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 |
|---|---|---|---|---|
| Cohere |  Command A | Text | InputUSD 2 / 1M tokensOutputUSD 8 / 1M tokens | View model |
| Cohere | Command A | Text | InputUSD 2 / 1M tokensOutputUSD 8 / 1M tokens | View model |
 Gemma 3 4B IT | Text | InputUSD 0.04 / 1M tokensOutputUSD 0.08 / 1M tokens | View model | |
| Gemma 3 12B IT | Text | InputUSD 0.04 / 1M tokensOutputUSD 0.12 / 1M tokens | View model | |
| Gemma 3 27B IT | Text | InputUSD 0.064 / 1M tokensOutputUSD 0.128 / 1M tokens | View model | |
| Rekaai |  Reka Flash 3 | Text | InputUSD 0.08 / 1M tokensOutputUSD 0.16 / 1M tokens | View model |
| Thedrummer |  Skyfall 36B V2 | Text | InputUSD 0.44 / 1M tokensOutputUSD 0.64 / 1M tokens | View model |
| Alibaba |  QwQ 32B | Text | Input · Context ≤ 24000 tokens · Maximum output 24000 tokensUSD 0.528 / 1M tokensOutput · Context ≤ 24000 tokens · Maximum output 24000 tokensUSD 0.8 / 1M tokens | View model |
| Alibaba | QwQ Plus | Text | InputUSD 0.184 / 1M tokensOutputUSD 0.4592 / 1M tokens | View model |
| Cohere | Command R7B Arabic | Text | InputUSD 0.03 / 1M tokensOutputUSD 0.12 / 1M tokens | View model |
| Anthropic |  Claude Sonnet 3.7 | Text | InputUSD 2.4 / 1M tokensOutputUSD 12 / 1M tokens | View model |
| Mistral |  Saba | Text | InputUSD 0.16 / 1M tokensOutputUSD 0.48 / 1M tokens | View model |
| MiniMax (minimax.io) |  MiniMax image-01 | Image | Output · Up to 1 input reference imagesUSD 0.0028 / image | View model |
| Aion Labs |  Aion-RP 1.0 (8B) | Text | InputUSD 0.880256 / 1M tokensOutputUSD 1.760512 / 1M tokens | View model |
| Perplexity |  Sonar Deep Research | Text | InputUSD 1.6 / 1M tokensOutputUSD 6.4 / 1M tokens | View model |
| Mistral | Mistral Small 3 | Text | InputUSD 0.04 / 1M tokensOutputUSD 0.064 / 1M tokens | View model |
| DeepSeek |  DeepSeek-R1 | Text | InputUSD 0.56 / 1M tokensOutputUSD 1.92 / 1M tokens | View model |
| DeepSeek | DeepSeek-R1-Distill-Qwen-32B | Text | Input · Context ≤ 32768 tokens · Maximum output 16384 tokensUSD 0.2296 / 1M tokensOutput · Context ≤ 32768 tokens · Maximum output 16384 tokensUSD 0.6888 / 1M tokens | View model |
| Alibaba | Qwen-Omni Turbo | Audio | InputUSD 0.0464 / 1M tokensOutputUSD 0.184 / 1M tokens | View model |
| MiniMax (minimax.io) | MiniMax Text 01 (MiniMax) | Text | InputUSD 0.16 / 1M tokensOutputUSD 0.88 / 1M tokens | View model |
| DeepSeek | DeepSeek-V3 | Text | InputUSD 0.256 / 1M tokensOutputUSD 0.712 / 1M tokens | View model |
| OpenAI |  o3-mini | Text | InputUSD 0.88 / 1M tokensOutputUSD 3.52 / 1M tokens | View model |
| Sao10k |  Llama 3.3 Euryale 70B | Text | InputUSD 0.715208 / 1M tokensOutputUSD 0.82524 / 1M tokens | View model |
| Microsoft |  Phi-4-mini | Text | InputUSD 0.06 / 1M tokensOutputUSD 0.24 / 1M tokens | View model |