ZMIME
Z.ai (Zhipu) · Released Dec 22, 2025

GLM-4.7

Mature GLM model for dependable coding, reasoning, and structured agent tasks.

  • Open weights
  • Reasoning
  • Tool calling
Capability
143.4ECI · #99 of 158
Input
$0.60per 1M tokens
Output
$2.20per 1M tokens
Context
205K131K max output
Pricing

What it costs

Input
$0.60per million tokens
Output
$2.20per million tokens
Cached input
$0.11per million tokens
Blended (3:1)
$1.00pricier than 57% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$2.30
Team assistant25M input + 5M output tokens$26.00
Production app250M input + 50M output tokens$260.00

Official Z.AI API price, as listed on models.dev.

Capability

Independent benchmarks

143.4Epoch Capabilities Index
#99 of 158 scored models
68Median 147174

The shaded band is Epoch AI’s confidence range (141.4–145.3); the tick marks the median scored model.

  • GPQA DiamondGraduate-level science questions83.3%
  • OTIS Mock AIME 2024–2025Competition mathematics83.3%
  • SimpleQA VerifiedShort factual questions32.2%

Scores from Epoch AI, run independently of Z.ai (Zhipu).

Specifications

The details

Lab
Z.ai (Zhipu)
Released
Dec 22, 2025
Knowledge cutoff
Apr 2025
Context window
204,800 tokens
Max output
131,072 tokens
Inputs
Text
Output
Text
Reasoning
Can be switched on or off
Tool calling
Yes
Structured output
No
API model ID
glm-4.7on Z.AI
Availability
30 API providerslisted on models.dev

Z.AI model documentation

Lab-reported

What Z.ai (Zhipu) claims

Published by the lab at launch. Settings vary, so compare these only with care.

BenchmarkScoreSettingSource
SWE-Bench Verified73.8 resolved—Source
Terminal Bench 2.033.4—Source
Same lab

More from Z.ai (Zhipu)

Questions

About GLM-4.7

How much does GLM-4.7 cost?

GLM-4.7 costs $0.60 input / $2.20 output per million tokens (official Z.AI API price). Cached input is $0.11 per million tokens. At a 3:1 input-to-output mix that is $1.00 per million tokens, more expensive than 57% of the 469 priced models we track.

What is the context window of GLM-4.7?

GLM-4.7 accepts up to 204,800 tokens per request and can write up to 131,072 tokens in one response.

How good is GLM-4.7?

Epoch AI gives GLM-4.7 a Capabilities Index score of 143.4 (likely range 141.4–145.3), ranking it #99 of 158 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 83.3%, OTIS Mock AIME 2024–2025 83.3%, SimpleQA Verified 32.2%.

Is GLM-4.7 open source?

Yes. Z.ai (Zhipu) publishes the weights, so it can be downloaded and self-hosted.

What inputs does GLM-4.7 support?

GLM-4.7 accepts text and replies in text. It is a reasoning model, supports tool calling.

When was GLM-4.7 released?

Z.ai (Zhipu) released GLM-4.7 on Dec 22, 2025. Its training data runs to Apr 2025.

What are the best alternatives to GLM-4.7?

The closest current models from other labs on capability, price and release date are Qwen3 235B-A22B Thinking 2507 (Alibaba (Qwen), ECI 143.3, $0.30 / $2.90), Kimi K2 Thinking (Moonshot AI, ECI 145.5, $0.60 / $2.50), Claude Haiku 4.5 (Anthropic, ECI 142.8, $1.00 / $5.00) and Gemini 2.5 Flash Preview 05-20 (Google, ECI 141.6, $0.142 / $3.33).