Guide

Quick Start

From zero to your first Blue Claw call in a few minutes. Change one setting; keep your stack.

Blue Claw speaks the OpenAI API. If your agent already talks to OpenAI, you're most of the way there. Swap the base URL, drop in a key, and your recurring workloads run on lower-cost open models.

1. Get an API key

Join the beta. Once you're approved we'll send a key that starts with bc_. Keep it somewhere safe. It's the only credential your client needs.

2. Point your client at Blue Claw

Change one line. Everything else about your setup stays the same.

client = OpenAI(
    base_url="https://openai.blueclaw.network/v1",
    api_key="bc_your-key-here",
)

3. Make your first call

Send a normal chat completion. Streaming works exactly as it does on OpenAI. If it comes back, you're live. 

curl https://openai.blueclaw.network/v1/chat/completions \
  -H "Authorization: Bearer bc_your-key-here" \
  -H "Content-Type: application/json" \
  -d '{"model": "auto", "messages": [{"role": "user", "content": "Hello, Blue Claw!"}]}'

4. Wire up your agent

OpenClaw, OpenCode, Hermes-style agents, LiteLLM routers, and anything that reads an OpenAI-compatible endpoint all work the same way: set the base URL and API key in the tool's config, pick a model, and point your recurring passes at Blue Claw. Keep another API on hand for the few calls that truly need frontier quality.

What you can call today

  • Chat & completions, including streaming.
  • Embeddings for search, RAG, and indexing.
  • Image generation on open image models.
  • Text-to-speech and speech-to-text.
  • Reranking to re-order retrieved candidates.

Durable async jobs and video AI tools are in development.

This is a starting point. Deeper, per-tool recipes are on the way. Stuck on something? Ask in the Discord.