Pricing
Simple, usage-based pricing. Pay only for what you use.
How It Works
Purchase Credits
Add funds to your account via Stripe. Your balance is available immediately.
Use the API
Make requests to any supported model. Costs are calculated per token.
Track Usage
Monitor your spending in real-time. Get detailed analytics on your usage.
Text Model Pricing
Pricing per 1,000,000 tokens for each model
| Model | Description | Input Cost | Output Cost |
|---|---|---|---|
| mistral-voxtral-mini-3b-2507 | Japan: Mistral's voxtral-mini-3b-2507 | ¥8.4 / 1M tokens | ¥8.4 / 1M tokens |
| anthropic-claude-opus-4-8 | Global: Claude Opus 4.8 - Most intelligent, best for agents and coding | ¥893.5 / 1M tokens | ¥4,467.5 / 1M tokens |
| anthropic-claude-opus-4-7 | Global: Claude Opus 4.7 - Most intelligent, best for agents and coding | ¥840 / 1M tokens | ¥4,200 / 1M tokens |
| anthropic-claude-opus-4-6 | Global: Claude Opus 4.6 - Most intelligent, best for agents and coding | ¥850 / 1M tokens | ¥4,200 / 1M tokens |
| anthropic-claude-sonnet-4-6 | Japan: Claude Sonnet 4.6 - Best balance of speed and intelligence | ¥554.4 / 1M tokens | ¥2,772 / 1M tokens |
| anthropic-claude-haiku-4-5 | Japan: Claude Haiku 4.5 - Fastest with near-frontier intelligence | ¥184.8 / 1M tokens | ¥924 / 1M tokens |
| minimax-m2.7 | Global: Minimax's M2.7 | ¥53.61 / 1M tokens | ¥214.44 / 1M tokens |
| glm-5 | Global: Z.ai's GLM-5 | ¥178.7 / 1M tokens | ¥571.84 / 1M tokens |
| llm-jp-3.1-8x13b-instruct4 | Japan: Japanese language model optimized for instruction following | ¥16 / 1M tokens | ¥79 / 1M tokens |
| japan-gemma-4-31b | Japan: Google's Gemma 4 31B - hosted and run in Japan | ¥26 / 1M tokens | ¥101 / 1M tokens |
| japan-qwen3.6-35b | Japan: Qwen 3.6 35B-A3B - hosted and run in Japan | ¥32 / 1M tokens | ¥158 / 1M tokens |
| japan-kimi-k2.6 | Japan: Moonshot AI's Kimi K2.6 - hosted and run in Japan | ¥64 / 1M tokens | ¥316 / 1M tokens |
| japan-kimi-k2.7-code | Japan: Moonshot AI's Kimi K2.7 Code - hosted and run in Japan | ¥55 / 1M tokens | ¥530 / 1M tokens |
| gpt-oss-120b | Japan: gpt-oss-120b | ¥16 / 1M tokens | ¥79 / 1M tokens |
| minimax-m3 | Global: MiniMax's M3 | ¥53.61 / 1M tokens | ¥214.44 / 1M tokens |
| qwen3.6-27b | Global: Qwen 3.6 27B | ¥80.415 / 1M tokens | ¥482.49 / 1M tokens |
| qwen3.8-27b | Global: Qwen 3.8 27B | ¥98.285 / 1M tokens | ¥589.71 / 1M tokens |
| kimi-k2.6 | Global: Moonshot AI's Kimi K2.6 | ¥169.765 / 1M tokens | ¥714.8 / 1M tokens |
| glm-4.7 | Global: Z.ai's GLM 4.7 | ¥107.22 / 1M tokens | ¥393.14 / 1M tokens |
| glm-4.7-flash | Global: Z.ai's GLM 4.7 Flash | ¥10.722 / 1M tokens | ¥71.48 / 1M tokens |
| glm-5.1 | Global: Z.ai's GLM 5.1 | ¥250.18 / 1M tokens | ¥786.28 / 1M tokens |
| mimo-v2.5 | Global: Xiaomi's MiMo-V2.5 | ¥25.018 / 1M tokens | ¥50.036 / 1M tokens |
| mimo-v2.5-pro | Global: Xiaomi's MiMo-V2.5-Pro | ¥77.7345 / 1M tokens | ¥155.469 / 1M tokens |
