GLM-5-Turbo
Model overview
glm-5-turbo
Production GLM-5 API model optimized for lower-latency agent and coding workflows.
general LLMreasoningcodinglong contextagentchatcode generationsoftware engineering agententerprise access
Representative version
glm-5-turbo
| Company | Zhipu AI |
|---|---|
| Release | 2026-03-15 |
| Release type | Model release |
| Parameters | Not disclosed |
| Architecture | Not disclosed |
| Context | 200,000 |
| Input modalities | text |
| Output modalities | text / code / tool_call |
| Tool use / function calling | Confirmed: Tool use, Function calling |
| Structured output / reasoning | Confirmed: Reasoning |
| Vision / audio / video | Vision: Not disclosed; Audio: Not disclosed; Video: Not disclosed |
| Open weights / License | No open weights currently / weight license not disclosed zhipu-glm-5-turbo-current · License not applicable |
| Vendor API | Available GLM-5-Turbo official guidezhipu-glm-5-turbo-current · 2026-03-15 |
| OpenRouter | OpenRouter listed |
| Pricing | OpenRouter · 2026-08-11: $1.2 / $4 input / output, per 1M tokens |
| Benchmark | No reliable public source |
| Public signals | No reliable public source |
| Use cases | Low-latency agents / coding and review / Enterprise API workloads / assistant chat |
| Claim evidence | Release event / Model specificationsGLM-5-Turbo official guideglm-5-turbo · 2026-03-15 · GLM-5-Turbo · glm-5-turbo OpenRouter context / capabilities / pricingOpenRouter public models APIz-ai/glm-5-turbo · 2026-08-11T06:28:09.895Z |
OpenRouter
Pricing / context / availability
| OpenRouter | OpenRouter listed |
|---|---|
| OpenRouter listing | z-ai/glm-5-turbo |
| Mapped version | glm-5-turbo zhipu-glm-5-turbo-current |
| Pricing | OpenRouter · 2026-08-11: $1.2 / $4 input / output, per 1M tokens |
| Context | 202752 |
| Speed/Latency | No reliable public source |
| Snapshot time | 2026-08-11T06:28:09.895Z |
| Source | View source |
Verified limitations
Usage boundaries
- Closed API model; parameter counts are not disclosed.
Missing public information
Public information not yet available
Parameter scale not disclosedNo reliable benchmark sourceNo public model-card activity countersNo linkable model-specific reviewSpeed/latency not disclosed