GLM-4.7-FlashX: API pricing, providers and specs
GLM-4.7-FlashX is a text model by Zhipu AI. 5 providers serve it, from $0.40 to $0.437 /1M; the lowest price is at Z.AI.
How GLM-4.7-FlashX compares
Against the 737 text models on the site priced the same way.
- Cheap for its class: at $0.40 /1M, its lowest price undercuts 71% of comparable models (median $1.10).
- Its 200K-token context window is larger than 32% of them (median 262K), about 300 pages of text.
- 5 providers serve it; 65% of comparable models have fewer.
GLM-4.7-FlashX prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
| Z.AIOfficial | $0.07/1M | $0.40/1M | $0.01/1M | — |
| $0.072/1M | $0.40/1M | $0.01/1M | 200K | |
| Vercel AI Gateway | $0.06/1M | $0.40/1M | $0.01/1M | 200K |
| DevPass (LLM Gateway) | $0.07/1M | From$0.40/1M | $0.01/1M | — |
| ZenMux | $0.073/1M | $0.437/1M | $0.015/1M | 200K |
- Z.AIOfficial$0.40
- Ofox$0.40
- Vercel AI Gateway$0.40
- DevPass (LLM Gateway)From$0.40
- ZenMux$0.437
Specs
- Type
- Text
- Maker
- Zhipu AI
- Inputs
- Text
- Outputs
- Text
- Context
- 200K≈ 300 pages of text
- Max output
- 128K
- Capabilities
- Prompt caching, Reasoning, Tool calling
- Released
- Jan 19, 2026
- License
- proprietary
- Open weights
- No, API only
Alternatives to GLM-4.7-FlashX
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| $0.40/1M | 200K | — | 5 | |
| $0.50/1M | 262K | 1591 | 33 | |
| GPT-6 Luna | $0.40/1M | 1.05M | 1578 | 28 |
| $1/1M | 127K | — | 9 | |
| Claude Haiku 5.5 | $0.30/1M | 1M | 1585 | 27 |
| $0.696/1M | 1.05M | 1625 | 21 | |
| $0.376/1M | 262K | 1628 | 5 | |
| $0.17/1M | 1.05M | — | 26 | |
| $0.294/1M | 1.05M | — | 26 |
More from Zhipu AI
GLM-4.7-FlashX FAQ
Z.AI, at $0.40 /1M. 5 providers serve GLM-4.7-FlashX; the table above lists every one with its price.
GLM-4.7-FlashX reads up to 200K tokens per request and writes up to 128K.
No. GLM-4.7-FlashX is only available through an API; Zhipu AI does not publish its weights.
5 API providers serve GLM-4.7-FlashX. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us