# GLM 5.3 API Pricing

As of October 10, 2026, GLM 5.3 costs $1.40 per 1M input tokens and $4.40 per 1M output tokens on Z.ai, with cache reads at $0.26 and cache writes at $0 per 1M tokens. Across 12 providers on LiteLLM, the input price ranges from $0.98 to $1.40. It has a 1,000,000-token context window and returns up to 128,000 tokens per response.

- Page: https://models.litellm.ai/models/glm-5.3
- Lab: Z.ai
- LiteLLM model name: `zai/glm-5.3`
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Added to LiteLLM: August 27, 2026
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Z.ai | `zai/glm-5.3` | $1.40 | $4.40 | $0.26 | – | – | 1M |
| AIHubMix | `aihubmix/glm-5.3` | $1.127 | $3.944 | $0.2817 | – | – | 1M |
| Baseten | `baseten/zai-org/GLM-5.3` | $1.40 | $4.40 | $0.14 | – | – | 1M |
| Databricks | `databricks/databricks-glm-5-3` | $1.40 | $4.40 | $0.26 | – | – | 1M |
| Fireworks AI | `fireworks_ai/accounts/fireworks/models/glm-5p3` | $1.40 | $4.40 | $0.26 | – | – | 1M |
| Fireworks AI | `fireworks_ai/glm-5p3` | $1.40 | $4.40 | $0.26 | – | – | 1M |
| FriendliAI | `friendliai/zai-org/GLM-5.3` | $1.26 | $3.96 | $0.234 | – | – | 1M |
| Nebius AI Studio | `nebius/zai-org/GLM-5.3` | $1.40 | $4.40 | – | – | – | 1M |
| Novita AI | `novita/zai-org/glm-5.3` | $1.40 | $4.40 | $0.26 | – | – | 1M |
| Perplexity | `perplexity/perplexity/glm-5.3` | $1.40 | $4.40 | $0.26 | – | – | – |
| Sail | `sail/zai-org/GLM-5.3` | $0.98 | $3.08 | $0.18 | – | – | 1M |
| Together AI | `together_ai/zai-org/GLM-5.3` | $1.40 | $4.40 | $0.26 | – | – | 1M |
| Amazon Bedrock (Global cross-region) | `global.zai.glm-5.3` | $1.68 | $5.28 | $0.312 | – | – | 1M |
| Amazon Bedrock (US cross-region) | `us.zai.glm-5.3` | $1.848 | $5.808 | $0.3432 | – | – | 1M |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- Z.ai: $5.00
- Sail: $3.50
- AIHubMix: $4.226
- FriendliAI: $4.50

100 long-document requests with 100,000 input and 2,000 output tokens each:

- Z.ai: $14.88
- Sail: $10.42
- AIHubMix: $12.06
- FriendliAI: $13.39

## Features

Supported: Function calling, Parallel tool calls, Structured output, Image input, Reasoning, Prompt caching, Web search.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="zai/glm-5.3",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does GLM 5.3 cost?

GLM 5.3 costs $1.40 per 1M input tokens and $4.40 per 1M output tokens on Z.ai, with cache reads at $0.26 and cache writes at $0 per 1M tokens. Across 12 providers on LiteLLM, the input price ranges from $0.98 to $1.40.

### What is the context window of GLM 5.3?

GLM 5.3 has a 1,000,000-token context window and returns up to 128,000 tokens per response.

### Which providers offer GLM 5.3?

GLM 5.3 is available from 12 providers through LiteLLM: Z.ai, AIHubMix, Baseten, Databricks, Fireworks AI, FriendliAI, Nebius AI Studio, Novita AI, Perplexity, Sail, Together AI and Amazon Bedrock. The lowest price is on Sail.

### How do I call GLM 5.3 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="zai/glm-5.3", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does GLM 5.3 support?

GLM 5.3 supports function calling, parallel tool calls, structured output, image input, reasoning, prompt caching and web search.

### When did LiteLLM add GLM 5.3?

GLM 5.3 was added to LiteLLM's model price file on August 27, 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json