Per-token, pay as you go. All models are 50% off list while we grow the network. The struck price is list, the green price is what you pay today.
| model | input $/1M | output $/1M | cached input $/1M |
|---|---|---|---|
| glm-5.2 | $1.40 $0.70 | $4.40 $2.20 | $0.35 $0.175 |
| qwen3.6-35b-a3b | $0.15 $0.075 | $1.00 $0.50 | $0.038 $0.019 |
Prompt-cache hits bill at the cached rate automatically, with no config and no cache_control markers. Agentic workloads (coding assistants, multi-turn tools) typically hit 90%+ cache on repeated prefixes, so effective input cost is usually far below the headline rate.
Prices are live from the billing engine. The API reports the
same numbers at https://api.engy.ai/v1/models. No minimums, no
subscription; new accounts start with a $5 credit.