CHrouter API

An OpenAI-compatible chat endpoint. Any OpenAI client library works by changing its base URL and API key.

Connecting

Base URL	`https://api.chrouter.ch/v1`
Authentication	`Authorization: Bearer chr_…` - the key you were given.
Endpoints	`POST /v1/chat/completions` (streaming and not) `GET /v1/models`

Models

Pass a routing name as model; it picks a model and falls back to the next one if a provider fails:

general_text
general_text_smart

A specific model id also works. GET /v1/models lists every name your key can use. Text chat only.

Limits

Requests per minute, set per key. The response headers x-ratelimit-limit-requests and x-ratelimit-remaining-requests show where you stand.
A monthly spending cap per key, and one for the whole API.
max_tokens is capped at 4096 per request and applied when you send none.
Request bodies up to 1 MB.
Prompts and answers are not stored; only token counts, cost, model and timing are kept.

Errors

In OpenAI's shape: {"error": {"message", "type", "code"}}.

Status	`code`	Meaning
400		The request is malformed (for example, `messages` missing).
401	`invalid_api_key`	No key, a wrong key, or a revoked key. Repeated failures block your address for a while.
402	`budget_exhausted`	Your key's monthly cap, or the API's, is reached.
404	`model_not_found`	The model or path does not exist.
413	`request_too_large`	The request body is over 1 MB.
422	`model_not_served`	The model exists but is not offered on this API.
429	`rate_limit_exceeded`	Too many requests this minute; wait the seconds in `Retry-After`.
502		Every provider for the model failed; retry later.
503	`service_unavailable`	The API is paused.

Examples

curl:

curl https://api.chrouter.ch/v1/chat/completions \
  -H "Authorization: Bearer $CHROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "general_text", "messages": [{"role": "user", "content": "Hello"}]}'

Python (pip install openai):

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.chrouter.ch/v1", api_key=os.environ["CHROUTER_API_KEY"])
reply = client.chat.completions.create(
    model="general_text",
    messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)

JavaScript (npm install openai):

import OpenAI from 'openai';

const client = new OpenAI({ baseURL: 'https://api.chrouter.ch/v1', apiKey: process.env.CHROUTER_API_KEY });
const stream = await client.chat.completions.create({
  model: 'general_text',
  messages: [{ role: 'user', content: 'Hello' }],
  stream: true,
});
for await (const chunk of stream) process.stdout.write(chunk.choices[0]?.delta?.content || '');