Quickstart
Send your first request: base URLs, keys and tested configs for Claude Code, Codex CLI, OpenCode and the OpenAI and Anthropic SDKs.
The settings
| Setting | Value |
|---|---|
| OpenAI-compatible base URL | https://api.inferspeed.ai/v1 |
| Anthropic-compatible base URL | https://api.inferspeed.ai (clients add /v1/messages) |
| Authentication | Authorization: Bearer $INFERSPEED_API_KEY (x-api-key also works) |
| Model IDs | Every public model, from GET https://inferspeed.ai/api/v1/public/pricing (data.models[].id) |
| Models per key | The models of the key's group (GET /v1/models with your key lists them) |
| Default limits | 30 requests per minute and 5 concurrent requests per account (rate limits) |
Plain-text versions
- /developers.md: base URLs, auth, endpoints, setup for Codex CLI, Claude Code, OpenCode and OpenClaw, SDK examples, errors and retries
- /agents.md: instructions for an agent configuring itself
- /skill.md: agent skill: settings, prices, balance, errors, key handling
- /llms.txt: site index; /llms-full.txt: the index and the files above in one file
- /codex.md, /glm.md, /claude-code.md: setup guides for Codex CLI and Claude Code
- /claude-agent-sdk.md, /openai-agents-sdk.md: setup guides for the Claude Agent SDK and the OpenAI Agents SDK
- /api/v1/public/pricing: prices as JSON, USD per 1M tokens