Rates
Model rates.
How quickly each model choice uses your AI usage allowance and any top-ups.
Your plan includes an AI usage allowance for each billing period. The model you pick decides how fast that allowance is used. Auto is the recommended value setting; stronger named models do more per turn and use your allowance faster.
| Model | Input | Output |
|---|---|---|
Z.ai GLM 5.2Recommended | $0.757 | $2.38 |
GPT-5 Nano | $0.05 | $0.4 |
GPT-4o Mini | $0.15 | $0.6 |
GPT-4.1 Mini | $0.4 | $1.6 |
Grok 4.1 Fast (non-reasoning) | $0.2 | $0.5 |
Grok 4.1 Fast (reasoning) | $0.2 | $0.5 |
OpenRouter: GPT-4o MiniPremium | $0.15 | $0.6 |
OpenRouter: GPT-4oPremium | $2.5 | $10.0 |
OpenRouter: Claude Sonnet 4.5Premium | $3.0 | $15.0 |
OpenRouter: Claude Opus 4.6Premium | $5.0 | $25.0 |
OpenRouter: Claude 3 HaikuPremium | $0.25 | $1.25 |
OpenRouter: Gemini 2.5 FlashPremium | $0.3 | $2.5 |
OpenRouter: Llama 3.1 8B InstructPremium | $0.05 | $0.08 |
Claude Haiku 4.5Premium | $0.8 | $4.0 |
Claude Sonnet 4.6Premium | $3.0 | $15.0 |
xAI Grok 4.3Premium | $1.25 | $2.5 |
xAI Grok Build 0.1Premium | $1.0 | $2.0 |
Kimi K2.7 CodePremium | $0.73 | $3.5 |
OpenAI GPT-5 Mini | $0.25 | $2.0 |
Rates shown per 1M tokens.
Rates, models, names, units, and availability may change going forward. The rate in effect at the time you use a model is the rate that governs that usage.
Usage you have already run is never recalculated at a new rate. Any change to your subscription price is handled through the subscription notice path — never as a silent charge after the fact.