Stay informed about Portkey's newest releases, features, and improvements
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
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
In addition to 𝘤𝘩𝘢𝘵.𝘤𝘰𝘮𝘱𝘭𝘦𝘵𝘪𝘰𝘯𝘴, we now support the 𝘮𝘦𝘴𝘴𝘢𝘨𝘦𝘴 route, available for Anthropic, AWS Bedrock, and Vertex AI.
What this means for you:
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
You can now define and enforce multiple guardrail policies at the workspace-level, making it easier to secure usage, filter content, and maintain compliance across your team.
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.
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
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
Featherless gives you access to 11,900+ open-source models with unlimited tokens, instantly deployable for fine-tuning, testing, and production at scale.
With Portkey, bring Featherless into production with:
✅ Unified access to all Featherless models
✅ Secure API key management with no extra config
✅ Full observability: logs, latency, spend
✅ Built-in caching, retries, and failover for reliability
See how you can integrate here
AWS Bedrock Knowledge Bases enables you to give foundation models access to your company’s private data sources
With Portkey, you can:
Working with API keys across teams?
Portkey now automatically adds _user metadata to every request made with a user key. No more manual tagging or messy workarounds.
This makes it easier to debug issues and track usage, all tied back to the right user.
