How much does GLM 4.6V cost?

GLM 4.6V costs $0.30 per million input tokens and $0.90 per million output tokens. For a typical conversation (~2,000 tokens), that's approximately $0.002 per message.

How does GLM 4.6V compare to Baichuan 2-7B?

GLM 4.6V has an average score of 28.3 while Baichuan 2-7B scores 29.0. Baichuan 2-7B slightly outperforms GLM 4.6V overall. See full comparison →

Home/Models/GLM 4.6V

GLM 4.6V

Name: GLM 4.6V
Price: 0.3 USD
Author: z-ai

by z-ai · Released Dec 2025

Open SourceMultimodal

28.3

avg score

Rank #185

Compare

Better than 21% of all models

Context

131K tokens (~66 books)

Input $/1M

$0.30

Output $/1M

$0.90

Type

multimodal

License

Open Source

Benchmarks

9 tested

Data updated today

About

GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...

Tested on 9 benchmarks with 40.1% average. Top scores: Chatbot Arena Elo — Overall (1377.9%), LiveBench — Coding (64.2%), LiveBench — Mathematics (62.5%).

Looking for similar performance at lower cost?
Llama 3.3 70B Instruct (free) scores 29.6 (105% as good) at $0.00/1M input · 100% cheaper

Capabilities

coding

33.8

#112 globally

reasoning

41.8

#63 globally

math

62.5

#44 globally

knowledge

40.1

#152 globally

language

33.4

#120 globally

Benchmark Scores

Compare All

Tested on 9 benchmarks · Ranked across 6 categories

Score Distribution (all 233 models)

0255075100

▲ You are here

codingCompare coding →

LiveBench — Coding

Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.

64.2—

LiveBench — Agentic Coding

LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.

3.3—

reasoningCompare reasoning →

LiveBench — Data Analysis

Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.

46.4—

LiveBench — Reasoning

Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.

37.2—

mathCompare math →

LiveBench — Mathematics

Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.

62.5—

Quick compare:

vs Baichuan 2-7B

vs Grok-2 (Dec 2024)

vs Hunyuan A13B Instruct

Excellent (85+) Good (70-85) Average (50-70) Below (<50)

Model Family · z-ai GLM 4

GLM 4 32B Jul 2025

18.0

$0.10/M in128Kctx6 benchmarks

GLM 4.5VAug 2025

$0.60/M in(+0.50)66Kctx(-62K)1 benchmark

GLM 4.6VDec 2025

40.1+40.1

$0.30/M in(-0.30)131Kctx(+66K)9 benchmarks

See the full GLM 4 family →

Similar Models

Hunyuan A13B Instruct

tencent

29.3$0.14/1M

Links

Info

z-ai Pricing explorer Developers · API

Research

Documentation

Community

Source Code

BenchGecko API

glm-4-6v

Specifications

Typemultimodal
Context131K tokens (~66 books)
ReleasedDec 2025
LicenseOpen Source
StatusActive
Cost / Message~$0.002

Available On

z-ai$0.30

Frequently Asked Questions

GLM 4.6V is an open-source multimodal AI model by z-ai, released in December 2025. It has an average benchmark score of 28.3. Context window: 131K tokens.

Benchmarks

Chatbot Arena Elo — Overall LiveBench — Coding LiveBench — Mathematics LiveBench — Language LiveBench — Data Analysis

z-ai · Provider z-ai · Economy All Models Compare Models Pricing Developers · API Context Window · Glossary

GLM 4.6V

Frequently Asked Questions

Related Models

Benchmarks

Related Pages