Models

Each model id maps to one published model and version.

Chat and coding

ModelIdInput per 1M tokensOutput per 1M tokens
DeepSeek V4.1 Flashdeepseek-v4.1-flash$0.30$1.20
Kimi K3.1 Prokimi-k3.1-pro$2.20$11.00

Also served

These are available now. Ask us for ids and prices.

  • Qwen
  • Hy4
  • Embedding models
  • Voice and transcription models

The same list is published as JSON at /models.json.