| deepseek-v4-flash | Global: DeepSeek's V4 Flash | ¥16.083 / 1M tokens | ¥32.166 / 1M tokens |
| deepseek-v4-flash-0731 | Global: DeepSeek's V4 Flash 0731 | ¥25.018 / 1M tokens | ¥50.036 / 1M tokens |
| deepseek-v4-pro | Global: DeepSeek's V4 Pro | ¥341.317 / 1M tokens | ¥684.421 / 1M tokens |
| glm-5.2 | Global: Z.ai's GLM 5.2 | ¥250.18 / 1M tokens | ¥786.28 / 1M tokens |
| glm-5.3 | Global: Z.ai's GLM 5.3 | ¥250.18 / 1M tokens | ¥786.28 / 1M tokens |
| kimi-k3 | Global: Moonshot AI's Kimi K3 | ¥536.1 / 1M tokens | ¥2,680.5 / 1M tokens |
| qwen3.7-max | Global: Qwen 3.7 Max | ¥263.5825 / 1M tokens | ¥790.7475 / 1M tokens |
| qwen3.8-max | Global: Qwen 3.8 Max | ¥357.4 / 1M tokens | ¥1,072.2 / 1M tokens |
| grok-4.5 | Global: xAI's Grok 4.5 | ¥357.4 / 1M tokens | ¥1,072.2 / 1M tokens |
| grok-4.6 | Global: xAI's Grok 4.6 | ¥357.4 / 1M tokens | ¥1,072.2 / 1M tokens |
| gpt-5.6-sol | Global: OpenAI's GPT-5.6 Sol | ¥893.5 / 1M tokens | ¥5,361 / 1M tokens |
| gpt-5.6-terra | Global: OpenAI's GPT-5.6 Terra | ¥357.4 / 1M tokens | ¥2,144.4 / 1M tokens |
| gpt-5.6-luna | Global: OpenAI's GPT-5.6 Luna | ¥35.74 / 1M tokens | ¥214.44 / 1M tokens |
| gemini-3.5-flash | Global: Google's Gemini 3.5 Flash | ¥268.05 / 1M tokens | ¥1,608.3 / 1M tokens |
| gemini-3.7-flash | Global: Google's Gemini 3.7 Flash | ¥134.025 / 1M tokens | ¥670.125 / 1M tokens |
| inkling | Global: Thinking Machines' Inkling | ¥178.7 / 1M tokens | ¥723.735 / 1M tokens |
| anthropic-claude-opus-5 | Global: Claude Opus 5 - Most intelligent, best for agents and coding | ¥893.5 / 1M tokens | ¥4,467.5 / 1M tokens |
| anthropic-claude-sonnet-5 | Global: Claude Sonnet 5 - Best balance of speed and intelligence | ¥357.4 / 1M tokens | ¥1,787 / 1M tokens |
| anthropic-claude-fable-5 | Global: Claude Fable 5 - Anthropic's flagship Mythos-class model | ¥1,787 / 1M tokens | ¥8,935 / 1M tokens |
| muse-glimmer-30b | Global: Meta's Muse Glimmer 30B | ¥62.545 / 1M tokens | ¥268.05 / 1M tokens |
| gemini-flash-lite-free | Global: Google's Gemini Flash Lite - free to try | ¥0 / 1M tokens | ¥0 / 1M tokens |
| random-free | Global: Random - free to try | ¥0 / 1M tokens | ¥0 / 1M tokens |
Image Model Pricing
Per-image pricing for image generation models
| Model | Description | Cost |
|---|---|---|
| google-nano-banana-2 | Global: Google Nano Banana 2 - fast, high-quality image generation | ¥12.23 / image |
| bytedance-seedream-4.5 | Global: Generate images | ¥7.15 / image |
| z-image-turbo | Global: Generate realistic images | ¥1.68 / image |
| lustify-sdxl | Global: Generate animated images | ¥1.68 / image |
Video Model Pricing
Flat per-video pricing for video generation models
| Model | Specs | Cost |
|---|---|---|
| Seedance 2.0 Fast | 8s · 1280x720 · with audio | ¥250 / video |
Using FastMetal at your company
Billing in yen, qualified invoices, and a prepaid balance that caps spend — with the questions procurement usually asks answered in one place.
See the business page