Zhipu AI
Multimodal

GLM-4V

Vision

Vision GLM-4. Chinese-language multimodal model with document and chart understanding.

GLM-4V is a multimodal AI model from Zhipu AI. It costs $7.00 per million input tokens and $7.00 per million output tokens (blended $7.00/M), with a 2,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$7.00/M
per million input tokens
OUTPUT
$7.00/M
per million output tokens
BLENDED 70/30
$7.00/M
unchanged since 3 May
CONTEXT
2,000
tokens

Hand-maintained from Zhipu AI's published pricing; no check date on record.

What it is good at
  • Vision-capable
  • Strong Chinese OCR
  • 128K context
Typical use cases
  • Chinese document parsing
  • Vision QA in Chinese

Benchmarks

vs. best public score
Scores inherited from GLM-4 Plus — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU86.8%
Multitask academic knowledge across 57 subjects. Source: Zhipu AI (self-reported), MMLU, read 2026-11-10.
Graduate-level science questions, "Google-proof". No source recorded yet.
MATH74.2%
High-school competition math problems. Source: Zhipu AI (self-reported), MATH, read 2026-11-10.
Python function synthesis from docstrings. No source recorded yet.
LMArena Elo1319 Elo
Crowd-sourced head-to-head preference Elo rating. Source: LMArena (independent), LMArena Text Arena score, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Zhipu AI

See all 5 →

Frequently asked questions

How much does GLM-4V cost?

GLM-4V costs $7.00 per million input tokens and $7.00 per million output tokens, for a blended reference rate of $7.00 per million tokens.

What is GLM-4V's context window?

GLM-4V supports up to 2,000 tokens of context in a single request.

What is GLM-4V best for?

GLM-4V is well suited to Vision-capable, Strong Chinese OCR and 128K context.

Who makes GLM-4V?

GLM-4V is developed and served by Zhipu AI.

Terms used on this page