GLM-4.7 (Non-reasoning)
Intelligence
34.2
#126/520
Coding
32
#114/426
Math
48
#144/265
Speed
84 tok/s
TTFT: 658.00s
Pricing
$0.55 / $2.15
per 1M tokens (in/out)
GLM 4.7 is a coding‑centric model that thinks before acting, preserves its reasoning across turns, and lets you control thinking per request for speed or accuracy. It upgrades agentic workflows with stronger multi‑step tool use, better terminal and multilingual coding, and a noticeable jump in UI output quality for modern, clean webpages and slides. You can use it in popular coding agents, call it via the Z.ai API, and even run it locally with public weights on HuggingFace and ModelScope using vLLM or SGLang.
GLM-4.7 (Non-reasoning) is Z AI’s model designed for various applications, processing at 83.862 tokens per second. It is priced at $0.55 per million input tokens and $2.15 per million output tokens, targeting professional users.
When to Use GLM-4.7 (Non-reasoning)
✓ Best For
- Natural language processing tasks
- Basic coding assistance
- Mathematical problem-solving
✗ Not Ideal For
- Advanced reasoning tasks
- High-speed real-time applications
How GLM-4.7 (Non-reasoning) Compares
Intelligence Index · Higher is better
GoogleAmazonZ AIDeepSeekTencent
Benchmark Profile
Coding Index
AnthropicGoogleZ AIDeepSeekXiaomi
Output Speed · tok/s
XiaomiZ AIAlibaba
Math Index
InclusionAIOpenAIZ AIAmazon
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (13)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 34.2 | |
| Coding Index | 32 | |
| Math Index | 48 | |
| MMLU-Pro | 794% | |
| GPQA | 664% | |
| LiveCodeBench | 562% | |
| HLE | 61% | |
| SciCode | 35.4% | |
| IFBench | 54.6% | |
| LCR | 36.3% | |
| TerminalBench Hard | 30.3% | |
| Tau2 | 94.2% | |
| AIME 2025 | 48% |
Data: Artificial Analysis · Updated: April 2, 2026
Frequently Asked Questions (15)
When was GLM-4.7 (Non-reasoning) released?
GLM-4.7 (Non-reasoning) was released on December 22, 2025.
Who created GLM-4.7 (Non-reasoning)?
GLM-4.7 (Non-reasoning) was created by Z AI.
How intelligent is GLM-4.7 (Non-reasoning)?
GLM-4.7 (Non-reasoning) scores 34 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 22).
How fast is GLM-4.7 (Non-reasoning)?
GLM-4.7 (Non-reasoning) generates output at 74.3 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight non-reasoning models of similar size (median: 47.2 t/s).
What is the latency of GLM-4.7 (Non-reasoning)?
GLM-4.7 (Non-reasoning) has a time to first token (TTFT) of 1.18s (based on the median across providers serving the model), which is very competitive compared to other open weight non-reasoning models of similar size (median: 1.95s).
How much does GLM-4.7 (Non-reasoning) cost?
GLM-4.7 (Non-reasoning) costs $0.55 per 1M input tokens (better than average, median: $0.60) and $2.15 per 1M output tokens (better than average, median: $2.33), based on the median across providers serving the model.
What is GLM-4.7 (Non-reasoning) API pricing?
GLM-4.7 (Non-reasoning) costs $0.55 per 1M input tokens and $2.15 per 1M output tokens (based on the median across providers serving the model). For a blended rate (3:1 input to output ratio), this is $0.94 per 1M tokens. Pricing may vary by provider.
How verbose is GLM-4.7 (Non-reasoning)?
When evaluated on the Intelligence Index, GLM-4.7 (Non-reasoning) generated 13M output tokens, which is at the higher end compared to other open weight non-reasoning models of similar size (median: 8.1M).
Is GLM-4.7 (Non-reasoning) a reasoning model?
No, GLM-4.7 (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does GLM-4.7 (Non-reasoning) support?
GLM-4.7 (Non-reasoning) supports text input.
What output modalities does GLM-4.7 (Non-reasoning) support?
GLM-4.7 (Non-reasoning) supports text output.
Can GLM-4.7 (Non-reasoning) process images?
No, GLM-4.7 (Non-reasoning) does not support image input. It can only process text.
Is GLM-4.7 (Non-reasoning) multimodal?
No, GLM-4.7 (Non-reasoning) is not multimodal. It only supports text input.
What is the context window of GLM-4.7 (Non-reasoning)?
GLM-4.7 (Non-reasoning) has a context window of 200k tokens. This determines how much text and conversation history the model can process in a single request.
Is GLM-4.7 (Non-reasoning) open source?
Yes, GLM-4.7 (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
