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 |
|---|---|---|---|---|
 Deep Research Max Preview | Image | Input · Base context tier (boundary 200000 tokens) · Context ≤ 131072 tokens · Maximum output 65536 tokensUSD 1.6 / 1M tokensOutput · Base context tier (boundary 200000 tokens) · Context ≤ 131072 tokens · Maximum output 65536 tokensUSD 9.6 / 1M tokens | View model | |
| Gemini Deep Research Preview | Image | Input · Base context tier (boundary 200000 tokens) · Context ≤ 131072 tokens · Maximum output 65536 tokensUSD 1.6 / 1M tokensOutput · Base context tier (boundary 200000 tokens) · Context ≤ 131072 tokens · Maximum output 65536 tokensUSD 9.6 / 1M tokens | View model | |
| OpenAI |  GPT-5.4 Image 2 | Image | InputUSD 6.4 / 1M tokensOutputUSD 12 / 1M tokens | View model |
| OpenAI | GPT-Image-2 | Image | InputUSD 4 / 1M tokensOutputUSD 24 / 1M tokens | View model |
| Moonshot AI |  Kimi K2.6 | Text | InputUSD 0.4 / 1M tokensOutputUSD 1.592 / 1M tokens | View model |
| Tencent |  Hy3 preview | Text | InputUSD 0.136 / 1M tokensOutputUSD 0.4533288 / 1M tokens | View model |
| Alibaba |  Qwen3.6 Max Preview | Text | InputUSD 1.72 / 1M tokensOutputUSD 10.288 / 1M tokens | View model |
| xAI |  Grok 4.3 | Text | InputUSD 1 / 1M tokensOutputUSD 2 / 1M tokens | View model |
| Alibaba | Qwen3.6 35B-A3B | Text | InputUSD 0.112 / 1M tokensOutputUSD 0.8 / 1M tokens | View model |
| Anthropic |  Claude Opus 4.7 | Text | InputUSD 4 / 1M tokensOutputUSD 20 / 1M tokens | View model |
| xAI | Grok Build 0.1 | Text | Input · Base context tier (boundary 200000 tokens)USD 0.8 / 1M tokensOutput · Base context tier (boundary 200000 tokens)USD 1.6 / 1M tokens | View model |
| Gemini 3.1 Flash TTS Preview | Audio | InputUSD 0.8 / 1M tokensOutputUSD 16 / 1M tokens | View model | |
| Gemini Robotics-ER 1.6 Preview | Text | InputUSD 0.8 / 1M tokensOutputUSD 4 / 1M tokens | View model | |
| Meta |  Muse Spark 1.1 | Text | InputUSD 1 / 1M tokensOutputUSD 3.4 / 1M tokens | View model |
| Zhipu AI |  GLM-5.1 | Text | InputUSD 0.36 / 1M tokensOutputUSD 1.72 / 1M tokens | View model |
| xAI | Grok Imagine Image Quality | Image | Input reference image fee · Resolution 1K · Up to 3 input reference imagesUSD 0.008 / imageOutput · Resolution 1K · Up to 3 input reference imagesUSD 0.04 / image | View model |
| Gemma 4 26B A4B IT | Text | InputUSD 0.0336 / 1M tokensOutputUSD 0.176 / 1M tokens | View model | |
| Gemma 4 31B IT | Text | InputUSD 0.08 / 1M tokensOutputUSD 0.2 / 1M tokens | View model | |
| Gemma 4 E2B IT | Text | InputUSD 0.032 / 1M tokensOutputUSD 0.064 / 1M tokens | View model | |
| Gemma 4 E4B IT | Text | Input · Context ≤ 32768 tokens · Maximum output 32768 tokensUSD 0.16 / 1M tokensOutput · Context ≤ 32768 tokens · Maximum output 32768 tokensUSD 0.16 / 1M tokens | View model | |
| Alibaba | Qwen3.6 Plus | Text | InputUSD 0.24 / 1M tokensOutputUSD 1.44 / 1M tokens | View model |
| StepFun (China) |  Step 3.5 Flash 2603 | Text | Input · Context ≤ 256000 tokens · Maximum output 131072 tokens · Maximum input 256000 tokensUSD 0.08 / 1M tokensOutput · Context ≤ 256000 tokens · Maximum output 131072 tokens · Maximum input 256000 tokensUSD 0.24 / 1M tokens | View model |
| Zhipu AI | GLM-5V-Turbo | Text | InputUSD 0.96 / 1M tokensOutputUSD 3.2 / 1M tokens | View model |
| Arcee Ai |  Trinity Large Thinking | Text | Input · Context ≤ 262144 tokens · Maximum output 262144 tokensUSD 0.2 / 1M tokensOutput · Context ≤ 262144 tokens · Maximum output 262144 tokensUSD 0.64 / 1M tokens | View model |