Model pricing
What every model costs.
Generation is billed at the provider's list price with no markup from us. These are the rates your workspace runs on. We add and retire models constantly, so the line-up stays on whatever is doing the best creative work, never on whatever we wired up first.
Billed per token, quoted per million. Input is what you send, output is what the model writes back.
| Model | Price |
|---|---|
Claude Haiku 4.5 anthropic/claude-haiku-4.5 | Input$1.00/ 1M tokens Output$5.00/ 1M tokens |
Claude Sonnet 5 anthropic/claude-sonnet-5 | Input$2.00/ 1M tokens Output$10.00/ 1M tokens |
Claude Opus 4.8 anthropic/claude-opus-4.8 | Input$5.00/ 1M tokens Output$25.00/ 1M tokens |
Claude Fable 5 anthropic/claude-fable-5 | Input$10.00/ 1M tokens Output$50.00/ 1M tokens |
Gemini 3 Flash google/gemini-3-flash | Input$0.500/ 1M tokens Output$3.00/ 1M tokens |
Gemini 3.5 Flash google/gemini-3.5-flash | Input$1.50/ 1M tokens Output$9.00/ 1M tokens |
Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | Input$2.00/ 1M tokens Output$12.00/ 1M tokens |
GPT 5.6 Luna openai/gpt-5.6-luna | Input$0.200/ 1M tokens Output$1.20/ 1M tokens |
GPT 5.6 Terra openai/gpt-5.6-terra | Input$2.00/ 1M tokens Output$12.00/ 1M tokens |
GPT 5.6 Sol openai/gpt-5.6-sol | Input$5.00/ 1M tokens Output$30.00/ 1M tokens |
About these prices
Prices last synced on 11 August 2026. They are provider list prices and can change at any time without notice from us. The rate charged is the one in effect when a generation runs, which is the figure your usage dashboard reports.
Figures exclude your seat subscription, add ons and any taxes.
Bringing your own provider keys? Ask us about BYOK.