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 |
|---|---|---|---|---|
| Anthropic |  Claude Sonnet 4 | Text | InputUSD 2.4 / 1M tokensOutputUSD 12 / 1M tokens | View model |
| Anthropic | Claude Sonnet 4 (latest) | Text | Input · Base context tier (boundary 200000 tokens)USD 2.4 / 1M tokensOutput · Base context tier (boundary 200000 tokens)USD 12 / 1M tokens | View model |
 Gemini Embedding 001 | Text | InputUSD 0.12 / 1M tokens | View model | |
| Upstage |  Solar Pro 2 | Text | InputUSD 0.12 / 1M tokensOutputUSD 0.48 / 1M tokens | View model |
| Mistral |  Mistral Medium 3 | Text | InputUSD 0.32 / 1M tokensOutputUSD 1.6 / 1M tokens | View model |
| Mistral | Mistral Medium 3 | Text | InputUSD 0.32 / 1M tokensOutputUSD 1.6 / 1M tokens | View model |
| Writer |  Palmyra X5 | Text | InputUSD 0.48 / 1M tokensOutputUSD 4.8 / 1M tokens | View model |
| Alibaba |  Qwen3 30B A3B | Text | InputUSD 0.0864 / 1M tokensOutputUSD 0.8608 / 1M tokens | View model |
| OpenAI |  o3 | Text | InputUSD 1.6 / 1M tokensOutputUSD 6.4 / 1M tokens | View model |
| OpenAI | o4-mini | Text | InputUSD 0.88 / 1M tokensOutputUSD 3.52 / 1M tokens | View model |
| Nvidia |  Llama 3.1 Nemotron 70B Instruct | Text | InputUSD 0.48 / 1M tokensOutputUSD 0.48 / 1M tokens | View model |
| OpenAI | GPT-4.1 | Text | InputUSD 1.6 / 1M tokensOutputUSD 6.4 / 1M tokens | View model |
| OpenAI | GPT-4.1 mini | Text | InputUSD 0.32 / 1M tokensOutputUSD 1.28 / 1M tokens | View model |
| OpenAI | GPT-4.1 nano | Text | InputUSD 0.064 / 1M tokensOutputUSD 0.208 / 1M tokens | View model |
| Mistral | Pixtral Large (25.02) | Text | InputUSD 1.5944 / 1M tokensOutputUSD 4.7824 / 1M tokens | View model |
| Nvidia | Llama 3.3 Nemotron Super 49B v1 | Text | Input · Context ≤ 128000 tokens · Maximum output 16384 tokens · Maximum input 128000 tokensUSD 0.12 / 1M tokensOutput · Context ≤ 128000 tokens · Maximum output 16384 tokens · Maximum input 128000 tokensUSD 0.12 / 1M tokens | View model |
| Meta |  Llama 4 Maverick 17B Instruct | Text | Input · Context ≤ 1048576 tokens · Maximum output 8192 tokensUSD 0.112 / 1M tokensOutput · Context ≤ 1048576 tokens · Maximum output 8192 tokensUSD 0.472 / 1M tokens | View model |
| Meta | Llama 4 Scout 17B Instruct | Text | Input · Context ≤ 131072 tokens · Maximum output 131072 tokensUSD 0.144 / 1M tokensOutput · Context ≤ 131072 tokens · Maximum output 131072 tokensUSD 0.472 / 1M tokens | View model |
| Alibaba | Qwen3 32B | Text | InputUSD 0.064 / 1M tokensOutputUSD 0.224 / 1M tokens | View model |
| Alibaba | Qwen3 235B-A22B | Text | InputUSD 0.24 / 1M tokensOutputUSD 0.4 / 1M tokens | View model |
| Alibaba | Qwen3-Coder 30B-A3B Instruct | Text | InputUSD 0.056 / 1M tokensOutputUSD 0.208 / 1M tokens | View model |
| Alibaba | Qwen3-Coder 480B-A35B Instruct | Text | InputUSD 0.304 / 1M tokensOutputUSD 1.24 / 1M tokens | View model |
| DeepSeek |  DeepSeek V3 0324 | Text | Input · Quantization fp8USD 0.2 / 1M tokensOutput · Quantization fp8USD 0.8 / 1M tokens | View model |
| DeepSeek | DeepSeek V3 0324 | Text | InputUSD 0.192 / 1M tokensOutputUSD 0.72 / 1M tokens | View model |