Quickstart

Every DeepToken endpoint is OpenAI-compatible. If you already have working OpenAI code, you only need to change two lines: the base URL and the API key.

Code Examples

Select your language of choice to initialize the client and make a request:

from openai import OpenAI

client = OpenAI(
    api_key="$DEEPTOKEN_API_KEY",
    base_url="https://api.deeptoken.app/v1",
)

resp = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hi"}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai"

const client = new OpenAI({
  apiKey: process.env.DEEPTOKEN_API_KEY,
  baseURL: "https://api.deeptoken.app/v1",
})

const completion = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Hi" }],
})

curl https://api.deeptoken.app/v1/chat/completions \
  -H "Authorization: Bearer $DEEPTOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Say hello in one sentence."}]
  }'

Streaming

Pass stream: true for an SSE stream. Streaming is metered on the same path as non-streaming requests — every token is counted, every call lands in the usage ledger.

Other endpoints

The gateway routes all common OpenAI-compatible endpoints:

POST /v1/chat/completions
POST /v1/completions
POST /v1/embeddings
POST /v1/moderations
POST /v1/images/generations
POST /v1/audio/speech
POST /v1/audio/transcriptions
POST /v1/audio/translations
GET /v1/models

Pick the model in the request body; the gateway picks the channel.