GLM 5.3 is now available through Amanai as amanai/glm-5.3.
What changed
The new model is available anywhere Amanai models can be selected: Chat Completions, Anthropic Messages, Responses, the dashboard calculator, status page, documentation, and Coding CLI model catalogs.
Capabilities
GLM 5.3 uses the same conservative public capability envelope as GLM 5.2: a 1M-token context window, up to 128k output tokens, streaming, tool calling, and selectable reasoning effort.
Supported reasoning choices are auto, low, medium, high, xhigh, and max.
Pricing
GLM 5.3 is priced identically to GLM 5.2 under Pricing Engine v3.
| Component | Multiplier |
|---|---|
| Input | 5.6 |
| Output | 28.0 |
| Cached input | 1.4 |
Using GLM 5.3
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","messages":[{"role": "user","content": "Hello"}]}' Availability
GLM 5.3 is available through Amanai's managed production routing. Direct text, reasoning, and forced tool-call probes passed before the catalog addition.