Skip to content
LLMs
Z.ai logo

Z.ai: GLM 5V Turbo

by Z.ai

Z.ai: GLM 5V Turbo is a large language model from Z.ai. It costs $1.20 per million input tokens and $4.00 per million output tokens. Its context window is 203K tokens.

ReasoningTool callingStructured outputPrompt cachingimage inputvideo input
Input / 1M tokens
$1.20
Output / 1M tokens
$4.00
Cached input / 1M
$0.240

On repeated prefixes

Context window
203K

tokens

Who serves it cheapest

1 hosts serve GLM 5V Turbo. Same weights, same API - the price difference is pure margin and routing.

Providers serving Z.ai: GLM 5V Turbo, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
Z.AICheapestfp8$1.20$4.00203K-100.0%

About GLM 5V Turbo

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...

Specifications

Z.ai: GLM 5V Turbo specifications
Model IDz-ai/glm-5v-turbo
ProviderZ.ai
Context window203K tokens
Max output131K tokens
Input modalitiesimage, text, video
Output modalitiestext
Knowledge cutoff-
Open weightsNo
ReleasedApril 1, 2026

Cheaper alternatives

Models that cost less than GLM 5V Turbo while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Z.ai: GLM 5V Turbo cost?

$1.20 per million input tokens and $4.00 per million output tokens. Cached input reads cost $0.240 per million tokens.

What is the context window of Z.ai: GLM 5V Turbo?

203K tokens, with up to 131K tokens of output per request.

Confirm against the source: Z.ai official pricing.