GLM-4.5V

Name: GLM-4.5V
Brand: Zhipu AI

Deprecates 2026-12-31

Free REST API for prices, specs and benchmarks

GLM-4.5V is Zhipu AI's language model with a 131K context window and up to 32K output tokens, available from 6 providers, starting at $0.6 / 1M input and $1.20 / 1M output. A multimodal MoE vision-language model from Z AI based on GLM-4.5 Air, delivering strong visual reasoning and tool-use performance.

Specifications
Canonical ID	`zhipu-glm-4-5v`
Type	Language
Status	Deprecating 2026-12-31
Creator	Zhipu AI
Providers	Fireworks AI Hugging Face Novita OpenRouter Vercel AI Gateway Z AI (Zhipu)
Context Window	131K tokens
Max Output	32K tokens
Input Modalities	ImageText
Output Modalities	Text
Reasoning Efforts	default
Parameters	108B
HuggingFace Likes	717
HuggingFace Downloads (30d)	44,600
HuggingFace Downloads (all-time)	417,587
Release Date	2025-08-11 · 1 year ago
Knowledge Cutoff	2024-12-31 · 2 years ago
Deprecation Date	2026-12-31

Benchmarks
Intelligence Index	#405
Math Index	#116
MMLU-Pro	#149
GPQA	#285
HLE	#327
LiveCodeBench	#140
IFBench	#322
Time to First Token	#518
SciCode	#421
AIME 2025	#116
LCR	#491
TerminalBench Hard	#258
TAU2	#314
Output TPS	#197

Capabilities

Input2/5

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

Provider	Standard
Provider	Input $ / 1M	Output $ / 1M	Cache Read $ / 1M
Fireworks AI `fireworks_ai/accounts/fireworks/models/glm-4p5v`	$1.20	$1.20	N/A
Hugging Face `novita:zai-org/glm-4.5v`	$0.6	$1.80	N/A
Novita `novita/zai-org/glm-4.5v`	$0.6	$1.80	$0.11
OpenRouter `z-ai/glm-4.5v`	$0.6	$1.80	$0.11
Vercel AI Gateway `zai/glm-4.5v`	$0.6	$1.80	$0.11
Z AI (Zhipu) `zai/glm-4.5v`	$0.6	$1.80	N/A

Cost Calculator

US Dollar ($)

Preset:

Input tokens

Output tokens

Cache write tokens

Cache read tokens

Number of calls

Cheapest Instances to Run It

Cloud GPU instances that can host GLM-4.5V, ranked by cheapest on-demand price. The model needs about 259 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds

FP16 (full precision)

US Dollar ($)

Instance	Cloud	GPU	VRAM	Price
Standard_NC96ads_A100_v4	Azure	4× NVIDIA A100	320 GB	$14.69/hr
g7e.24xlarge	AWS	4× RTX PRO Server 6000	384 GB	$16.57/hr
g4-standard-192	GCP	4× nvidia-rtx-pro-6000	384 GB	$18.00/hr
7 more instances can run GLM-4.5V Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

Version	Released	Context	Input / 1M	Output / 1M	Status
GLM-4.6V	2025-12-08	131K	$0.300	$0.900	Available
GLM-4.5V	2025-08-11	131K	$0.600	$1.20	Current

Model IDs

accounts/fireworks/models/glm-4p5v

fireworks_ai/accounts/fireworks/models/glm-4p5v

glm-4-5v

glm-4-5v-reasoning

novita/zai-org/glm-4.5v

openrouter/z-ai/glm-4.5v

z-ai/glm-4.5v

zai-org/glm-4.5v

zai/glm-4.5v

zhipu-glm-4-5v

GLM-4.5V

CapabilitiesAPIGET/api/v1/models/zhipu-glm-4-5v

Pricing by ProviderAPIGET/api/v1/models/zhipu-glm-4-5v/pricing

Cost CalculatorAPIGET/api/v1/models/zhipu-glm-4-5v/pricing/calculate?input_tokens=1000000&output_tokens=500000

Cheapest Instances to Run ItAPIGET/api/v1/models/zhipu-glm-4-5v/instances

VersionsAPIGET/api/v1/models?family=glm4v_moe

Model IDsAPIGET/api/v1/models/zhipu-glm-4-5v

Capabilities

Pricing by Provider

Cost Calculator

Cheapest Instances to Run It

Versions

Model IDs