PRICING
Models and prices
Every model on sale, in US dollars per million tokens. You pay per token used, from a prepaid balance: the tokens you send at the input price, the tokens the model writes at the output price — a reasoning model’s reasoning included.
| Model | Context | Input / 1M tokens | Output / 1M tokens | Providers, regions and data policy |
|---|---|---|---|---|
DeepSeek-V4.1-Flashdeepseek-ai/deepseek-v4.1-flashUpdated | 1M tokens | $0.081 | $0.27 |
|
GLM-5.3zai-org/glm-5.3Updated | 1M tokens | $0.50 | $2.00 |
|
GLM-5.3-Flashzai-org/glm-5.3-flashUpdated | 800K tokens | $0.02 | $0.2475 |
|
About these prices
- These are Token Engine’s own prices, the ones in effect now. An account a reseller referred may pay the reseller’s markup on top, for 12 months after it signed up: signed in, the console’s Models page shows the prices your account pays.
- A price marked “from” is the lowest: a long prompt, or another provider, may cost more, as its row says. Where a provider prices its prompt cache apart, its row says what the part of a prompt read from or written to the cache costs. Regions and data policies are as each provider has recorded them, and you can keep your requests away from the providers that do not meet your requirements (Privacy Policy §4).
- Prices exclude taxes unless stated otherwise, and a purchase may carry a fee shown at checkout (Terms §4). How retries and streams cut short are billed is in the API docs.