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 |  GPT-5.2 Pro | Text | InputUSD 16.8 / 1M tokensOutputUSD 134.4 / 1M tokens | View model |
| Zhipu AI |  AutoGLM Phone 9B Multilingual | Text | InputUSD 0.028 / 1M tokensOutputUSD 0.1104 / 1M tokens | View model |
| Mistral |  Devstral 2 | Text | InputUSD 0.32 / 1M tokensOutputUSD 1.6 / 1M tokens | View model |
| Mistral | Devstral Small 2 | Text | Input · Context ≤ 256000 tokens · Maximum output 131072 tokensUSD 0.08 / 1M tokensOutput · Context ≤ 256000 tokens · Maximum output 131072 tokensUSD 0.24 / 1M tokens | View model |
| Zhipu AI | GLM-4.6V | Text | Input · Base context tier (boundary 32000 tokens)USD 0.1096 / 1M tokensOutput · Base context tier (boundary 32000 tokens)USD 0.3288 / 1M tokens | View model |
| Zhipu AI | GLM-4.6V-Flash | Text | Input · Base context tier (boundary 32000 tokens)USD 0.01744 / 1M tokensOutput · Base context tier (boundary 32000 tokens)USD 0.17472 / 1M tokens | View model |
| Relace |  Relace Search | Text | InputUSD 1.10032 / 1M tokensOutputUSD 3.30096 / 1M tokens | View model |
| Kling AI |  Kling 2.6 Pro Image to Video | Video | Output · Audio off · Service route kling · Last-frame image omitted · Video duration 5 seconds · Up to 1 input reference imagesUSD 0.05824 / second | View model |
| Kling AI | Kling 2.6 Pro Text to Video | Video | Output · Audio off · Service route kling · Video duration 5 secondsUSD 0.05824 / second | View model |
| Kling AI | Kling Image O1 | Image | Output · Up to 2500 characters per request · Reference elements omitted · image urls limits ≤10 MB; width≥300 px; height≥300 px; W/H 0.4–2.5 · num images 1 · Service route fal · Resolution 1K · Up to 1 input reference imagesUSD 0.0224 / image | View model |
| Kling AI | Kling O1 Video to Video Reference | Video | Output · Up to 2500 characters per request · Reference elements omitted · keep audio off · Service route fal · Video input required · video url limits ≤200 MB; width≥720 px; width≤2160 px; height≥720 px; height≤2160 px; 3–10.05 s · Video duration 5 secondsUSD 0.1344 / second | View model |
| Kling AI | Kling Video O1 Image to Video | Video | Output · Up to 2500 characters per request · Reference elements omitted · Service route fal · start image url limits ≤50 MB; width≥300 px; height≥300 px; W/H 0.4–2.5 · Last-frame image omitted · Video duration 5 seconds · Up to 1 input reference imagesUSD 0.0896 / second | View model |
| Kling AI | Kling Video O1 Reference to Video | Video | Output · Up to 2500 characters per request · Reference elements omitted · Service route fal · Video duration 5 seconds · Up to 1 input reference imagesUSD 0.0896 / second | View model |
| Kling AI | Kling Video O1 Video to Video Edit | Video | Input · Up to 2500 characters per request · Reference elements omitted · keep audio off · Service route fal · Video input required · video url limits ≤200 MB; width≥720 px; width≤2160 px; height≥720 px; height≤2160 px; 3–10.05 s · Video duration 3–10 secondsUSD 0.1344 / second | View model |
| Mistral | Devstral 2 (latest) | Text | InputUSD 0.32 / 1M tokensOutputUSD 1.6 / 1M tokens | View model |
| Mistral | Ministral 3 3B | Text | InputUSD 0.08368 / 1M tokensOutputUSD 0.08368 / 1M tokens | View model |
| Mistral | Ministral 3 3B 2512 | Text | InputUSD 0.08 / 1M tokensOutputUSD 0.08 / 1M tokens | View model |
| Mistral | Ministral 3 8B | Text | InputUSD 0.12 / 1M tokensOutputUSD 0.12 / 1M tokens | View model |
| Mistral | Ministral 3 8B 2512 | Text | InputUSD 0.12 / 1M tokensOutputUSD 0.12 / 1M tokens | View model |
| Mistral | Ministral 3 14B | Text | InputUSD 0.16 / 1M tokensOutputUSD 0.16 / 1M tokens | View model |
| Mistral | Ministral 3 14B 2512 | Text | InputUSD 0.16 / 1M tokensOutputUSD 0.16 / 1M tokens | View model |
| Mistral | Ministral 14B | Text | Input · Context ≤ 256000 tokens · Maximum output 131072 tokensUSD 0.16 / 1M tokensOutput · Context ≤ 256000 tokens · Maximum output 131072 tokensUSD 0.16 / 1M tokens | View model |
| Mistral | Mistral Large 3 | Text | InputUSD 0.4 / 1M tokensOutputUSD 1.2 / 1M tokens | View model |
| Amazon |  Nova 2 Lite | Text | Input · Maximum output 65535 tokensUSD 0.24 / 1M tokensOutput · Maximum output 65535 tokensUSD 2 / 1M tokens | View model |