Post-Cutoff.com
  1. Home
  2. Models
  3. GLM-5.3

GLM-5.3

Zhipu AI (Z.ai)currentreasoning-llmGLM-5open weights

Z.ai flagship. Text-only input. Migration: requests with thinking disabled fail - set enabled + reasoning_effort low. Coding Plan base URL is https://api.z.ai/api/coding/paas/v4. Release day not verified (OpenRouter 2026-08-18, HF 2026-08-25). GLM-5.2 (same price, MIT weights) still listed.

Context window
1,000,000 tokens
Max output
128,000 tokens
Input
text
Output
text
License
glm-5.3 (custom)
Pricing
input: $1.4 · output: $4.4 · cache read: $0.26 (per 1M tokens (USD)) source
Verified
2026-09-29

How to call it

ProviderModel idEndpoint / URLDocs
Z.ai APIglm-5.3https://api.z.ai/api/paas/v4docs
Z.ai API (Anthropic format)glm-5.3https://api.z.ai/api/anthropicdocs
Alibaba Cloud Model StudioZHIPU/GLM-5.3—docs
OpenRouterz-ai/glm-5.3openrouter.ai/z-ai/glm-5.3—
Hugging Face—huggingface.co/zai-org/GLM-5.3—
Web app—chat.z.ai—

Notable capabilities (4)

Z.ai's top model for long-horizon software engineering, terminal agents and security research; 1M context, 128K output.

curl https://api.z.ai/api/paas/v4/chat/completions \
 -H "Authorization: Bearer $ZAI_API_KEY" -H "Content-Type: application/json" \
 -d '{"model":"glm-5.3","thinking":{"type":"enabled"},"reasoning_effort":"max","messages":[{"role":"user","content":"Hello"}]}'

Sources: https://docs.z.ai/guides/llm/glm-5.3 · https://docs.z.ai/guides/overview/pricing · https://huggingface.co/zai-org/GLM-5.3

Other Zhipu AI (Z.ai) models

GLM-5.3-Flash / FlashX · GLM-4.6V