GLM-5.3-Flash
by Zhipu AI Coding Plan · family glm · listed Aug 2026RTV
Native multimodal GLM model for efficient coding and long-horizon agent tasks
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache readfree
Cache writefree
Against the market
On the record
- Model id
glm-5.3-flash- Context window
- 1M tokens
- Max output
- 131K tokens
- Input modalities
- text, image, video, pdf
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-08-26
- Last updated
- 2026-08-26
- Provider docs
- docs.bigmodel.cn/cn/coding-plan/overview
Back of the envelope
≈
Also listed at
- Z.AI Coding Planfree in · free out
- NanoGPT$0.075 in · $0.25 out
- OpenRouter$0.075 in · $0.25 out
- Z.AI$0.075 in · $0.25 out
- OpenCode Go$0.075 in · $0.25 out
- Merge Gateway$0.075 in · $0.25 out
- Zhipu AI$0.075 in · $0.25 out
- Kilo Gateway$0.075 in · $0.25 out
- Requesty$0.135 in · $0.45 out
- Cloudflare Workers AI$0.15 in · $0.50 out
- Deep Infra$0.15 in · $0.50 out
- Hugging Face$0.15 in · $0.50 out
- LLM Gateway$0.15 in · $0.50 out
- Vercel AI Gateway$0.15 in · $0.50 out
- Eden AI$0.15 in · $0.50 out