GLM-5.2 is Zhipu AI's language model with a 1.0M context window and up to 262K output tokens, available from 8 providers, starting at $0.7 / 1M input and $2.20 / 1M output. Z.AI's flagship long-horizon autonomous LLM capable of sustained multi-hour task execution with agentic reasoning.
Specifications
Canonical IDzhipu-glm-5-2
TypeLanguage
StatusActive
CreatorZhipu AIZhipu AI
Providers
Context Window1.0M tokens
Max Output262K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters753B
HuggingFace Likes692
HuggingFace Downloads (30d)0
HuggingFace Downloads (all-time)0
Release Date · 2 months ago
Benchmarks
Intelligence Index
#19
Coding Index
#24
GPQA
#39
HLE
#21
IFBench
#35
Time to First Token
#452
SciCode
#30
LCR
#24
TerminalBench Hard
#13
TAU2
#2
Output TPS
#36

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
ProviderStandardBatch
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Input
$ / 1M
Output
$ / 1M
$1.40$4.40$0.28$0.7$2.20
Azure AI Foundry logo
Azure AI Foundry
azure_ai/FW-GLM-5.2
$1.54$4.84$0.15
Fireworks AI logo
Fireworks AI
fireworks_ai/glm-5p2
$1.40$4.40$0.14
Hugging Face logo
Hugging Face
novita:zai-org/glm-5.2
$1.40$4.40N/A
Hugging Face logo
Hugging Face
scaleway:glm-5.2
$2.05$6.27N/A
Mistral AI logo
Mistral AI
zai-glm-5-2
$1.40$4.40N/A$0.7$2.20
Nebius logo
Nebius
zai-org/GLM-5.2
$1.40$4.40N/A
OpenRouter logo
OpenRouter
z-ai/glm-5.2
$1.19$3.74$0.221
OpenRouter logo
OpenRouter
z-ai/glm-5.2:batch
$0.7$2.20$0.13
$1.10$3.85$0.275

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host GLM-5.2, ranked by cheapest on-demand price. The model needs about 1808 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
p6-b300.48xlargeAWS8× B3002149 GB$142.42/hr

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
GLM-5.2 Fast1.0M$2.10$6.60Available
GLM-5.21.0M$0.700$2.20Current
GLM-5.2 Free128KAvailable
GLM-5V Turbo203K$1.20$4.00Deprecating
GLM-5 Turbo203K$1.20$4.00Deprecating
GLM-5.1 Non-ReasoningAvailable
GLM-5 Non-ReasoningAvailable
GLM-5 Code200K$1.20$5.00Available
GLM-5.1 Fast203K$2.80$8.80Available
GLM-5.1 NVFP4 MTP203K$1.40$4.40Available
GLM-5.2 Fast Preview$2.80$8.80Available

Model IDs

accounts/fireworks/models/glm-5p2
accounts/fireworks/models/glm-5p2-fp8
azure_ai/FW-GLM-5.2
cloudflare/@cf/zai-org/glm-5.2
dashscope/glm-5.2
fireworks_ai/accounts/fireworks/models/glm-5p2
fireworks_ai/glm-5p2
glm-5-2
glm-5-2-non-reasoning
glm-5.2
huggingface-llm-glm-5-2-fp8
z-ai/glm-5.2
z-ai/glm-5.2:batch
zai-glm-5-2
zai-org/glm-5.2
zai-org/GLM-5.2
zai/glm-5.2
zhipu-glm-5-2