OpenAI-compatible · streaming · one key

Inference API for developers.

Point any OpenAI-compatible client at a single endpoint. Hosted models, low latency, transparent token usage.

8M free tokens for 3 days · no card required · $6/mo after

Base URL
https://api.modelrouters.net/v1

Models

More models coming online. All served over the same OpenAI-compatible API.

DeepSeek

COMING SOON

Reasoning-optimized model. Coming soon.

Reasoning

GLM

COMING SOON

A highly-requested open model tuned for rich, long-form conversation. Coming soon.

Conversational128K context

Complex Qwen

LIVE

Our hosted, high-throughput conversational model. OpenAI-compatible, streaming, low latency.

General / conversational32K context

Pricing

Free trial
8M tokens / 3 days
  • • Full access to Complex Qwen
  • • No card required
  • • Streaming + non-streaming
Start trial
Full access
$6 / mo
  • • Uncapped usage for normal use
  • • Priority scheduling over trial traffic
  • • Cancel anytime
Get started