Pricing
Token-based billing. No hidden fees. Volume discounts for committed usage.
Standard
Monthly usage < 10B tokens
- check Full access to base models
- check Standard API response speed
- check Community technical support
Pro
For growing teams · 30% token discount
Free users can upgrade to Pro anytime and unlock 30% off token usage for $99/month.
- check Priority queue response
- check Team collaboration dashboard
- check Dedicated technical consultant
Enterprise
Monthly usage > 100B tokens
- check Unlimited Token consumption
- check Independent infrastructure deployment
- check 24/7 Premium expert support
Full Pricing Breakdown
| Model Name | Context Window | Tier 1 (Standard) | Tier 2 (Pro −30%) | Tier 3 (Ent −60%) |
|---|---|---|---|---|
| GLM-5.2 | 1M tokens | $0.30 / $1.00 | $0.21 / $0.70 | $0.12 / $0.40 |
| Qwen-3.6-27B | 256K tokens | $0.10 / $0.80 | $0.07 / $0.56 | $0.04 / $0.32 |
| DeepSeek-V4-Flash | 1M tokens | $0.10 / $0.40 | $0.07 / $0.28 | $0.04 / $0.16 |
| Kimi-K2.6 | 256K tokens | $0.10 / $0.50 | $0.07 / $0.35 | $0.04 / $0.20 |
| MiniMax-M2.7 | 200K tokens | $0.10 / $0.50 | $0.07 / $0.35 | $0.04 / $0.20 |
| MiMo-V2.5-Pro | 1M tokens | $0.20 / $0.60 | $0.14 / $0.42 | $0.08 / $0.24 |
All prices in USD per 1M tokens (input / output). Volume discounts applied automatically based on monthly usage.
Frequently Asked Questions
Tokens represent the basic unit of text processing. On average, 1,000 tokens are roughly 750 words. We charge based on total tokens processed through our router across all models.
Yes, you can upgrade at any time. Your billing will be prorated based on the remaining days in your current cycle. Downgrades take effect at the start of the next billing period.
For Standard and Pro plans, we offer a small buffer zone. If you exceed this, API requests may be throttled until an upgrade or the next billing cycle. Enterprise plans feature seamless overages.