Anthropic Integration

Run Claude 3.5 Sonnet and Claude 3 Opus via FastAPI.

Switch to Anthropic Claude with a single environment variable change. The kit's unified LLM abstraction handles Claude's message format, streaming protocol, and token counting automatically.

Setup in 4 steps

1Add ANTHROPIC_API_KEY to your .env file
2Set LLM_PROVIDER=anthropic in config
3Your existing llm.chat() calls work unchanged
4Token counting maps automatically to Anthropic's usage format

What's included

Claude 3.5 Sonnet, Claude 3 Opus, Claude 3 Haiku — configurable
Streaming via Anthropic's native streaming protocol, abstracted
Token counting normalised across providers for consistent billing
System prompt support with Claude's preferred message structure
Fallback to OpenAI if Anthropic is unavailable

Code example

example.py

# .env — just change the provider
ANTHROPIC_API_KEY=sk-ant-...
LLM_PROVIDER=anthropic
LLM_MODEL=claude-3-5-sonnet-20241022

# Zero code changes in your business logic
response = await llm.chat(
    messages=[{"role": "user", "content": prompt}],
    stream=True,  # Kit handles Anthropic's stream format
)

Full documentation: /docs/llm-providers

Anthropic integration pre-wired and ready.

FastAPI AI Kit ships with Anthropic configured out of the box. No manual setup required.

Ready to ship your AI backend this weekend?

Join developers who skipped weeks of boilerplate and went straight to building.

Read the docs

No subscriptions · One-time payment · Lifetime updates