    ✅ Audit your OpenAI API calls

    ✅ Plan migration to the recommended replacements

    ✅ Finish all tests before the shutdown dates (July and October)

     

     

  6. Bedrock prompt caching is now live on Portkey

    You can now implement Amazon Bedrock’s prompt caching seamlessly using Portkey’s OpenAI-compliant unified API and prompt templates.

     

    ✅ Cache specific portions of your prompts for repeated use

    ✅ Cut down on response latency and input token costs

    ✅ Improve performance for high-volume, repeated requests

     

    To see the implementation and supported models, check out the docs 

     

  7. ⚡ Day 0 support for Qwen 3!

    You can now start using Alibaba’s new Qwen 3 models through Portkey’s AI Gateway.

    These models offer hybrid reasoning modes for faster and more efficient responses, and show strong performance on STEM, code generation, and have strengthened their support for MCP.

     

    With Portkey, you also get:

    ✅ Org-wide guardrails, retries, and rate limits

    ✅ Full logging and metadata on every call

    ✅ Usage, latency, and cost tracking

     

    Looking to build with Qwen 3? Get started today!!

     

    OpenAI Codex CLI (2)
  8. Portkey now integrates with OpenAI Codex CLI!

    OpenAI Codex CLI gives developers a streamlined way to analyze, modify, and execute code directly from their terminal.

    Portkey's integration enhances this experience with:

     

    ✅ Access to 250+ additional models beyond OpenAI Codex CLI's standard offerings

    ✅ Content filtering and PII detection with guardrails

    ✅ Real-time analytics and logging

    ✅ Enterprise-grade governance with cost attribution, budget controls, RBAC, and more!

     

    Read more about the integration here 

     

     

     

     

  9. Unlock advanced capabilities!

    ✅ Gemini 2.5 thinking parameters on Vertex AI

    Configure Gemini 2.5’s advanced thinking settings through Portkey to better guide how the model reasons, plans, and generates outputs, without changing your existing integration.

     

    ✅ Anthropic beta features, now accessible via Bedrock

    You can now pass the anthropic_beta parameter in Bedrock’s Anthropic chat completions API through Portkey to enable Computer use, a beta feature that allows Claude to run instructions in a computer desktop environment.

     

  10. OpenAI Image Gen API on Portkey

    Announcement

    We're excited to announce that OpenAI's powerful new image generation API (with the gpt-image-1 model) is now supported on Portkey! 🎨

    What This Means For You

    You can now access OpenAI's latest image generation capabilities directly through your existing Portkey integration, with all the benefits of:

    • Higher fidelity, more accurate images
    • Diverse visual styles to match your creative needs
    • Precise image editing functionality
    • Rich world knowledge for generating contextually relevant visuals
    • Consistent text rendering for images with text elements
    image-gen-gpt-image

     Link to docs