# GLM 5.3 Flash

> Zhipu's newest Flash — MIT-licensed, multimodal, latency/cost-optimized successor to GLM 4.7 Flash. ~1.3M context, vision.

Human version: https://kymaapi.com/models/glm-5.3-flash
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `glm-5.3-flash`: pass this as `model` in the request body
- **Creator**: Zhipu AI
- **Released**: 2026-08-26
- **Context window**: 1M tokens
- **Max output**: 66K tokens per response, a hard ceiling, not a default
- **Price**: $0.101 in / $0.338 out per 1M, prompt caching supported (cached rate not published)
- **Capabilities**: tools, vision, reasoning, caching

## Call it

```bash
curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "glm-5.3-flash", "messages": [{"role": "user", "content": "Hello"}]}'
```

## See also

- All models: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md
- Other models by Zhipu AI: https://kymaapi.com/models?q=Zhipu%20AI