13 models · 3 providers
Models
01 · anthropic
Anthropic
6 models
- Claude Fable 5input / 1M$10.00output / 1M$50.00context1M
- Claude Fable 5.1input / 1M$10.00output / 1M$50.00context1M
- Claude Opus 4.8input / 1M$5.00output / 1M$25.00context1M
- Claude Opus 5.5input / 1M$4.00output / 1M$20.00context1M
- Claude Sonnet 5input / 1M$2.00output / 1M$10.00context1M
- Claude Sonnet 5.5input / 1M$2.00output / 1M$10.00context1M
02 · openai
OpenAI
1 model
- GPT-5.4 Miniinput / 1M$0.75output / 1M$4.50context400k
03 · google
6 models
- Gemini 3.1 Flash Liteinput / 1M$0.25output / 1M$1.50context1.05M
- Gemini 3.5 Flashinput / 1M$1.50output / 1M$9.00context1.05M
- Gemini 3.5 Flash Liteinput / 1M$0.30output / 1M$2.50context1.05M
- Gemini 3.6 Flashinput / 1M$0.75output / 1M$3.75context1.05M
- Gemini 3.7 Flashinput / 1M$0.75output / 1M$3.75context1.05M
- Gemini 3.8 Flashinput / 1M$0.75output / 1M$3.75context1.05M
Prices are the provider's list price per million tokens; usage is billed at that price, and adding credits carries a processing fee. Context is the model's context window: the conversation plus a turn's input must fit in it. The settings each model accepts, and their ranges, are on the compatibility page.
Start
Pick a model and make the first call.
model is a field on every request. Name one on the first turn and change it on any later one; the thread stays with us. 14 days free, then $19 a month, tokens at provider price.