Hitchhikethe internet
Directory/LLM models/GLM 5
LLM models · Model

GLM 5

Researched

GLM-5.2 is a 753B-parameter Mixture of Experts text generation model from zai-org, available on Hugging Face with multiple inference providers, tool calling, and up to 1M token context windows.

Online Checked Follow updates
Official model pageView model card
Official site snapshots

See the official site at a glance

Read-only public captures of GLM 5’s homepage and verified pricing page. Screenshots are dated, never live embeds, and open full-screen.

Visit live site
Homepage · captured Jul 23, 2026
1 earlier capture
Pricing page · captured Jul 23, 2026
At a glance

In one minute

Start here for the decision-making essentials: what GLM 5 does, who it is for, how it is accessed, and the first-party sources behind this profile.

Pricing3 options

zai-org/GLM-5.2 on deepinfra (cheapest): $0.93 input per 1M tokens, $3.00 output per 1M to

zai-org/GLM-5.2 on novita, together, and fireworks-ai: $1.40 input per 1M tokens, $4.40 ou

zai-org/GLM-5.2 on scaleway: $2.05 input per 1M tokens, $6.27 output per 1M tokens

Platforms
Hugging FaceHuggingChat
API accessNot public
FoundedNot disclosed by source
AvailabilityWeb / remote
LicenseProprietary

Best suited to

Source-backed fit
Large-scale text generation workloads Tool/function calling applications Long-context tasks up to 1M tokens Multi-provider inference deployments Quantized deployment
Model registry

Specifications and best fit

Source backed

Published specifications and use cases for GLM 5. Repository dates are kept separate from the model's original release date.

Developer
zai-org
Family
GLM
Original release
Updated 20 days ago (relative to page snapshot)
Repository created
2026-02-11
Parameters
753B
Context window
zai-org/GLM-5.2 supports a 1,048,576 token context window on deepinfra, novita, and firewo
Architecture
Mixture of Experts (MoE) — listed filter tag
License
mit
Weights
Not stated
Modalities
text, Text Generation
Languages
Not stated
Repository
zai-org/GLM-5

Good fit for

  • Chat with AI models directly via HuggingChat

Reported benchmarks

These are publisher-reported results. Test conditions and benchmark versions can differ.

  • Listed under eval-results filter on Hugging Face

Known limitations

  • Generated content may be inaccurate or false
Decision support

Common questions and adoption checks

6 sourced answers

Short answers to the questions buyers and builders commonly ask about GLM 5. Each answer cites the shared ledger below, where every source is listed once.

01What does GLM 5 say it can do?

Text Generation

zai-org/GLM-5.2 Text Generation • 753B
Ledger citations[6] huggingface.co/models[4] huggingface.co/models[1] huggingface.co/models
02What use cases does GLM 5 describe?

Chat with AI models directly via HuggingChat

You can also choose from any available open source models to chat with directly.
Ledger citation[3] huggingface.co/chat/models/zai-org/GLM-5
03What should teams verify before adopting GLM 5?

Generated content may be inaccurate or false

Generated content may be inaccurate or false.
Ledger citation[3] huggingface.co/chat/models/zai-org/GLM-5
04What pricing information is available for GLM 5?

zai-org/GLM-5.2 on deepinfra (cheapest): $0.93 input per 1M tokens, $3.00 output per 1M to · zai-org/GLM-5.2 on novita, together, and fireworks-ai: $1.40 input per 1M tokens, $4.40 ou · zai-org/GLM-5.2 on scaleway: $2.05 input per 1M tokens, $6.27 output per 1M tokens

zai-org/GLM-5.2 GLM-5.2 deepinfra cheapest $0.93 $3.00 1,048,576
Ledger citation[2] huggingface.co/inference/models
05How can GLM 5 be deployed or accessed?

zai-org/GLM-5.2 can be served via Hugging Face Inference Providers including direct servin · Multiple inference providers available, including Groq, Novita, Cerebras, Nscale, fal, Tog

zai-org/GLM-5.2 GLM-5.2 zai-org - - - 3.87 33 Yes No
Ledger citations[2] huggingface.co/inference/models[1] huggingface.co/models
06Is GLM 5 open source?

true

You can also choose from any available open source models to chat with directly.
Ledger citation[3] huggingface.co/chat/models/zai-org/GLM-5
Decision guide

Capabilities and operating fit

LLM models

This profile connects the jobs GLM 5 is described as handling with its delivery model, access options and the subjects used to match it to related products in this directory.

