GLM 5.3
by Baseten · family glm · listed Aug 2026RTVW
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
Current rates USD per 1M tokens
Input$1.40
Output$4.40
Cache read$0.14
Cache write—
Against the market
On the record
- Model id
zai-org/GLM-5.3- Context window
- 1.0M tokens
- Max output
- 262K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-08-14
- Last updated
- 2026-08-14
- Provider docs
- docs.baseten.co/inference/model-apis/overview
Back of the envelope
≈
Also listed at
- Alibaba Token Planfree in · free out
- Alibaba Token Plan (China)free in · free out
- Zhipu AI Coding Planfree in · free out
- Volcengine Ark Coding Planfree in · free out
- Z.AI Coding Planfree in · free out
- SCNet Token Planfree in · free out
- Nvidiafree in · free out
- CrofAI$0.40 in · $1.40 out
- Merge Gateway$0.70 in · $2.20 out
- Vultr$0.75 in · $3.00 out
- Cortecs$0.873 in · $3.31 out
- Deep Infra$0.90 in · $4.00 out
- LLM Gateway$0.90 in · $3.00 out
- DevPass (LLM Gateway)$0.90 in · $3.00 out
- engy$0.98 in · $3.08 out