Zhipu AI logo

GLM-4.6

Deprecated
Pricing & Specs API
Free REST API for prices, specs and benchmarks
GLM-4.6 is Zhipu AI's language model with a 205K context window and up to 131K output tokens, available from 9 providers, starting at $0.5 / 1M input and $2.00 / 1M output. A MoE LLM from Z AI that extends GLM-4.5 with a 200K context window and improved agentic reasoning and tool-use capabilities.
Specifications
Canonical IDzhipu-glm-4-6
TypeLanguage
StatusDeprecated
CreatorZhipu AIZhipu AI
Providers
Context Window205K tokens
Max Output131K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters357B
HuggingFace Likes1,212
HuggingFace Downloads (30d)36,176
HuggingFace Downloads (all-time)681,060
Release Date · 1 year ago
Knowledge Cutoff · 2 years ago
Deprecation Date
Benchmarks
Intelligence Index
#190
Coding Index
#79
Math Index
#57
MMLU-Pro
#67
GPQA
#181
HLE
#177
LiveCodeBench
#88
IFBench
#230
Time to First Token
#533
SciCode
#207
AIME 2025
#57
LCR
#236
TerminalBench Hard
#114
TAU2
#130
Output TPS
#230

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities6/13
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
Baseten
baseten/zai-org/GLM-4.6
$0.6$2.20N/A
DeepInfra logo
DeepInfra
deepinfra/zai-org/GLM-4.6
$0.5$2.00$0.1
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/glm-4p6
$0.55$2.19N/A
Hugging Face logo
Hugging Face
novita:zai-org/glm-4.6
$0.55$2.20N/A
Novita logo
Novita
novita/zai-org/glm-4.6
$0.55$2.20$0.11
OpenRouter logo
OpenRouter
z-ai/glm-4.6
$0.5$2.00$0.1
Together AI logo
Together AI
together_ai/zai-org/GLM-4.6
$0.6$2.20N/A
$0.6$2.20$0.11
Z AI (Zhipu) logo
Z AI (Zhipu)
zai/glm-4.6
$0.6$2.20$0.11

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host GLM-4.6, ranked by cheapest on-demand price. The model needs about 856 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
Cheapest region
Standard_ND96is_MI300X_v5Azure8× AMD Instinct MI300X GPU (192GB)1536 GB$48.00/hr
Standard_ND96isr_MI300X_v5Azure8× AMD Instinct MI300X1536 GB$48.00/hr
p5en.48xlargeAWS8× H2001128 GB$63.30/hr
5 more instances can run GLM-4.6
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
GLM-4.7205K$0.400$1.75Deprecated
GLM-4.6205K$0.500$2.00Current
GLM-4.5131K$0.400$1.60Deprecated
GLM-4.5 Air131K$0.125$0.450Available

Model IDs

accounts/fireworks/models/glm-4p6
baseten/zai-org/GLM-4.6
cerebras/zai-glm-4.6
deepinfra/zai-org/GLM-4.6
dev/glm46
fireworks_ai/accounts/fireworks/models/glm-4p6
glm-4-6
glm-4-6-reasoning
glm-4.6
novita/zai-org/glm-4.6
openrouter/z-ai/glm-4.6
openrouter/z-ai/glm-4.6:exacto
together_ai/zai-org/GLM-4.6
vercel_ai_gateway/zai/glm-4.6
z-ai/glm-4.6
zai-org/glm-4.6
zai-org/GLM-4.6
zai/glm-4.6
zhipu-glm-4-6