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 |
|---|---|---|---|---|
| Nvidia |  Llama Nemotron Rerank VL 1B v2 | Text | Input · Maximum input 10240 tokens · Service tier defaultUSD 0.008 / 1M tokens | View model |
 Veo 3.1 Lite Preview | Video | Output · video · Audio off · Resolution 720pUSD 0.0312 / second | View model | |
| Gemini 3.1 Flash Live Preview | Audio | InputUSD 0.6 / 1M tokensOutputUSD 3.6 / 1M tokens | View model | |
| Lyria 3 Clip Preview | Audio | Output · 30 seconds per songUSD 0.032 / song | View model | |
| Lyria 3 Pro Preview | Audio | Output · Maximum input 131072 tokensUSD 0.064 / song | View model | |
| Rekaai |  Reka Edge | Text | InputUSD 0.110032 / 1M tokensOutputUSD 0.110032 / 1M tokens | View model |
| Xiaomi |  MiMo-V2-Omni | Text | InputUSD 0.32 / 1M tokensOutputUSD 1.6 / 1M tokens | View model |
| Xiaomi | MiMo-V2-Pro | Text | InputUSD 0.8 / 1M tokensOutputUSD 2.4 / 1M tokens | View model |
| MiniMax (minimax.io) |  MiniMax-M2.7 | Text | InputUSD 0.064 / 1M tokensOutputUSD 0.256 / 1M tokens | View model |
| MiniMax (minimax.io) | MiniMax-M2.7-highspeed | Text | InputUSD 0.48 / 1M tokensOutputUSD 1.92 / 1M tokens | View model |
| OpenAI |  GPT-5.4 mini | Text | InputUSD 0.6 / 1M tokensOutputUSD 3.6 / 1M tokens | View model |
| OpenAI | GPT-5.4 nano | Text | InputUSD 0.16 / 1M tokensOutputUSD 1 / 1M tokens | View model |
| Zhipu AI |  GLM-5-Turbo | Text | InputUSD 0.96 / 1M tokensOutputUSD 3.2 / 1M tokens | View model |
| Mistral |  Mistral Small (latest) | Text | InputUSD 0.12 / 1M tokensOutputUSD 0.48 / 1M tokens | View model |
| Mistral | Mistral Small 4 | Text | InputUSD 0.12 / 1M tokensOutputUSD 0.48 / 1M tokens | View model |
| Nvidia | Nemotron 3 Super 120B A12B | Text | InputUSD 0.096 / 1M tokensOutputUSD 0.416 / 1M tokens | View model |
| xAI |  Grok 4.20 (Non-Reasoning) | Text | InputUSD 1 / 1M tokensOutputUSD 2 / 1M tokens | View model |
| xAI | Grok 4.20 (Reasoning) | Text | InputUSD 1 / 1M tokensOutputUSD 2 / 1M tokens | View model |
| OpenAI | GPT-5.4 | Text | InputUSD 1.44 / 1M tokensOutputUSD 8.64 / 1M tokens | View model |
| OpenAI | GPT-5.4 Pro | Text | Input · Rate applies to input ≤ 271999 tokens · Service tier flexUSD 12 / 1M tokensOutput · Rate applies to input ≤ 271999 tokens · Service tier flexUSD 72 / 1M tokens | View model |
| Inception |  Mercury 2 | Text | InputUSD 0.2 / 1M tokensOutputUSD 0.6 / 1M tokens | View model |
| Gemini 3.1 Flash Lite Preview | Text | InputUSD 0.1 / 1M tokensOutputUSD 0.6 / 1M tokens | View model | |
| OpenAI | GPT-5.3 Chat (latest) | Text | InputUSD 1.4 / 1M tokensOutputUSD 11.2 / 1M tokens | View model |
| Nano Banana 2 Preview | Image | InputUSD 0.4 / 1M tokensOutputUSD 2.4 / 1M tokens | View model |