GLM-5-Turbo
by TensorX · family glm · listed Mar 2026RT
Faster GLM-5 lane for coding agents that need lower latency
Current rates USD per 1M tokens
Input$1.20
Output$4.00
Cache read$0.30
Cache write$1.50
Against the market
On the record
- Model id
z-ai/glm-5-turbo- Context window
- 203K tokens
- Max output
- 131K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-03-16
- Last updated
- 2026-03-16
- Provider docs
- docs.tensorx.ai/
Back of the envelope
≈
Also listed at
- Z.AI Coding Planfree in · free out
- Zhipu AI Coding Planfree in · free out
- 302.AI$0.72 in · $3.20 out
- ZenMux$0.88 in · $3.48 out
- CrossModel$0.90 in · $3.70 out
- Cortecs$1.19 in · $3.96 out
- NanoGPT$1.20 in · $4.00 out
- Impossibl$1.20 in · $4.00 out
- LLM Gateway$1.20 in · $4.00 out
- Vercel AI Gateway$1.20 in · $4.00 out
- DevPass (LLM Gateway)$1.20 in · $4.00 out
- Kilo Gateway$1.20 in · $4.00 out
- Merge Gateway$1.20 in · $4.00 out
- OpenRouter$1.20 in · $4.00 out
- Ofox$1.20 in · $4.00 out