Roo Code is built for fast development, Portkey makes it enterprise-ready.

With Portkey, you can:

✅ Trace every request by user, tool, or team

✅ Manage LLM spend with rate limits and budgets

✅ Enforce RBAC for users, teams, and environments

✅ Add retries, fallbacks, and safety guardrails

✅ Get full logging and metrics across all models

 Explore Roo Code integration 

With Portkey, you can turn your Cline setup into an enterprise-grade system with:

• Real-time usage and spend tracking
• Budget limits per team or project
• RBAC for fine-grained access and model management
• Full observability—trace every call across 1600+ LLMs
• Fallbacks, retries, and guardrails with zero code changes

Keep building without interruptions. Check out the documentation here.

Bring visibility, governance, and control to Anthropic’s agentic coding assistant with Portkey.

With this integration, you can:

✅ Avoid system overload by enforcing rate limits

✅ Monitor usage by tagging and filtering with metadata (e.g., user ID, workspace)

✅ Debug and trace issues faster with detailed logs for every interaction

✅ Share controlled, secure access by issuing virtual API keys per user

✅ Use Claude code in your existing AWS Bedrock or Vertex AI setup, with granular governance and access control

Read more about it here 

Portkey now supports embedding APIs from Vertex AI, giving you a standardized interface for embeddings across modalities, including text, image, and video.

 Explore 

Claude 4 offers significantly improved long-term reasoning, enhanced coding capabilities, and can autonomously handle complex, multi-step tasks for extended durations.

With Portkey, you also get:

✅ Org-wide guardrails, retries, and rate limits

✅ Prompt playground to try and test the new models

✅ Full logging and metadata on every call

✅ Usage, latency, and cost tracking

Looking to build with Claude 4? Get started today!

Thinking Mode lets you visualize and test more deliberate, multi-step reasoning from your model, perfect for more complex prompts and structured outputs.

Try it out!

You can now add a Model Whitelist guardrail in Portkey, ensuring that only approved models are used for inference.

✔️ Specify allowed models for a route, environment, or org

✔️ Use the toggle to invert the list and treat it as a blacklist, blocking specific models instead

In addition to authentication via JWT (alongside API keys), Portkey now supports JWT validation as an input guardrail, letting you verify JWTs for any LLM call.

You can now:

✅ Authenticate your requests using JWTs

✅ Validate your JWT tokens with each request

You can now assign multiple labels to a single prompt version in Portkey. This makes it

easier to promote a prompt version from staging to production.

Now live for all users.

We’ve reorganized the Guardrails section in our documentation for better clarity. You’ll now find Guardrail checks listed under Integrations.