Standard Compute
Flat-rate smart-routing gateway: one model id, each request routed across a curated catalog of 1M-context models (DeepSeek, GLM, MiniMax, Qwen, GPT-5.6, Claude 5, Gemini 2.5, Kimi) or pinned to a user-selected model
Model facts
- Context window
- 1M tokens
- Maximum output
- 25K tokens
- Cheapest paid input
- free per 1M tokens
- Cheapest paid output
- free per 1M tokens
- Open weights
- no
- Providers
- 1
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, text, image.
Observed price history
- 2026-08-25: free input / free output per 1M tokens
API providers
- Standard Compute — model id standardcompute; free input / free output per 1M tokens; provider documentation