Available Models
All models are available on every plan. Token usage coefficients depend on the model.
| Model | Tier | Input | Output | Cache |
|---|---|---|---|---|
| GPT (OpenAI) | ||||
gpt-6-astra | Flagship | 5.0x | 5.0x | 2.25x |
gpt-5.6-sol | High | 2.0x | 2.0x | 0.9x |
gpt-5.6-terra | Standard | 1.0x | 1.0x | 0.45x |
gpt-5.6-luna | Budget | 0.4x | 0.4x | 0.2x |
gpt-5.5 | High | 2.0x | 2.0x | 0.9x |
gpt-5.4 | Standard | 1.0x | 1.0x | 0.45x |
gpt-5.4-mini | Budget | 0.3x | 0.3x | 0.15x |
gpt-image-2 | Standard | 1.0x | 1.0x | 0.45x |
| Claude (Anthropic) | ||||
claude-fable-5-1 | Flagship | 9.5x | 9.5x | 4.25x |
claude-opus-5 | Premium | 2.0x | 2.0x | 0.9x |
claude-opus-4.8 | Premium | 2.0x | 2.0x | 0.9x |
claude-opus-4.6 | Premium | 2.0x | 2.0x | 0.9x |
claude-sonnet-5 | Entry | 0.8x | 0.8x | 0.35x |
claude-sonnet-4.6 | Standard | 1.2x | 1.2x | 0.5x |
claude-haiku-4.5 | Budget | 0.4x | 0.4x | 0.2x |
| Gemini (Google GenAI) | ||||
gemini-3.7-flash | Standard | 1.2x | 1.2x | 0.5x |
gemini-3.6-flash | Standard | 1.2x | 1.2x | 0.5x |
gemini-3.5-flash | Standard | 1.2x | 1.2x | 0.5x |
gemini-3.1-pro | Standard | 1.2x | 1.2x | 0.5x |
gemini-3-flash-preview | Standard | 1.2x | 1.2x | 0.5x |
| Grok (xAI) | ||||
grok-4.6 | Standard | 1.15x | 1.15x | 0.5x |
grok-4.5 | Standard | 1.15x | 1.15x | 0.5x |
The coefficient shows how token usage from your balance is multiplied. For example, 1.2x on input = 1000 input tokens deduct 1200 from your balance.