Simple, transparent pricing
Pay only for what you use. No hidden fees, no surprise charges. Start free and scale as you grow.
Free
Get started with basic access
¥0/mo
¥10 quota included
- 5 API keys
- 1,000 requests/day
- 100K tokens/day
- 2 QPS limit
- Community support
Starter
For individual developers
¥49/mo
¥100 quota included
- 20 API keys
- 10,000 requests/day
- 1M tokens/day
- 10 QPS limit
- Priority support
Most Popular
Pro
For teams and production apps
¥199/mo
¥500 quota included
- Unlimited API keys
- 100,000 requests/day
- 10M tokens/day
- 30 QPS limit
- Dedicated support
Enterprise
Custom solutions at scale
Custom
Volume-based pricing
- Unlimited everything
- Custom rate limits
- Dedicated instances
- SLA guarantees
- 24/7 phone support
Model Pricing
Per-token pricing for every model. Billed in real-time — only pay for what you use.
| Model | Input (per 1M tokens) | Output (per 1M tokens) | Context Window |
|---|---|---|---|
| claude-sonnet-4-20250514 | ¥21.00 | ¥105.00 | 200K |
| claude-opus-4-20250514 | ¥105.00 | ¥525.00 | 200K |
| claude-haiku-4-5-20251001 | ¥7.00 | ¥35.00 | 200K |
| gpt-4.1 | ¥14.00 | ¥42.00 | 1M |
| gpt-4.1-mini | ¥2.80 | ¥11.20 | 1M |
| o4-mini | ¥7.70 | ¥30.80 | 200K |
| deepseek-r1 | ¥3.50 | ¥10.50 | 128K |
Frequently Asked Questions
How does billing work?
▼
You're billed per token based on the model pricing table above. Each request consumes input and output tokens, and the cost is deducted from your quota in real-time. You can top up your quota at any time.
What happens when my quota runs out?
▼
When your quota reaches zero, new API requests will be rejected with a 429 error. Existing requests in progress will complete normally. You can top up your quota instantly from the dashboard.
Can I switch plans at any time?
▼
Yes, you can upgrade or downgrade your plan at any time. When upgrading, you'll get immediate access to the new plan's features and quota. Downgrades take effect at the start of the next billing cycle.
Do unused tokens carry over?
▼
Yes, your remaining quota balance carries over between billing periods. It never expires — you only pay for the tokens you actually use.
Is there a rate limit?
▼
Each plan has a QPS (queries per second) limit. Free tier allows 2 QPS, Starter 10 QPS, and Pro 30 QPS. Enterprise customers can request custom rate limits based on their needs.