Using the API

Coco Router exposes the standard OpenAI API surface. Anything that can talk to OpenAI can talk to Coco Router by changing two settings: the base URL and the API key.

Connection settings

curl

curl https://router.cocolevio.com/dash/v1/chat/completions \
  -H "Authorization: Bearer sk-YOUR-KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"auto","messages":[{"role":"user","content":"Write a Python LRU cache"}]}'

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://router.cocolevio.com/dash/v1",
    api_key="sk-YOUR-KEY",
)
resp = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Summarize this meeting…"}],
)
print(resp.choices[0].message.content)

JavaScript / TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://router.cocolevio.com/dash/v1",
  apiKey: "sk-YOUR-KEY",
});
const resp = await client.chat.completions.create({
  model: "auto",
  messages: [{ role: "user", content: "hi" }],
});

Reading the routing decision

raw = resp.model_dump()          # or resp.json() on raw HTTP
print(raw.get("ai_router"))      # {'tier': 'SIMPLE', 'model': 'openrouter/…'}
print(resp.model)                 # rewritten to the real backend model

Other endpoints

curl https://router.cocolevio.com/dash/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-YOUR-KEY" \
  -F file=@answer.wav -F model=whisper-1

curl https://router.cocolevio.com/dash/v1/embeddings \
  -H "Authorization: Bearer sk-YOUR-KEY" -H "Content-Type: application/json" \
  -d '{"model":"text-embedding-3-small","input":"hello"}'

curl https://router.cocolevio.com/dash/v1/models -H "Authorization: Bearer sk-YOUR-KEY"