GLM-4.7
GLM-4.7 is Zhipu's flagship text-only model with a 128K token context window, designed for complex reasoning and tool-calling applications.
API Pricing
Cheapest on Deep Infra — 85% below avg| Provider | Input / 1M | Output / 1M | Cached / 1M |
|---|---|---|---|
| $0.060 | $0.400 | $0.010 | |
| $0.070 | $0.400 | - | |
| $0.400 | $1.75 | $0.080 | |
| $0.450 | $2.00 | - | |
| $0.964 | $2.46 | $0.482 |
Prices updated daily. Last check: Jul 13, 2026
Performance & Benchmarks
Source: Artificial Analysis →Reasoning & Knowledge
- MMLU-Pro79.4%
- GPQA Diamond66.4%
- Humanity's Last Exam6.1%
Coding
- LiveCodeBench56.2%
- SciCode35.4%
Math
- AIME 202548.0%
Agentic & Tool Use
- Terminal-Bench Hard30.3%
- τ²-bench94.2%
Instruction & Long Context
- IFBench54.6%
- Long-Context Reasoning36.3%
Benchmarks measured Jul 2026. Scores are independent evaluations, not vendor-reported.
Model Details
General
- Creator
- Zhipu
- Family
- GLM
- Tier
- Flagship
- Context Window
- 128K
- Modalities
- Text
Capabilities
- Tool Calling
- Yes
- Open Source
- No
- Subtypes
- Chat Completion
Strengths & Limitations
Strengths
- 128,000 token context window for processing lengthy documents
- Tool calling support enables integration with external APIs and services
- 87.72 tokens per second output speed for responsive interactions
- Flagship-tier capabilities for complex reasoning tasks
- Part of established GLM model family with proven track record
- Competitive inference speed for real-time applications
- Supports chat completion format for conversational applications
Limitations
- Text-only input support - no image or multimodal capabilities
- Proprietary model with no open source availability
- 1,380ms time to first token is slower than some competitors
- Smaller context window compared to some flagship models with 200K+ tokens
- Limited benchmark data available for comprehensive evaluation
Key Features
About GLM-4.7
Common Use Cases
GLM-4.7 is designed for sophisticated applications requiring advanced reasoning and tool integration. Its flagship-tier capabilities make it suitable for complex coding assistance, research analysis, and agent-based systems that need to interact with external APIs. The 128K context window enables processing of lengthy documents, technical specifications, and multi-turn conversations with substantial context retention. Organizations building AI assistants, automated workflows, or applications requiring function calling will find GLM-4.7's tool integration capabilities particularly valuable for creating interactive systems that can query databases, call APIs, and perform multi-step reasoning tasks.
Frequently Asked Questions
How much does GLM-4.7 cost per million tokens?
GLM-4.7 pricing varies by provider and pricing type (standard vs batch). Check the pricing table above for current rates across all providers.
What is GLM-4.7 best used for?
GLM-4.7 excels at complex reasoning tasks, coding assistance, and agent-based applications requiring tool calling capabilities. Its 128K context window makes it well-suited for document analysis, research tasks, and multi-turn conversations with substantial context retention.
Does GLM-4.7 support image input or multimodal capabilities?
No, GLM-4.7 is text-only and does not support image input or other modalities. It focuses exclusively on text generation, reasoning, and tool calling functionality for text-based applications.