What this model supports
ReasoningYes
Tool callingYes
Structured outputNo
AttachmentsNo
Temperature controlYes
Open weightsYes
- Creator
- Zhipu AI
- Family
- glm
- Modalities
- Text
- License
- Not documented
- Release date
- 2025-12-22
- Model ID
zhipuai/glm-4.7
GLM-4.7
zhipuai/glm-4.7Mature GLM model for dependable coding, reasoning, and structured agent tasks
Input modalities
Output modalities
Source-linkedglmOpen weightsReleased 2025-12-22
Context window204.8K
Maximum output131.072K
Provider offers24
Knowledge cutoff2025-04
Market availability
Report price →Provider pricing
| Provider | Provider model ID | Context | Input / 1M | Output / 1M | Cached / 1M | Features | All pricing |
|---|---|---|---|---|---|---|---|
 Alibaba Coding Plan (China) | glm-4.7 | 202.752K | $0 | $0 | $0 | R T · | View{
"cache_read": 0,
"cache_write": 0,
"input": 0,
"output": 0
} |
 Z.AI Coding Plan | glm-4.7 | 204.8K | $0 | $0 | $0 | R T · | View{
"cache_read": 0,
"cache_write": 0,
"input": 0,
"output": 0
} |
 Zhipu AI Coding Plan | glm-4.7 | 204.8K | $0 | $0 | $0 | R T · | View{
"cache_read": 0,
"cache_write": 0,
"input": 0,
"output": 0
} |
 Alibaba Coding Plan | glm-4.7 | 202.752K | $0 | $0 | $0 | R T · | View{
"cache_read": 0,
"cache_write": 0,
"input": 0,
"output": 0
} |
 KUAE Cloud Coding Plan | GLM-4.7 | 204.8K | $0 | $0 | $0 | R T · | View{
"cache_read": 0,
"cache_write": 0,
"input": 0,
"output": 0
} |
 Meganova | zai-org/GLM-4.7 | 202.752K | $0.2 | $0.8 | — | R T · | View{
"input": 0.2,
"output": 0.8
} |
 CrofAI | glm-4.7 | 202.752K | $0.25 | $1.1 | $0.05 | R T · | View{
"cache_read": 0.05,
"cache_write": 0,
"input": 0.25,
"output": 1.1
} |
 LLM Gateway | glm-4.7 | 204.8K | $0.38 | $1.98 | $0.19 | R T · | View{
"cache_read": 0.19,
"cache_write": 0,
"input": 0.38,
"output": 1.98
} |
 OpenRouter | z-ai/glm-4.7 | 202.752K | $0.4 | $1.75 | $0.08 | R T S | View{
"cache_read": 0.08,
"input": 0.4,
"output": 1.75
} |
 Deep Infra | zai-org/GLM-4.7 | 202.752K | $0.4 | $1.75 | $0.08 | R T S | View{
"cache_read": 0.08,
"input": 0.4,
"output": 1.75
} |
 DInference | glm-4.7 | 200K | $0.45 | $1.65 | — | R T · | View{
"input": 0.45,
"output": 1.65
} |
 CrossModel | z-ai/glm-4.7 | 200K | $0.47 | $2.16 | $0.1 | R T · | View{
"cache_read": 0.1,
"cache_write": 0.47,
"input": 0.47,
"output": 2.16,
"tiers": [
{
"cache_read": 0.13,
"cache_write": 0.62,
"input": 0.62,
"output": 2.47,
"tier": {
"size": 32000,
"type": "context"
}
}
]
} |
 Abacus | zai-org/GLM-4.7 | 204.8K | $0.6 | $2.2 | — | R T · | View{
"input": 0.6,
"output": 2.2
} |
 OrcaRouter | z-ai/glm-4.7 | 204.8K | $0.6 | $2.2 | $0.11 | R T · | View{
"cache_read": 0.11,
"cache_write": 0,
"input": 0.6,
"output": 2.2
} |
 Z.AI | glm-4.7 | 204.8K | $0.6 | $2.2 | $0.11 | R T · | View{
"cache_read": 0.11,
"cache_write": 0,
"input": 0.6,
"output": 2.2
} |
 OpenCode Zen | glm-4.7 | 204.8K | $0.6 | $2.2 | $0.1 | R T · | View{
"cache_read": 0.1,
"input": 0.6,
"output": 2.2
} |
 Amazon Bedrock | zai.glm-4.7 | 204.8K | $0.6 | $2.2 | — | R T S | View{
"input": 0.6,
"output": 2.2
} |
 Jiekou.AI | zai-org/glm-4.7 | 204.8K | $0.6 | $2.2 | — | R T S | View{
"input": 0.6,
"output": 2.2
} |
 Vertex | zai-org/glm-4.7-maas | 200K | $0.6 | $2.2 | — | R T S | View{
"input": 0.6,
"output": 2.2
} |
 Hugging Face | zai-org/GLM-4.7 | 204.8K | $0.6 | $2.2 | $0.11 | R T · | View{
"cache_read": 0.11,
"input": 0.6,
"output": 2.2
} |
 NovitaAI | zai-org/glm-4.7 | 204.8K | $0.6 | $2.2 | $0.11 | R T S | View{
"cache_read": 0.11,
"input": 0.6,
"output": 2.2
} |
 Zhipu AI | glm-4.7 | 204.8K | $0.6 | $2.2 | $0.11 | R T · | View{
"cache_read": 0.11,
"cache_write": 0,
"input": 0.6,
"output": 2.2
} |
 Merge Gateway | zai/glm-4.7 | 204.8K | $0.6 | $2.2 | $0.11 | R T · | View{
"cache_read": 0.11,
"cache_write": 0,
"input": 0.6,
"output": 2.2
} |
 Moark | GLM-4.7 | 204.8K | $3.5 | $14 | — | R T · | View{
"input": 3.5,
"output": 14
} |
Published benchmark results
SWE-Bench Verified
vs top 8 models
Terminal Bench 2.0
vs top 1 models