# GLM-5.3 API on Boundless

> Z.ai's open-weight model for long-running coding agents that need a million-token context, served on Boundless.

Page: https://boundless.network/models/glm-5.3

## Price per 1M tokens

| Input | Cached input | Output |
| --- | --- | --- |
| $1.12 | $0.14 | $3.52 |

## GLM-5.3 at a glance

GLM-5.3 is Z.ai's 753B-parameter mixture-of-experts flagship, with sparse attention that keeps long prompts affordable. It always thinks, with reasoning effort you can set to low, high or max.

Source: https://inference.boundless.network/models/glm-5.3

- Developer: Z.ai
- Context window: 1M tokens
- Input: Text
- Capabilities: Reasoning, tool use

## GLM-5.3 API pricing by provider

| Provider | Input | Cached | Output | Context |
| --- | --- | --- | --- | --- |
| Boundless | $1.12 | $0.14 | $3.52 | 1M |
| Z.ai (model creator) | $1.40 | $0.26 | $4.40 | 1M |
| DeepInfra | $0.56 | $0.13 | $2.50 | 1M |
| Baseten | $1.40 | $0.14 | $4.40 | 1M |
| Together | $1.40 | $0.26 | $4.40 | 1M |
| Fireworks | $1.40 | $0.26 | $4.40 | 1M |

Prices per 1M tokens. Source: OpenRouter (https://openrouter.ai/z-ai/glm-5.3)

## Switch with a base URL and a key

1. Get an API key: Sign up in the console and create a key. No sales call. https://inference.boundless.network/api-keys
2. Point your SDK at Boundless: Change the base URL and key. For Anthropic SDKs, drop the /v1 and set max_tokens.

```bash
curl https://api.inference.boundless.network/v1/chat/completions \
  -H "Authorization: Bearer $BOUNDLESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3",
    "messages": [{
      "content": "Say hello",
      "role": "user"
    }]
  }'
```

More examples: https://inference.boundless.network/docs/quickstart

## FAQ

### How much does GLM-5.3 cost on Boundless?

$1.12 per 1M input tokens, $0.14 per 1M cached input tokens and $3.52 per 1M output tokens, billed from prepaid credits. Every response includes exact token counts, so any charge can be checked against these prices.

### What is GLM-5.3's context window on Boundless?

1M tokens, shared by the prompt and the reply. max_tokens can go up to that limit.

### Does GLM-5.3 support tool calling?

Yes. GLM-5.3 supports tool use and reasoning.

### Can I control how much GLM-5.3 reasons?

Yes. Set reasoning_effort to low, high or max. GLM-5.3 always thinks, so size max_tokens for both the thinking and the reply.

### What are the rate limits?

Each team has caps on tokens per minute, requests per minute and concurrent requests, shown on the usage page. Cached input doesn't count against them, and support can raise them for your team.

### Does Boundless store my prompts or outputs?

No. Boundless never stores prompts or outputs and never trains on them. It keeps only what billing needs: token counts, model, timestamp and cost.

### Can Boundless help me decide if GLM-5.3 fits my workload?

Yes. We test it against your current model on your own prompts, then tune and run it to your targets.

## Links

- Try it in the playground: https://inference.boundless.network/playground?model=glm-5.3
- Talk to an engineer: https://boundless.network/#get-access
- All models: https://boundless.network/models