# Docs
Quick start
OrbitRouter uses the OpenAI Chat Completions format. Point any OpenAI SDK at the base URL below.
Base URL: /v1
API keys and credits
Every request needs an API key. Sign up to get $10 in free credits, then create a key on your dashboard. Send it as Authorization: Bearer sk-orbit-....
Each successful request is charged from your balance by input and output tokens, using the per-model prices on the models page (USD per 1M tokens). Failed requests are free. When your balance runs out, requests return 402.
Endpoints
| Method | Path | What it does |
|---|---|---|
| POST | /v1/chat/completions | Chat in OpenAI format. Set "stream": true to get SSE. |
| GET | /v1/models | List of models, including thinking and default_thinking for each. |
| GET | /v1/stats | Public usage totals and leaderboards. |
| GET | /health | Health check. |
Request fields
| Field | Notes |
|---|---|
model | Model id from /v1/models. Can end with a thinking suffix. |
messages | The roles system, user, assistant and tool. Images can be sent as image_url data URLs. |
max_tokens | Maximum length of the reply. If not set, there is no limit and the model stops on its own. |
temperature, top_p, seed, stop | Passed through to the model. |
tools | OpenAI function-calling format. |
response_format | {"type": "json_object"} forces the reply to be JSON. |
Thinking
| How | Example |
|---|---|
| Model suffix | gpt-oss-120b:high, qwen3.6-35b:think, gemma4-31b:nothink |
| Request field | "think": true or false |
| OpenAI field | "reasoning_effort": "low" | "medium" | "high" | "none" |
Models that cannot think ignore these settings. Reasoning text is returned in message.reasoning_content.
Streaming
Errors
| Code | Meaning |
|---|---|
| 400 | Bad request body or bad parameter. |
| 401 | Missing or invalid API key. |
| 402 | Out of credits. |
| 404 | Unknown model. Check /v1/models. |
| 429 | Rate limited. Retry later. |
| 502 / 504 | Model unavailable or timed out. Retry. |