You can now extend OpenAI’s AgentKit to work across different LLM providers — all through Portkey

• End-to-end observability

• Guardrails for every interaction

• Cost tracking across executions

• Reliability features like fallbacks and retries

• Bring production-grade visibility and control to your agents.

Read more about this here -> https://portkey.ai/docs/integrations/libraries/openai-agent-builder

Llama 3.1 and 3.2 models on Vertex AI Managed API will be deactivated on January 15, 2026.

What to do:

• Migrate to Llama 3.3 or Llama 4 (recommended)
• Update model names in your integration
• Test before the cutoff date

Anthropic’s latest Claude Sonnet 4.5 is now available through the Portkey AI Gateway.

With Portkey, you can bring Claude Sonnet 4.5 into production with:

✅ Unified access via the AI Gateway

✅ Full observability: logs, latency, and spend

✅ Budget and rate-limit controls across teams and apps

Your data policies aren’t always one-size-fits-all.

Alongside our PII guardrail, we’ve introduced a Regex Replace Guardrail for specific redactions.

Define custom regex patterns and automatically mask sensitive data before it reaches the model so that you can:

• Mask sensitive data (e.g., emails, phone numbers)
• Normalize inputs before they reach the model
• Enforce consistent formatting across requests

Read more here -> https://lnkd.in/dgkPGrQF

We’ve introduced a new guardrail that lets you restrict model access based on metadata key–value pairs at runtime.

This means you can:

• Enforce tenant, region, or environment-based restrictions dynamically

• Ensure compliance policies are checked per request

• Control model usage without changing your app logic

Granular governance, enforced in real time.

We’re teaming up with Exa to host the next edition of LLMs in Prod. Expect talks, panels, and conversations with PG&E, Postman, Palo Alto Networks, LinkedIn, Cerebras, and more, focused on running LLMs in production at scale.

📍 Exa HQ, San Francisco

📅 Today, 5–8 PM

Are we seeing you today? (few spots left!)

We’ve introduced a single endpoint for counting tokens across AWS Bedrock, Vertex AI, and Anthropic.

This makes it easier to:

• Get an estimate of tokens before sending the request

• Manage rate limits and costs

• Enforce routing and quota rules inside your app

• Optimize prompts to be a specific length

Read more here ->

By default, finish_reason parameter is now mapped to an OpenAI-compatible value for consistency. If you want to keep the original provider-returned value, set x-portkey-strict-openai-compliance = false.

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 →

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