GLM-5 is Zhipu AI's language model with a 203K context window and up to 131K output tokens, available from 9 providers, starting at $0.573 / 1M input and $1.92 / 1M output. An open-source MoE LLM from Z AI designed for long-context reasoning, multi-step tool orchestration, and complex agentic engineering tasks.
Specifications
Canonical IDzhipu-glm-5
TypeLanguage
StatusActive
CreatorZhipu AIZhipu AI
Providers
Context Window203K tokens
Max Output131K tokens
Input ModalitiesPDFText
Output ModalitiesText
Reasoning Effortsdefault
Parameters754B
HuggingFace Likes2,070
HuggingFace Downloads (30d)477,667
HuggingFace Downloads (all-time)777,726
Release Date · 5 months ago
Benchmarks
Intelligence Index
39.5
#37
GPQA
0.8
#93
HLE
0.3
#43
IFBench
0.7
#46
Time to First Token
1.26s
#389
SciCode
0.5
#42
LCR
0.6
#82
TerminalBench Hard
0.4
#30
TAU2
1.0
#9
Output TPS
50.5
#210

Capabilities

Input2/5
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
ProviderStandardBatchFlexPriority
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Cache Write
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
$0.573$2.58N/AN/A$0.286$1.29
$1.00$3.20N/AN/A$0.5$1.60$0.5$1.60$1.75$5.60
Baseten
baseten/zai-org/GLM-5
$0.95$3.15N/AN/A
$1.00$3.20N/A$0.1
$1.00$3.20$0.1$0.1
Hugging Face logo
Hugging Face
novita:zai-org/glm-5
$1.00$3.20N/AN/A
OpenRouter logo
OpenRouter
z-ai/glm-5
$0.6$1.92$0.12N/A
$0.95$3.15$0.2N/A
Z AI (Zhipu) logo
Z AI (Zhipu)
zai/glm-5
$1.00$3.20$0.2N/A

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host GLM-5, ranked by cheapest on-demand price. The model needs about 1809 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/hrus-east-1

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
GLM-5.1203K$0.966$3.04Available
GLM-5203K$0.573$1.92Current

Model IDs

accounts/fireworks/models/glm-5
baseten/zai-org/GLM-5
bedrock/us-east-1/zai.glm-5
bedrock/us-west-2/zai.glm-5
glm-5
glm-5-maas
glm-5-non-reasoning
openrouter/z-ai/glm-5
publishers/google/models/glm-5-maas
vertex_ai/zai-org/glm-5-maas
z-ai/glm-5
zai-org/glm-5
zai-org/GLM-5
zai.glm-5
zai/glm-5
zhipu-glm-5