D
GLM 4.7 Flash
GLM 4.7 Flash, a language model from DeepInfra.
modelOverride: { model: "glm-4.7-flash" }
Z.ai·served viaPricing
- Input
- $0.060 / 1M
- Output
- $0.40 / 1M
Specifications
- Context window
- 202,752 tokens
- Max output
- 16,384 tokens
- Released
- January 2026
- Model string
- zai-org/GLM-4.7-Flash
- Capabilities
- FastLow cost
Parameters
Model options, passed in
modelOverride.config.| Parameter | Type | Default | Range / options |
|---|---|---|---|
reasoning_effort | Select | medium | nonelowmediumhigh |
Use this model
await mindstudio.generateText({ message: "...", modelOverride: { model: "glm-4.7-flash", config: { reasoning_effort: "medium", }, }, });