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 | $10.00 | $50.00 | $0.25 | $12.50 |
| Claude Opus 5.5 Anthropic | $4.00 | $20.00 | $0.20 | $5.00 |
| Claude Sonnet 5.5 Anthropic | $2.00 | $10.00 | $0.10 | $2.50 |
| Claude Haiku 5.5 Anthropic | $0.10 | $0.50 | $0.01 | $0.13 |
| Claude Fable 5 Anthropic | $10.00 | $50.00 | $1.00 | $12.50 |
| Claude Opus 5 Anthropic | $5.00 | $25.00 | $0.50 | $6.25 |
| Claude Sonnet 5 Anthropic | $2.00 | $10.00 | $0.20 | $2.50 |
| Claude Opus 4.8 Anthropic | $5.00 | $25.00 | $0.50 | $6.25 |
| Claude Opus 4.7 Anthropic | $5.00 | $25.00 | $0.50 | $6.25 |
| Claude Opus 4.6 Anthropic | $5.00 | $25.00 | $0.50 | $6.25 |
| Claude Sonnet 4.6 Anthropic | $3.00 | $15.00 | $0.30 | $3.75 |
| Claude Opus 4.5 Anthropic | $5.00 | $25.00 | $0.50 | $6.25 |
| Claude Sonnet 4.5 Anthropic | $3.00 | $15.00 | $0.30 | $3.75 |
| Claude Haiku 4.5 Anthropic | $1.00 | $5.00 | $0.10 | $1.25 |
| Gemini 3.1 Pro Google | $2.00 | $12.00 | $0.20 | $0.38 |
| Gemini 3 Flash Google | $0.50 | $3.00 | $0.05 | $0.0833 |
| Gemini 4 Argon Google | $2.00 | $10.00 | $0.20 | $0.38 |
| Gemini 3.5 Flash Google | $1.50 | $9.00 | $0.15 | $0.0833 |
| Gemini 3.8 Flash Google | $0.75 | $3.75 | $0.075 | $0.0417 |
| Gemini 3.6 Flash Google | $0.75 | $3.75 | $0.075 | $0.0417 |
| GPT-6 Astra OpenAI | $10.00 | $50.00 | $1.00 | — |
| GPT-6.1 Sol OpenAI | $2.00 | $10.00 | $0.10 | — |
| GPT-6 Sol OpenAI | $2.00 | $10.00 | $0.20 | — |
| GPT-6.1 Terra OpenAI | $1.00 | $5.00 | $0.05 | — |
| GPT-5.6 Sol OpenAI | $2.00 | $10.00 | $0.20 | — |
| GPT-5.6 Terra OpenAI | $2.00 | $12.00 | $0.20 | — |
| GPT-5.6 Luna OpenAI | $0.20 | $1.20 | $0.02 | — |
| DeepSeek V4.1 Flash Abliterated DeepSeek | $0.80 | $2.00 | $0.20 | — |
| Dongfangshuo 27B v2 Dongfangshuo | $1.50 | $23.40 | $0.15 | — |
Images
Image generation through the OpenAI Images API. One flat price per image, any size or quality.
Video
Character swap through the Videos API: re-shoot a clip with a new character. Priced per second of video you get back.
Text to speech
Preset voices, voices designed from a description and voice cloning, in many languages. Priced per minute of audio, billed by the second.
Data tools
101 scrapers and search tools for agents, from $0.0001 per result. Runs that fail pay only for the results they delivered.
Browser agent
A real browser that clicks, types and logs in for your agents. Billed per step; AI models and JSON output included.
Cloud agents
Hosted agents with their own workspace and API. You pay for the size while an agent runs, plus its storage; model calls and tools inside it cost their usual prices.
| Size | Shared vCPUs | Memory | Per hour running |
|---|---|---|---|
| Small | 2 | 2 GiB | $0.05 |
| Medium | 4 | 4 GiB | $0.10 |
| Large | 8 | 8 GiB | $0.20 |
- • Kept ready between sessions: $0.36 per month + $0.30 per GB-month of disk + $0.16 per GB-month of daily backups, charged daily
- • Unused for 7 days: archived at $0.20 per GiB-month of its files
- • Shared vCPUs run at full speed in bursts; long CPU-heavy work runs at a lower baseline. No extra charge for bursts
- • White-label agents (your own branding): 1.5× the rates above
- • Your own domain for white-label agents: $0.50 per day
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 what you use: tokens, results, browser steps and agent hours. 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.
›Are model prices the same as the official ones?
Yes. Each model costs what its maker lists per million tokens, including cache reads and writes. Some channel groups cost more; the marketplace shows every price.
›What happens when my balance runs out?
Requests are refused with HTTP 402 and new runs do not start until you top up. Data tool and browser runs hold their maximum cost up front, so they never overspend.
›Do failed requests cost anything?
You pay for tokens generated and results delivered. A model call that fails before producing output costs nothing, and a data tool run that fails pays only for the results it returned.
›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.