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 |
|---|---|---|---|---|
| DeepSeek |  DeepSeek V4 Flash Vision Exp | Text | InputUSD 0.112 / 1M tokensOutputUSD 0.224 / 1M tokens | View model |
| Tencent |  Hy-MT2-1.8B | Text | InputUSD 0.0352 / 1M tokensOutputUSD 0.1416 / 1M tokens | View model |
| Tencent | Hy-MT2-30B-A3B | Text | InputUSD 0.0592 / 1M tokensOutputUSD 0.236 / 1M tokens | View model |
| Tencent | Hy-MT2-7B | Text | InputUSD 0.0592 / 1M tokensOutputUSD 0.236 / 1M tokens | View model |
| Deepreinforce |  Ornith 1.5 35B A3B | Text | InputUSD 0.08 / 1M tokensOutputUSD 0.32 / 1M tokens | View model |
| Zhipu AI |  GLM-5.3 | Text | Input · Quantization fp4USD 0.0632 / 1M tokensOutput · Quantization fp4USD 1.12 / 1M tokens | View model |
| Alibaba |  Qwen3.8 27B | Text | Input · Quantization fp4USD 0.016 / 1M tokensOutput · Quantization fp4USD 0.4 / 1M tokens | View model |
 Gemini 3.7 Flash | Text | InputUSD 0.6 / 1M tokensOutputUSD 3 / 1M tokens | View model | |
| Gemini Flash Latest | Text | InputUSD 0.4 / 1M tokensOutputUSD 2.4 / 1M tokens | View model | |
| Mixedbread |  Toast 1 | Text | InputUSD 0.24 / 1M tokensOutputUSD 0.576 / 1M tokens | View model |
| DeepSeek | DeepSeek V4 Pro 0813 | Text | InputUSD 0.3536 / 1M tokensOutputUSD 0.7072 / 1M tokens | View model |
| xAI |  Grok 4.6 | Text | InputUSD 1.6 / 1M tokensOutputUSD 4.8 / 1M tokens | View model |
| Alibaba | Qwen3.8 2.4T A95B | Text | InputUSD 1.56 / 1M tokensOutputUSD 4.56 / 1M tokens | View model |
| Microsoft |  MAI-Code-1.1-Flash | Text | InputUSD 0.16 / 1M tokensOutputUSD 0.96 / 1M tokens | View model |
| Nvidia |  Nemotron 3.5 Lightning 30B A3B | Text | InputUSD 0.04 / 1M tokensOutputUSD 0.16 / 1M tokens | View model |
| Meta |  Muse Glimmer 30B | Text | InputUSD 0.2 / 1M tokensOutputUSD 0.8 / 1M tokens | View model |
| OpenAI |  GPT-5.6 Cyber | Text | InputUSD 10 / 1M tokensOutputUSD 60 / 1M tokens | View model |
| Motif Technologies |  Motif 3 | Text | InputUSD 0.4 / 1M tokensOutputUSD 1.6 / 1M tokens | View model |
| Upstage |  Solar Pro 4 | Text | InputUSD 0.024 / 1M tokensOutputUSD 0.096 / 1M tokens | View model |
| Meta | Muse Spark 1.2 | Text | InputUSD 1 / 1M tokensOutputUSD 3.4 / 1M tokens | View model |
| Alibaba | Qwen3.8 Max | Text | InputUSD 1.232 / 1M tokensOutputUSD 3.7048 / 1M tokens | View model |
| Sakana AI |  Sakana Namazu | Text | InputUSD 0.76 / 1M tokensOutputUSD 3.2 / 1M tokens | View model |
| DeepSeek | DeepSeek V4 Flash 0731 | Text | InputUSD 0.028 / 1M tokensOutputUSD 0.056 / 1M tokens | View model |
| Thinking Machines |  Inkling Small | Text | Input · Context ≤ 524288 tokens · Maximum output 1048576 tokensUSD 0.36 / 1M tokensOutput · Context ≤ 524288 tokens · Maximum output 1048576 tokensUSD 0.96 / 1M tokens | View model |