Docs — Routix

Authentication

Every request carries your key in the Authorization header, as a bearer token. Keep it server-side; a key in a browser bundle is a key you have published.

Authorization: Bearer $ROUTIX_API_KEY

Quickstart

Your first request, end to end. Works with curl and with any OpenAI client library.

curl

curl https://routix.tech/v1/chat/completions \
  -H "Authorization: Bearer $ROUTIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3-flash",
    "messages": [
      {"role": "user", "content": "Explain routing in one sentence."}
    ]
  }'

response · 200

{
  "id": "chatcmpl-rx9f2a...",
  "object": "chat.completion",
  "created": 1792523626,
  "model": "glm-5.3-flash",
  "choices": [{
    "index": 0,
    "message": { "role": "assistant", "content": "Routing sends each request to the model..." },
    "finish_reason": "stop"
  }],
  "usage": { "prompt_tokens": 11, "completion_tokens": 24, "total_tokens": 35 }
}

API reference

List models

GET /v1/models

Returns every model your key can call.

{
  "object": "list",
  "data": [
    {
      "id": "glm-5.3-flash",
      "object": "model",
      "owned_by": "Zhipu AI"
    }
  ]
}

Fields

Field	Type	Description
id	string	Model identifier to pass in model.
object	string	Always "model".
owned_by	string	The model family that owns it.

Chat completions

POST /v1/chat/completions

The same request body as the OpenAI chat completions endpoint. Supported parameters are passed through unchanged.

Request body

Parameter	Type	Required	Description
model	string	yes	One of the ids from /v1/models.
messages	array	yes	Conversation history as {role, content} objects.
stream	boolean	no	Return server-sent events instead of a single JSON body.
temperature	number	no	Passed through to the model.
max_tokens	integer	no	Upper bound on generated tokens.
top_p	number	no	Nucleus sampling threshold.
stop	string \| array	no	Sequences that end generation.

Streaming

Set "stream": true and the response arrives as server-sent events. Each event is a chat.completion.chunk, terminated by data: [DONE].

curl · stream

curl -N https://routix.tech/v1/chat/completions \
  -H "Authorization: Bearer $ROUTIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3-flash",
    "stream": true,
    "messages": [{"role": "user", "content": "Count to three."}]
  }'

events

data: {"id":"chatcmpl-rx...","object":"chat.completion.chunk","model":"glm-5.3-flash","choices":[{"delta":{"role":"assistant","content":""}}]}

data: {"id":"chatcmpl-rx...","object":"chat.completion.chunk","model":"glm-5.3-flash","choices":[{"delta":{"content":"One"}}]}

data: {"id":"chatcmpl-rx...","object":"chat.completion.chunk","model":"glm-5.3-flash","choices":[{"delta":{"content":", two"}}]}

data: [DONE]

Note

Events are forwarded as they arrive from the model. If you proxy Routix through another layer, disable that layer's response buffering or tokens will arrive in bursts instead of as they are generated.

Errors

Errors use the standard OpenAI envelope, so existing error handling keeps working.

{
  "error": {
    "message": "Model not found: gpt-9",
    "type": "invalid_request_error",
    "code": "model_not_found"
  }
}

Status	Code	Meaning
400	invalid_request_error	The body was not valid JSON.
401	authentication_error	Missing or invalid API key.
404	model_not_found	The model id is not available to your key.
429	rate_limit_exceeded	Too many requests for this key. Wait Retry-After seconds. See Limits.
503	api_error	The upstream model is temporarily unavailable.

Guides

Using the OpenAI SDK

Point the client at Routix and everything else stays the same.

python

from openai import OpenAI

client = OpenAI(
    base_url="https://routix.tech/v1",
    api_key=os.environ["ROUTIX_API_KEY"],
)

r = client.chat.completions.create(
    model="glm-5.3-flash",
    messages=[{"role": "user", "content": "Hi"}],
)

node

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://routix.tech/v1",
  apiKey: process.env.ROUTIX_API_KEY,
});

const r = await client.chat.completions.create({
  model: "glm-5.3-flash",
  messages: [{ role: "user", content: "Hi" }],
});

Limits

Limit	Value
Request body	32 MB
Request timeout	300 s
Rate limit	60 requests / 60 s, per key

Rate limiting

Limits apply per API key over a sliding 60-second window. Every successful response includes the current state of your quota:

response headers

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 59
X-RateLimit-Reset: 60

Header	Meaning
X-RateLimit-Limit	Requests allowed in the window.
X-RateLimit-Remaining	Requests left in the current window.
X-RateLimit-Reset	Seconds until the window frees up again.

Exceeding the limit returns 429 with a Retry-After header in seconds. Back off by that amount rather than retrying immediately.

429 response

HTTP/1.1 429 Too Many Requests
Retry-After: 43

{
  "error": {
    "message": "Rate limit exceeded: 60 requests per 60s per key",
    "type": "rate_limit_error",
    "code": "rate_limit_exceeded"
  }
}

Need more

Limits are per key, not per account — create additional keys from your dashboard if you run several workloads. For substantially higher volume, get in touch.

← Back home Get API key

Routix API