# GLM-5.1

> GLM-5.1 is a Z.ai model with major gains in coding, built to work on long-horizon tasks independently.

## Key facts

- Model author: Z.ai
- Input: $0.8163 per 1M tokens (starting tier)
- Output: $3.2653 per 1M tokens (starting tier)
- Cached input: $0.1769 per 1M tokens
- Context window: 200,000 tokens
- Maximum output: 128,000 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools
- Released: 2026-04-07
- Model IDs: `baidu/glm-5.1`, `jd/glm-5.1`, `z-ai/glm-5.1`
- Model page: https://www.realrelay.ai/model/z-ai/glm-5.1

## Overview

GLM-5.1 is a text model from Z.ai that delivers a major leap in coding capability, with particularly significant gains on long-horizon tasks. Z.ai says it can work independently and continuously on a single task for hours, rather than in short, minute-level interactions. It supports reasoning, structured output and tool calling.

GLM-5.1 has a 200K-token context window and can generate up to 128K output tokens. It accepts text input and returns text output. It was released on April 7, 2026.

## Capabilities

GLM-5.1 supports reasoning, structured output and tool calling. Z.ai lists coding proficiency and independent work on one task over long periods as its main strengths.

## Pricing

GLM-5.1 starts from $0.8163 per 1M input tokens and from $3.2653 per 1M output tokens. Cache reads start from $0.1769 per 1M tokens. The prices shown are the starting tier.

GLM-5.1 is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GLM-5.1 for long-running coding agents that take a task, work through it independently for hours and keep calling tools until the code is written, tested and fixed.

It also suits other long-horizon jobs that need steady progress without frequent human prompts, such as multi-stage refactors, with a 200K-token context window to keep the history in view.

## Call it

OpenAI-compatible chat completions:

```bash
curl https://www.realrelay.ai/v1/chat/completions \
  -H "Authorization: Bearer $REALRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "z-ai/glm-5.1", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GLM-5.1?

GLM-5.1 is a Z.ai model with major gains in coding, built to work on long-horizon tasks independently.

### How much does GLM-5.1 cost?

GLM-5.1 starts from $0.8163 per 1M input tokens and from $3.2653 per 1M output tokens, with cache reads from $0.1769 per 1M tokens.

### What is the context window of GLM-5.1?

GLM-5.1 has a 200K-token context window and can generate up to 128K output tokens.

### What inputs and outputs does GLM-5.1 support?

GLM-5.1 accepts text input and returns text output.

### Does GLM-5.1 support tool calling?

Yes. GLM-5.1 supports tool calling, along with reasoning and structured output.

### When was GLM-5.1 released?

GLM-5.1 was released on April 7, 2026.

### How do I call GLM-5.1 via the API?

Send requests to RealRelay's OpenAI-compatible API and use the model ID z-ai/glm-5.1.