GLM-4.6V FlashX is Zhipu AI's language model with a 131K context window and up to 33K output tokens, starting at $0.04 / 1M input and $0.4 / 1M output. A fast, lightweight vision-language variant of GLM-4.6 optimized for low-latency multimodal inference.
Specifications
Canonical IDzhipu-glm-4-6v-flash-x
TypeLanguage
StatusActive
CreatorZhipu AIZhipu AI
Providers
Context Window131K tokens
Max Output33K tokens
Input ModalitiesImage
Output ModalitiesText
Reasoning Effortsdefault

Capabilities

Input1/5
Text·
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema·
Web Search✓
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Empiriolabs
empiriolabs/glm-4-6v-flashx
$0.04$0.4$0.036

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
GLM-5.3 FlashX Legal1.0M$0.370$1.25Available
GLM-5.3 FlashX1.0M$0.286$1.00Available
GLM-5.3 Flash1.3M$0.040$0.078Available
GLM-5.3 Flash Abliterated—1.0M$0.120$0.500Available
GLM-5.3 Flash US—1.0M$0.225$0.750Deprecated
GLM-4.6V Flash128K——Available
GLM-4.6V FlashX—131K$0.040$0.400Current
GLM-4.5 Flash—128K——Available
GLM-4.7 Flash Non-Reasoning————Available
Ultramarine 1 Flash1.0M$0.150$0.500Available

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
GLM-5.3 Prime—1.0M$1.68$5.28
GLM-5.3—1.3M$0.070$1.40
GLM-5.3 (50% off)—1.0M——
GLM-5.2 Fast—1.0M$2.10$6.60
GLM-5.2—1.0M$0.007$1.76
GLM-5V Turbo—205K$0.704$3.10
GLM-5 Turbo—203K$1.20$4.00
GLM-5 Code——200K$1.20$5.00
GLM-5 FP8——203K$0.600$1.92
GLM-5 Non-Reasoning—————

Model IDs

empiriolabs/glm-4-6v-flashx
zhipu-glm-4-6v-flash-x