# GLM-4.7

> GLM-4.7 is an open-weight language model from Zhipu AI (Z.ai), released on 22 Dec 2025. It accepts text and generates text, with a 205K-token context window and up to 131K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.40 per million input tokens and $1.75 per million output tokens (DeepInfra), across 8 providers we track. It is scheduled for retirement on 31 Dec 2026.

Source page: https://www.aimodel.directory/models/glm-4-7
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Zhipu AI (Z.ai)
- **Release date:** 22 Dec 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/zai/models/glm-4.7.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/zai/models/glm-4.7.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/zai-org/GLM-4.7)
- **License:** mit (source: Hugging Face, https://huggingface.co/zai-org/GLM-4.7)
- **Parameters:** 358B (source: Hugging Face, https://huggingface.co/zai-org/GLM-4.7)
- **Context window:** 205K (204,800 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/zai/models/glm-4.7.toml)
- **Max output:** 131K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/zai/models/glm-4.7.toml)
- **Knowledge cutoff:** Apr 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/zai/models/glm-4.7.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/zai/models/glm-4.7.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/zai/models/glm-4.7.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/zai/models/glm-4.7.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/zai/models/glm-4.7.toml)
- **Retirement date:** 31 Dec 2026 (source: OpenRouter, https://openrouter.ai/z-ai/glm-4.7)
- **Hugging Face:** zai-org/GLM-4.7 (source: Hugging Face, https://huggingface.co/zai-org/GLM-4.7)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| DeepInfra | $0.40 | $1.75 | $0.08 | 203K |
| Z.ai API | $0.60 | $2.20 | $0.11 | 205K |
| Amazon Bedrock | $0.60 | $2.20 | – | 203K |
| Baseten | $0.60 | $2.20 | $0.12 | 200K |
| Novita AI | $0.60 | $2.20 | $0.11 | 205K |
| Hugging Face Inference Providers | $0.60 | $2.20 | $0.11 | 205K |
| OpenRouter | $0.60 | $2.20 | $0.11 | 203K |
| Vercel AI Gateway | $0.60 | $2.20 | – | 200K |

## FAQ

### What is the context window of GLM-4.7?

GLM-4.7 has a context window of 204,800 tokens (205K) and can generate up to 131,072 tokens in a single response, according to models.dev.

### How much does the GLM-4.7 API cost?

Through Z.ai API, GLM-4.7 costs $0.60 per million input tokens and $2.20 per million output tokens. The lowest listed price is $0.40 input / $1.75 output through DeepInfra. Prices last verified 4 Oct 2026.

### Is GLM-4.7 open source?

GLM-4.7 is an open-weight model: its weights are published on Hugging Face as zai-org/GLM-4.7 under the mit license. Check the license terms before commercial use.

### When was GLM-4.7 released?

Zhipu AI (Z.ai) released GLM-4.7 on 22 Dec 2025, according to models.dev.

### Which providers offer GLM-4.7?

We track GLM-4.7 on 8 providers: DeepInfra, Z.ai API, Amazon Bedrock, Baseten, Novita AI, Hugging Face Inference Providers, OpenRouter, Vercel AI Gateway.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "GLM-4.7", https://www.aimodel.directory/models/glm-4-7