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 |  Whisper Large v3 Turbo | Text | InputUSD 0.00184 / 1M tokensOutputUSD 0.00184 / 1M tokens | View model |
| Meta |  Llama-3.2-1B | Text | InputUSD 0.08 / 1M tokensOutputUSD 0.08 / 1M tokens | View model |
| Meta | Llama-3.2-3B | Text | InputUSD 0.08 / 1M tokensOutputUSD 0.08 / 1M tokens | View model |
| Meta | Llama-3.2-11B-Vision-Instruct | Text | InputUSD 0.276 / 1M tokensOutputUSD 0.276 / 1M tokens | View model |
| Meta | Llama 3.2 1B Instruct | Text | Input · Context ≤ 60000 tokens · Maximum output 32000 tokensUSD 0.0216 / 1M tokensOutput · Context ≤ 60000 tokens · Maximum output 32000 tokensUSD 0.1608 / 1M tokens | View model |
| Mistral |  Pixtral 12B | Text | Input · Context ≤ 128000 tokens · Maximum output 4000 tokensUSD 0.12 / 1M tokensOutput · Context ≤ 128000 tokens · Maximum output 4000 tokensUSD 0.12 / 1M tokens | View model |
| Alibaba |  Qwen2.5-VL 72B Instruct | Text | InputUSD 1.8352 / 1M tokensOutputUSD 5.5048 / 1M tokens | View model |
| Cohere |  Command R | Text | InputUSD 0.12 / 1M tokensOutputUSD 0.48 / 1M tokens | View model |
| Cohere | Command R+ | Text | InputUSD 2 / 1M tokensOutputUSD 8 / 1M tokens | View model |
| Sao10k |  Llama 3.1 Euryale 70B v2.2 | Text | InputUSD 1.595904 / 1M tokensOutputUSD 1.595904 / 1M tokens | View model |
| Nousresearch |  Hermes 3 70B Instruct | Text | InputUSD 0.56 / 1M tokensOutputUSD 0.56 / 1M tokens | View model |
| Nousresearch | Hermes 3 405B Instruct | Text | InputUSD 0.8 / 1M tokensOutputUSD 0.8 / 1M tokens | View model |
| Sao10k | Llama 3 8B Lunaris | Text | InputUSD 0.055016 / 1M tokensOutputUSD 0.055016 / 1M tokens | View model |
| OpenAI | GPT-4o (2024-08-06) | Text | InputUSD 2 / 1M tokensOutputUSD 8 / 1M tokens | View model |
| Meta | Llama-3.1-8B-Instruct | Text | InputUSD 0.016 / 1M tokensOutputUSD 0.032 / 1M tokens | View model |
| Meta | Llama-3.1-70B-Instruct | Text | InputUSD 0.32 / 1M tokensOutputUSD 0.32 / 1M tokens | View model |
| Meta | Llama-Guard-3-8B | Text | InputUSD 0.044 / 1M tokensOutputUSD 0.044 / 1M tokens | View model |
| OpenAI | GPT-4o mini | Text | InputUSD 0.06 / 1M tokensOutputUSD 0.24 / 1M tokens | View model |
 Gemma 2 27B | Text | InputUSD 0.52 / 1M tokensOutputUSD 0.52 / 1M tokens | View model | |
| Mistral | Mistral Nemo | Text | InputUSD 0.016 / 1M tokensOutputUSD 0.024 / 1M tokens | View model |
| Mistral | Codestral (latest) | Text | InputUSD 0.24 / 1M tokensOutputUSD 0.72 / 1M tokens | View model |
| Mistral | Codestral-22B-v0.1 | Text | Input · Context ≤ 128000 tokens · Maximum output 4000 tokensUSD 0.24 / 1M tokensOutput · Context ≤ 128000 tokens · Maximum output 4000 tokensUSD 0.72 / 1M tokens | View model |
| Vispark |  Vision Large | Text | InputUSD 5.896 / 1M tokensOutputUSD 17.688 / 1M tokens | View model |
| Vispark | Vision Medium | Text | InputUSD 3.368 / 1M tokensOutputUSD 10.104 / 1M tokens | View model |