GLM 5.3 Flash is available through Amanai as amanai/glm-5.3-flash.
What changed
GLM 5.3 Flash joins the public model catalog, dashboard calculator, status page, documentation, and Coding CLI model picker. The previous anonymous preview alias has been retired from those surfaces.
Capabilities
GLM 5.3 Flash accepts text, image, and video input and produces text output. Like GLM 5.3, it supports a 1M-token context window, up to 128k output tokens, streaming, tool calling, structured output, and selectable reasoning effort.
Supported reasoning choices are auto, low, medium, high, xhigh, and max.
Pricing
Each Pricing Engine v3 multiplier is exactly half the corresponding GLM 5.3 multiplier.
| Component | GLM 5.3 Flash | GLM 5.3 |
|---|---|---|
| Input | 2.8 | 5.6 |
| Output | 14.0 | 28.0 |
| Cached input | 0.7 | 1.4 |
Using GLM 5.3 Flash
Existing Amanai API keys work without configuration changes:
curl https://api.amanai.dev/v1/chat/completions -H "Authorization: Bearer $AMANAI_API_KEY" -H "Content-Type: application/json" -d '{"model": "amanai/glm-5.3-flash","messages":[{"role": "user","content": "Hello"}]}'