Zhipu AI/ GLM
GLM-5.2
zhipuai/glm/5-2
Open flagship GLM for long-horizon coding agents and million-token context work
Released
2026-06-13
Context window
1M
Max output
131K
Weights
Open weight
Modalities
Input
Text
Output
Text
Identity
- Version
- glm-5.2
- Aliases
- GLM-5.2
Resources
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| Zhipu AI | glm-5.2 | custom | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $1.4/M · cache read $0.26/M output $4.4/M · cache write $0/M | Yes |
| GreenPT | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $1.254/M output $5.016/M | Yes |
| OpenCode Go | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $1.4/M · cache read $0.26/M output $4.4/M | Yes |
| Vivgrid | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $1.2/M · cache read $0.3/M output $4.2/M | Yes |
| Zhipu AI Coding Plan | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $0/M · cache read $0/M output $0/M · cache write $0/M | Yes |
| CrofAI | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $0.5/M · cache read $0.08/M output $2.2/M | Yes |
| LLM Gateway | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $0.8/M · cache read $0.16/M output $2.55/M · cache write $0/M | Yes |
| Kenari | glm-5-2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0/M output $0/M | Yes |
| OpenCode Zen | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $1.4/M · cache read $0.26/M output $4.4/M | Yes |
| DInference | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $1.25/M output $3.89/M | Yes |
| UnoRouter | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $1.6001/M output $5.0288/M | Yes |
| UnoRouter | glm-5.2:free | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0/M output $0/M | Yes |
| EmpirioLabs AI | glm-5-2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $1.4/M · cache read $1.4/M output $4.4/M | Yes |
| Alibaba Token Plan | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $0/M · cache read $0/M output $0/M · cache write $0/M | Yes |
| Wafer | GLM-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $1.2/M · cache read $0.2/M output $4.1/M · cache write $0/M | Yes |
| Scaleway | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $1.8/M output $5.5/M | Yes |
| DigitalOcean | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $1.05/M · cache read $0.21/M output $4.4/M | Yes |
| Model Oracle AI | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | - | Yes |
| Neuralwatt | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $1.45/M · cache read $0.3625/M output $4.5/M | Yes |
| AIHubMix | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $1.1268/M · cache read $0.2817/M output $3.9438/M | Yes |
| routing.run | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $0.8/M output $2.4/M | Yes |
| Z.AI Coding Plan | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $0/M · cache read $0/M output $0/M · cache write $0/M | Yes |
| Charm Hyper | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $1.4/M · cache read $0.28/M output $4.4/M | Yes |
| Alibaba (China) | glm-5.2 | custom | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $1.1/M · cache read $0.275/M output $3.851/M · cache write $0/M | Yes |
| Tinfoil | glm-5-2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $1.5/M · cache read $0.375/M output $5.25/M | Yes |
| Alibaba Token Plan (China) | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $0/M · cache read $0/M output $0/M · cache write $0/M | Yes |
| Ollama Cloud | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | - | Yes |
| Z.AI | glm-5.2 | custom | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $1.4/M · cache read $0.26/M output $4.4/M · cache write $0/M | Yes |
| Cortecs | glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $1.44/M · cache read $0.39/M output $4.53/M | Yes |
| OpenRouter | z-ai/glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output, Default reasoning: high, Hugging Face: zai-org/GLM-5.2 | input $0.6286/M · cache read $0.11674/M output $1.9756/M | Yes |
| CrossModel | z-ai/glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $1.2/M · cache read $0.3/M output $4.4/M · cache write $1.2/M | Yes |
| Nvidia | z-ai/glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $0/M output $0/M | Yes |
| Ambient | z-ai/glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $1.05/M · cache read $0.2/M output $4.4/M · cache write $0/M | Yes |
| ZenMux | z-ai/glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $1.4/M · cache read $0.26/M output $4.5/M | Yes |
| Ofox | z-ai/glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $1.4/M · cache read $0.26/M output $4.4/M | Yes |
| TensorX | z-ai/glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $1.5/M · cache read $0.375/M output $4.5/M | Yes |
| Kilo Gateway | z-ai/glm-5.2 | openai_chat | 1M | 131K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $1.4/M · cache read $0.26/M output $4.4/M | Yes |
Capabilities
ReasoningTool callStructuredTemperatureOpen weight
Official price
input $1.4/M · cache read $0.26/M
output $4.4/M · cache write $0/M