glm-5.3-flashChatGLM-5.3-Flash
Lightweight GLM that reads images, video, and files, $0.15 / $0.5.
GLM-5.3 Flash (glm-5.3-flash) is Zhipu’s lightweight, natively multimodal GLM-5 model: it reads text, images, video, and files, has a 1M-token context window, and always thinks (returned in reasoning_content). The official price is $0.15 input and $0.50 output per 1M tokens (cached input $0.03). Call POST /v1/chat/completions with a key that includes the GLM Official API group.
- Official price
- $0.15 / $0.50/ 1M tokensInput / output
- Context window
- 1M tokens1,000,000
Notes
- Thinking can't be turned off; reasoning_effort=none returns 400.
- Callable only with a key from the "GLM Official API" group.
Pricing
Official price in USD. Actual charge = official price × group multiplier.
- Input
- $0.15 / 1M tokens
- Cached input
- $0.03 / 1M tokens
- Output
- $0.50 / 1M tokens
Endpoints
Quick start
Replace sk-your-key with a key whose group includes this model.
curl https://api.hop-base.com/v1/chat/completions \
-H "Authorization: Bearer sk-your-key" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.3-flash",
"temperature": 1,
"top_p": 0.95,
"reasoning_effort": "max",
"messages": [
{ "role": "user", "content": "Hello, introduce yourself" }
]
}'FAQ
- Which group do I need?
- The key must include the GLM Official API group; keys without it get a 404 for glm-5.3-flash. Add the group to an existing key under API Keys in the console, or create a new key with it.
- Can I turn thinking off?
- No. reasoning_effort accepts only low, high, or max, and none returns 400. Recommended settings: reasoning_effort max, temperature 1, top_p 0.95.
- How much does it cost?
- The official price is $0.15 input, $0.03 cached input, and $0.50 output per 1M tokens; max_tokens is shared by thinking and the answer. Actual charge = official price × group multiplier.