TokenRouter

Overview

TokenRouter is a unified API gateway that aggregates models from many upstream providers behind a single OpenAI-compatible interface.

Official Website: https://www.tokenrouter.com API Documentation: https://www.tokenrouter.com/docs

Key features

Unified gateway — Broad model selection from one endpoint
OpenAI-compatible — Standard /chat/completions interface
Multi-provider routing — Route requests across upstream providers
Unified access — One endpoint across all upstream providers

Address TokenRouter models using the provider/model convention by prefixing with tokenrouter/. Like OpenRouter, TokenRouter model ids may themselves be namespaced; Yunxin passes the nested suffix upstream (for example, tokenrouter/openai/gpt-4o). Requests use the same Yunxin base URL (https://api.yuhuanstudio.com/v1) and your Yunxin sk- API key.

Usage example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["YUNXIN_API_KEY"],
    base_url="https://api.yuhuanstudio.com/v1"
)

response = client.chat.completions.create(
    model="tokenrouter/openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.YUNXIN_API_KEY,
  baseURL: "https://api.yuhuanstudio.com/v1",
});

const response = await client.chat.completions.create({
  model: "tokenrouter/openai/gpt-4o",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.choices[0].message.content);

curl https://api.yuhuanstudio.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YUNXIN_API_KEY" \
  -d '{
    "model": "tokenrouter/openai/gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Available models

Query the live catalog with the Models API:

curl "https://api.yuhuanstudio.com/v1/models?provider=tokenrouter" \
  -H "Authorization: Bearer $YUNXIN_API_KEY"

Capabilities and pricing are tracked per model. Use GET /v1/models?provider=tokenrouter and each model's capabilities array as the authoritative source rather than relying on a hardcoded list.

Unified gateway — Broad model selection from one endpoint
OpenAI-compatible — Standard /chat/completions interface
Multi-provider routing — Route requests across upstream providers
Unified access — One endpoint across all upstream providers

Using TokenRouter with Yunxin

Usage example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["YUNXIN_API_KEY"],
    base_url="https://api.yuhuanstudio.com/v1"
)

response = client.chat.completions.create(
    model="tokenrouter/openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.YUNXIN_API_KEY,
  baseURL: "https://api.yuhuanstudio.com/v1",
});

const response = await client.chat.completions.create({
  model: "tokenrouter/openai/gpt-4o",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.choices[0].message.content);

curl https://api.yuhuanstudio.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YUNXIN_API_KEY" \
  -d '{
    "model": "tokenrouter/openai/gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Available models

Query the live catalog with the Models API:

curl "https://api.yuhuanstudio.com/v1/models?provider=tokenrouter" \
  -H "Authorization: Bearer $YUNXIN_API_KEY"

Capabilities and pricing are tracked per model. Use GET /v1/models?provider=tokenrouter and each model's capabilities array as the authoritative source rather than relying on a hardcoded list.

Overview

Key features

Using TokenRouter with Yunxin

Usage example

Available models

Official resources

On this page

TokenRouter

Overview

Key features

Using TokenRouter with Yunxin

Usage example

Available models

Official resources

On this page