Models API
Claude, GPT and Gemini through their native APIs. USD per 1M tokens, at the lowest price each model is available for.
| Model | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Claude Fable 5.1 Anthropic | $5.00 | $25.00 | $0.13 | $6.25 |
| Claude Opus 5.5 Anthropic | $2.00 | $10.00 | $0.10 | $2.50 |
| Claude Sonnet 5.5 Anthropic | $1.00 | $5.00 | $0.05 | $1.25 |
| Claude Haiku 5.5 Anthropic | $0.05 | $0.25 | $0.005 | $0.0625 |
| Claude Fable 5 Anthropic | $5.00 | $25.00 | $0.50 | $6.25 |
| Claude Opus 5 Anthropic | $2.50 | $12.50 | $0.25 | $3.13 |
| Claude Sonnet 5 Anthropic | $1.00 | $5.00 | $0.10 | $1.25 |
| Claude Opus 4.8 Anthropic | $2.50 | $12.50 | $0.25 | $3.13 |
| Claude Opus 4.7 Anthropic | $2.50 | $12.50 | $0.25 | $3.13 |
| Claude Opus 4.6 Anthropic | $2.50 | $12.50 | $0.25 | $3.13 |
| Claude Sonnet 4.6 Anthropic | $1.50 | $7.50 | $0.15 | $1.88 |
| Claude Opus 4.5 Anthropic | $2.50 | $12.50 | $0.25 | $3.13 |
| Claude Sonnet 4.5 Anthropic | $1.50 | $7.50 | $0.15 | $1.88 |
| Claude Haiku 4.5 Anthropic | $0.50 | $2.50 | $0.05 | $0.63 |
| Gemini 3.1 Pro Google | $1.00 | $6.00 | $0.10 | $0.19 |
| Gemini 3 Flash Google | $0.25 | $1.50 | $0.025 | $0.0416 |
| Gemini 4 Argon Google | $1.00 | $5.00 | $0.10 | $0.19 |
| Gemini 3.5 Flash Google | $0.75 | $4.50 | $0.075 | $0.0416 |
| Gemini 3.8 Flash Google | $0.38 | $1.88 | $0.0375 | $0.0209 |
| Gemini 3.6 Flash Google | $0.38 | $1.88 | $0.0375 | $0.0209 |
| GPT-6 Astra OpenAI | $5.00 | $25.00 | $0.50 | — |
| GPT-6.1 Sol OpenAI | $1.00 | $5.00 | $0.05 | — |
| GPT-6 Sol OpenAI | $1.00 | $5.00 | $0.10 | — |
| GPT-5.6 Sol OpenAI | $1.00 | $5.00 | $0.10 | — |
| GPT-5.6 Terra OpenAI | $1.00 | $6.00 | $0.10 | — |
| GPT-5.6 Luna OpenAI | $0.10 | $0.60 | $0.01 | — |
Frequently asked questions
Billing details are in the docs and the Terms of Service.
›Is there a subscription or monthly fee?
No. You top up your balance from $5 and pay only for the tokens you use. There is no monthly fee.
›How do I pay?
Top up in US dollars with PayPal, from $5 to $5,000 at a time. Credit is added to your balance as soon as the payment completes.
›How are model prices set?
Every model costs 50% of its official list price per million tokens, for input, output, cache reads and cache writes. The marketplace shows each price live.
›What happens when my balance runs out?
Requests are refused with HTTP 402 until you top up.
›Do failed requests cost anything?
You pay for the tokens generated. A model call that fails before producing output costs nothing.
›Can I get a refund?
Payments for credit are non-refundable except where the law requires otherwise. If you think you were charged in error, contact support within 30 days.