# Glm Flash (latest)

> Always resolves to the newest live Glm Flash model — currently GLM-5.3-Flash (z-ai/glm-5.3-flash). GLM-5.3-Flash is a native multimodal model from Z.ai (320B-A18B, MIT License, 1M-token context). It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.

**ID**: `z-ai/glm-flash-latest`  
**Creator**: Zhipu AI  
**Category**: text  
**Context**: 1M tokens  
**Family alias**: always resolves to the newest live family member — currently [`z-ai/glm-5.3-flash`](https://anyrouter.dev/model/z-ai/glm-5.3-flash). Specs below are z-ai/glm-5.3-flash's.  
**Fallback order**: `z-ai/glm-5.3-flash` → `z-ai/glm-4.7-flash`  
**Input**: $0.15/M  
**Output**: $0.50/M  
**Released**: 2026-08-26  
**Web page**: https://anyrouter.dev/model/z-ai/glm-flash-latest

**Input modalities**: text, image, video  
**Output modalities**: text  

**Tokenizer**: GLM

**Capabilities**: chat, streaming, reasoning, coding, agentic, function-calling, vision

**Supported parameters**: max_tokens, temperature, top_p, top_k, tools, tool_choice, response_format, reasoning, include_reasoning, reasoning_effort

**Aliases**: `zai-org/glm-5.3-flash`

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "z-ai/glm-flash-latest",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| hue | $0.15/M | $0.50/M |
| aihubmix-byok | $0 | $0 |
| aihubmix-byok | $0 | $0 |
| opencode-zen-byok | $0 | $0 |
| commandcode-byok | $0 | $0 |
| hermes-agent | $0.15/M | $0.50/M |
| hermes-agent-byok | $0 | $0 |
| openrouter-byok | $0 | $0 |
| venice-byok | $0 | $0 |
| cline-byok | $0 | $0 |

## Source

- Upstream docs: https://z.ai/blog/glm-5.3-flash