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

# GLM 5.3

> Text, code, reasoning, and tool use with a 393,216-token context window on Corvex Token Factory.

GLM 5.3 is Z.AI's open-weight model for text, code, reasoning, and tool use. Token Factory serves it with a 393,216-token context window.

Model ID: `zai-org/GLM-5.3`

## Specifications

* **Context window:** 393,216 tokens (384K)
* **Maximum output:** 393,216 tokens, subject to the remaining context space
* **Input:** text
* **Output:** text
* **Capabilities:** chat, reasoning, coding, tool use, JSON mode, structured output
* **Sampling parameters:** `temperature`, `top_p`, `stop`, `max_tokens`
* **License identifier:** `glm-5.3`
* **Model repository:** [zai-org/GLM-5.3](https://huggingface.co/zai-org/GLM-5.3)

Input and reserved output share the context window: `input_tokens + max_tokens` must fit within 393,216 tokens. Image input is not supported.

## Pricing

| Direction | Rate (USD)         |
| --------- | ------------------ |
| Input     | \$1.40 / 1M tokens |
| Output    | \$4.40 / 1M tokens |

During the free Alpha, the dashboard reports equivalent usage value but does not charge these rates. See [Pricing](/pricing).

## Send a request

```bash theme={null}
curl https://api.tokenfactory.corvex.cloud/v1/chat/completions \
  -H "Authorization: Bearer ${CORVEX_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/GLM-5.3",
    "messages": [
      {"role": "user", "content": "Refactor this Go function and explain each change."}
    ]
  }'
```

Set `stream: true` for streamed responses. See the [API reference](/api-reference/openapi) for request fields and the [integration guides](/integrations/overview) for SDKs and developer tools.

[Open GLM 5.3 in the Token Factory playground](https://tokenfactory.corvex.cloud/app/playground/zai-org/GLM-5.3).