@anthropic-ai/claude-agent-sdk and for Python as claude-agent-sdk) lets you build AI agents with tool calling, hooks, and MCP server support. This page shows how to point the SDK at Requesty so your agents can use 300+ models from multiple providers. For the SDK’s own API reference (hooks, tool definitions, MCP configuration, TypeScript interfaces), see Anthropic’s official Agent SDK documentation.
Using the Requesty integration, you can:
- Use 300+ models while building agents, giving you flexibility to choose the best model for each task
- Track and manage your spend in a single location
- Keep a record of your agent interactions
Configuration
Set ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN
The Claude Agent SDK reads theANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN environment variables, so the easiest way to integrate Requesty is:
- Get Your API Key Create an API key on the API Keys Page.
-
Set Environment Variables
With this setup, the Agent SDKs will route all requests through Requesty, giving you access to models from OpenAI, Anthropic, Google,
Mistral, and many more providers.
Model Selection
You can choose any model from the Model Library or any policy configured for your organization. Standard model IDs follow the formatprovider/model-name:
anthropic/claude-fable-5openai/gpt-5google/gemini-2.5-flashmistral/mistral-large-latest
policy/policy-name:
policy/reliable-sonnet-4-5
TypeScript
The TypeScript Agent SDK (@anthropic-ai/claude-agent-sdk) automatically respects the ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN environment variables.
Python
The Python Agent SDK (claude-agent-sdk) automatically respects the ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN environment variables.
Looking for the Agent SDK API reference?
This page covers routing the SDK through Requesty. For the SDK itself, Anthropic maintains the official documentation:- Agent SDK overview, concepts, installation, and quickstart
- TypeScript SDK reference,
query(), options, hooks, and tool interfaces - Python SDK reference,
ClaudeSDKClient,ClaudeAgentOptions, and@tool - MCP in the Agent SDK, connecting MCP servers to your agents
Benefits of Using Requesty with Agent SDKs
Access 300+ Models
Switch between models from different providers without changing your setup
Cost Management
Monitor spending and set limits across all your AI interactions
Fallback Policies
Automatic fallbacks ensure your agents never get interrupted
Unified Interface
Use the same SDK interface with models from multiple providers
Troubleshooting
Model Not Found
If you get a “model not found” error, make sure:- Your API key is valid and has access to the model (check the approved models in your organization)
- The model ID format is correct (
provider/model-name) - The model is available in the Model Library
Connection Issues
If the Agent SDK can’t connect:- Verify your
ANTHROPIC_BASE_URLis set tohttps://router.requesty.ai - Check your
ANTHROPIC_AUTH_TOKENis correct - Ensure you have internet connectivity
- For TypeScript, make sure environment variables are set before importing the SDK