QWEN API
Qwen3 models, one endpoint.
Call Qwen3 for chat, vision, code and text-to-speech through one OpenAI-compatible API key, with long context and strong multilingual output.
Hand this to your agent
Add a Runcrate model to this project: run curl -fsSL"https://runcrate.ai/agents.md?intent=build"and follow it.
Your agent asks for an API key. Create a key
Quick start
Hand it to your agent. Or read the request it sends.
Your agent writes and runs it. The same key works for every model and every GPU.
Available models
Models you can call today. Billed prices, as charged.
| Model | Maker | Price | Detail |
|---|---|---|---|
| Qwen/Qwen3-235B-A22B-Instruct-2507 | Alibaba | $0.0945 in, $0.578 out per 1M tokens | 235B MoE, flagship model |
| Qwen/Qwen3-TTS | Alibaba | $0.021 per 1K characters | Text-to-speech synthesis |
Why Runcrate
Built for production. One key, one balance.
Multimodal family
Chat, vision, TTS, and code models all under one model family. Use the same API patterns across modalities.
29+ languages
Native support for Chinese, English, Japanese, Korean, Arabic, and 24 more languages. Strong performance on multilingual benchmarks.
128K context
Process long documents, large codebases, or extended conversations without hitting context limits.
Listed prices
Each Qwen model has one listed per-token price on /inference/pricing, and requests are billed at exactly that rate.
FAQ
Common questions.
Related