Introduction · Token Streamer

Token Streamer gives your organization one API for many AI models. You send OpenAI-style requests to one address. Token Streamer sends each request to the right provider, records usage and applies your limits.

Quickstart

1. Create your workspace

2. Choose how you pay for model calls

Use your own provider key. Connect a provider, such as OpenAI or Anthropic. The provider bills you directly.
Use Token Streamer credits. Buy credits and use the models Token Streamer funds.

3. Create an API key

Open API keys and create a key. Copy it. You see the full key only once. See API keys.

4. Send your first request

The base URL is https://router.streamtoken.dev/v1. Send the key as a Bearer token.

bash

curl https://router.streamtoken.dev/v1/chat/completions \
  -H "Authorization: Bearer $STREAMTOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.4-mini",
    "messages": [{"role": "user", "content": "Say hello."}]
  }'

The API is compatible with the OpenAI SDKs. Change only the base URL and the key.

python

from openai import OpenAI

client = OpenAI(
    base_url="https://router.streamtoken.dev/v1",
    api_key="<STREAMTOKEN_API_KEY>",
)

completion = client.chat.completions.create(
    model="openai/gpt-5.4-mini",
    messages=[{"role": "user", "content": "Say hello."}],
)
print(completion.choices[0].message.content)

typescript

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: 'https://router.streamtoken.dev/v1',
    apiKey: process.env.STREAMTOKEN_API_KEY,
});

const completion = await client.chat.completions.create({
    model: 'openai/gpt-5.4-mini',
    messages: [{ role: 'user', content: 'Say hello.' }],
});
console.log(completion.choices[0].message.content);

Use GET /v1/models to list the models your key can use. See the model API reference for streaming, tools, embeddings, images and more.

What you get

Feature	What it does
One API	Chat, streaming, tool calls, embeddings, moderation, transcription, images and video through one OpenAI-compatible API.
Your own provider keys	Save a provider key once. Every eligible model in that region uses it.
Credits	Prepaid balance for models that Token Streamer funds. You see each charge.
Organizations and departments	Invite your team. Give each department its own models and spending limit.
Scoped API keys	Limit each key to an organization or a department, a region and a list of models.
Regions	Keep requests in Europe or the United States. Keys stay in their region.
Usage history and diagnostics	See requests, tokens, errors and spending by model or provider. Look up one request by its ID.
Data controls	Choose what Token Streamer keeps. The Pro plan never keeps request text.
Account security	Two-factor authentication and passkeys for every account.

Plans

Pay as you go, Pro and Enterprise. See plans.