Pricing
Simple, per-token pricing
All token prices are per 1M tokens. No subscriptions, no minimums.
| Model | Input 1M | Output 1M | Context | Cache-read 1M | Cache-write 1M | Status |
|---|---|---|---|---|---|---|
| glm-5.1 | $0.950 | $3.50 | 200K | $0.250 | — | Available |
| kimi-k2.6 | $0.750 | $3.50 | 256K | $0.150 | — | Available |
Token prices are per 1M tokens. Cache-read is the discounted rate for cached prompt reads; cache-write is charged when prompt prefixes are written to cache.
Need volume pricing or a private deployment? Talk to us.