01
Top up your balance
Start with a minimum $10 top-up. Your first successful top-up adds bonus credit equal to 50% of the amount actually paid.
$10 minimum · First top-up +50%
Pay for what you use.
From your first experiment to production at scale, use the models you need through one API. Top up from $10, pay for actual usage, and grow without a fixed monthly fee.
No fixed monthly fee$10 minimum top-up50% extra credit on your first successful top-upRates based on model and usage
How billing works
One account balance across models. Each call is measured by the model’s billing unit and shown in your account.
02
Choose a model
Compare model rates before you call. Charges depend on the model, selected specification, billing unit and actual usage.
Tokens · Images · Video time
03
Review your usage
Check request records and costs by model in your account. Use the usage view to follow how your balance is spent.
Dashboard → Usage
| Provider | Model | Category | Price | Details |
|---|---|---|---|---|
| OpenAI |  GPT-5 | Text | InputUSD 1 / 1M tokensOutputUSD 8 / 1M tokens | View model |
| OpenAI | GPT-5 Chat (latest) | Text | Input · Context ≤ 400000 tokens · Maximum output 100000 tokens · Maximum input 272000 tokensUSD 1 / 1M tokensOutput · Context ≤ 400000 tokens · Maximum output 100000 tokens · Maximum input 272000 tokensUSD 8 / 1M tokens | View model |
| OpenAI | GPT-5 Mini | Text | Input · Service tier flexUSD 0.1 / 1M tokensOutput · Service tier flexUSD 0.8 / 1M tokens | View model |
| OpenAI | GPT-5 Nano | Text | Input · Service tier flexUSD 0.02 / 1M tokensOutput · Service tier flexUSD 0.16 / 1M tokens | View model |
| Anthropic |  Claude Opus 4.1 | Text | InputUSD 12 / 1M tokensOutputUSD 60 / 1M tokens | View model |
| Anthropic | Claude Opus 4.1 (latest) | Text | InputUSD 12 / 1M tokensOutputUSD 60 / 1M tokens | View model |
| OpenAI | GPT OSS 20B | Text | InputUSD 0.0144 / 1M tokensOutputUSD 0.072 / 1M tokens | View model |
| OpenAI | GPT OSS 120B | Text | InputUSD 0.0256 / 1M tokensOutputUSD 0.112 / 1M tokens | View model |
| Cohere |  Command A Vision | Text | InputUSD 2 / 1M tokensOutputUSD 8 / 1M tokens | View model |
| Mistral |  Codestral 25.08 | Text | InputUSD 0.24 / 1M tokensOutputUSD 0.72 / 1M tokens | View model |
| Zhipu AI |  GLM-4.5 | Text | InputUSD 0.48 / 1M tokensOutputUSD 1.76 / 1M tokens | View model |
| Zhipu AI | GLM-4.5-Air | Text | InputUSD 0.104 / 1M tokensOutputUSD 0.68 / 1M tokens | View model |
| Zhipu AI | GLM-4.5-Flash | Text | Input · Context ≤ 128000 tokens · Maximum output 96000 tokensUSD 0 / 1M tokensOutput · Context ≤ 128000 tokens · Maximum output 96000 tokensUSD 0 / 1M tokens | View model |
| Alibaba |  Qwen3 Coder Flash | Text | InputUSD 0.1152 / 1M tokensOutputUSD 0.4592 / 1M tokens | View model |
| Alibaba | Qwen Flash | Text | InputUSD 0.0176 / 1M tokensOutputUSD 0.1728 / 1M tokens | View model |
| Alibaba | Qwen MT Plus | Text | InputUSD 0.2 / 1M tokensOutputUSD 0.6 / 1M tokens | View model |
| Alibaba | Qwen3 Coder Plus | Text | InputUSD 1.44 / 1M tokensOutputUSD 7.2 / 1M tokens | View model |
| Alibaba | Qwen3 235B-A22B Instruct 2507 | Text | InputUSD 0.104 / 1M tokensOutputUSD 0.4 / 1M tokens | View model |
| Mistral | Voxtral Mini 3B 2507 | Text | InputUSD 0.032 / 1M tokensOutputUSD 0.032 / 1M tokens | View model |
| Mistral | Voxtral Small (latest) | Text | InputUSD 0.08 / 1M tokensOutputUSD 0.24 / 1M tokens | View model |
| Mistral | Voxtral Small 24B 2507 | Text | InputUSD 0.08 / 1M tokensOutputUSD 0.24 / 1M tokens | View model |
| Moonshot AI |  Kimi K2 0711 | Text | InputUSD 0.456 / 1M tokensOutputUSD 1.84 / 1M tokens | View model |
| Moonshot AI | Kimi K2 Instruct | Text | InputUSD 0.4 / 1M tokensOutputUSD 1.6 / 1M tokens | View model |
| Cognitivecomputations |  Uncensored | Text | InputUSD 0.220064 / 1M tokensOutputUSD 0.990288 / 1M tokens | View model |