> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kymaapi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# GLM 4.7 Flash

> A fast, efficient GLM model on Kyma for cheap long-context throughput and routine workloads.

## Overview

`glm-4.7-flash` is the efficiency-oriented GLM option on Kyma. It is aimed at routine, high-volume workloads where long context and low cost matter more than flagship depth.

## Specs

| Field              | Value                                              |
| ------------------ | -------------------------------------------------- |
| Model ID           | `glm-4.7-flash`                                    |
| Best for           | Cheap long context, bulk throughput, routine tasks |
| Context window     | 203K                                               |
| Max output tokens  | 65K                                                |
| Input modalities   | Text                                               |
| Output modalities  | Text                                               |
| Tool calling       | Yes                                                |
| Structured outputs | Yes                                                |
| Prompt caching     | Yes                                                |
| Speed              | Fast                                               |
| Cost band          | Cheap                                              |
| Release stage      | Preview                                            |

## Use this when

* You need cheap long-context throughput.
* You want a faster, lighter GLM option for routine tasks.
* You are comfortable using a preview-stage model for volume work.

## Pick something else when

* You want the stronger GLM flagship: use [`glm-5.1`](/models/glm-5.1).
* You want the safer stable cheap GLM pick: use [`glm-4.5-air`](/models/glm-4.5-air).
* You need better multimodal support: use `gemini-2.5-flash` or [`kimi-k2.6`](/models/kimi-k2.6).

## Example

```python theme={null}
from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")

response = client.chat.completions.create(
    model="glm-4.7-flash",
    messages=[{"role": "user", "content": "Summarize these logs and group recurring issues by type."}]
)
```