Common use cases

  • Conversational AI with function calling
  • Long-document analysis and generation
  • Structured output generation via supported providers
  • Cost-optimized inference via deepinfra pricing
  • Production serving via Hugging Face Inference Providers
  • Chat with AI models directly via HuggingChat

Verified capabilities

Access signals

Pricing model
zai-org/GLM-5.2 on deepinfra (cheapest): $0.93 input per 1M tokens, $3.00 output per 1M to · zai-org/GLM-5.2 on novita, together, and fireworks-ai: $1.40 input per 1M tokens, $4.40 ou · zai-org/GLM-5.2 on scaleway: $2.05 input per 1M tokens, $6.27 output per 1M tokens
API
Not publicly listed
Source links
16 recorded
Source-backed

Verified facts

Updated July 22, 2026

Each fact points to a recorded source, making it easy to distinguish verified product information from claims that need checking.

Official website

HTTP 200 verified twice

[8]huggingface.co/zai-org/GLM-5
First-party description

zai-org/GLM-5 · Hugging Face

[8]huggingface.co/zai-org/GLM-5
Source-supported facts

GLM-5.2 is a text generation model with 753B parameters · Developed by zai-org in the GLM model family · Listed on the Hugging Face Models hub

[8]huggingface.co/zai-org/GLM-5
Tool use

Supports function/tool calling within the chat template, allowing one or more function calls per user query

[8]huggingface.co/zai-org/GLM-5
Model family

GLM

[6]huggingface.co/models
Model version

5.2

[6]huggingface.co/models
Parameter count

753B

[6]huggingface.co/models
Capability

Text Generation

[6]huggingface.co/models
View 32 more verified facts
Platform

Hugging Face

[6]huggingface.co/models
Model

zai-org/GLM-5.2 is a model listed on the Hugging Face Inference Providers supported models directory

[2]huggingface.co/inference/models
Platform

zai-org/GLM-5.2 is offered by multiple Inference Providers including novita, together, fireworks-ai, zai-org, scaleway, and deepinfra

[2]huggingface.co/inference/models
Pricing

zai-org/GLM-5.2 on deepinfra (cheapest): $0.93 input per 1M tokens, $3.00 output per 1M tokens

[2]huggingface.co/inference/models
Pricing

zai-org/GLM-5.2 on novita, together, and fireworks-ai: $1.40 input per 1M tokens, $4.40 output per 1M tokens

[2]huggingface.co/inference/models
Pricing

zai-org/GLM-5.2 on scaleway: $2.05 input per 1M tokens, $6.27 output per 1M tokens

[2]huggingface.co/inference/models
Context window

zai-org/GLM-5.2 supports a 1,048,576 token context window on deepinfra, novita, and fireworks-ai providers

[2]huggingface.co/inference/models
Context window

zai-org/GLM-5.2 supports a 262,144 token context window on together provider

[2]huggingface.co/inference/models
Tool use

zai-org/GLM-5.2 supports tool/function calling across all listed providers (novita, together, fireworks-ai, zai-org, scaleway, deepinfra)

[2]huggingface.co/inference/models
Deployment

zai-org/GLM-5.2 can be served via Hugging Face Inference Providers including direct serving by zai-org (3.87s latency, 33 t/s throughput)

[2]huggingface.co/inference/models
Structured output

zai-org/GLM-5.2 supports structured output on novita, together, scaleway, and deepinfra providers but not on fireworks-ai or zai-org

[2]huggingface.co/inference/models
Model version

GLM-5.2

[4]huggingface.co/models
Company

zai-org

[4]huggingface.co/models
Capability

Text Generation

[4]huggingface.co/models
Parameter count

753B

[4]huggingface.co/models
Modality

text

[4]huggingface.co/models
Platform

Hugging Face

[4]huggingface.co/models
Model

GLM-5.2

[7]huggingface.co/models
Parameter count

753B

[7]huggingface.co/models
Modality

Text Generation

[7]huggingface.co/models
Company

zai-org

[7]huggingface.co/models
Release date

Updated 20 days ago (relative to page snapshot)

[7]huggingface.co/models
Platform

Listed on Hugging Face Models hub (ZH language filter)

[7]huggingface.co/models
Parameter count

> 500B

[1]huggingface.co/models
Model

zai-org/GLM-5.2

[1]huggingface.co/models
Capability

Text Generation

[1]huggingface.co/models
Parameter count

753B

[1]huggingface.co/models
Parameter count

754B (GGUF variants)

[1]huggingface.co/models
Parameter count

381B (NVFP4 variants)

[1]huggingface.co/models
Quantization

FP8 (zai-org/GLM-5.2-FP8)

[1]huggingface.co/models
Quantization

GGUF (unsloth/GLM-5.2-GGUF)

[1]huggingface.co/models
Quantization

NVFP4 (nvidia/GLM-5.2-NVFP4)

[1]huggingface.co/models
Practical capabilities

What it helps with

7 documented areas

A concise view of the jobs, capabilities and integrations described in the recorded product sources.

Use case

Conversational AI with function calling

Use case

Long-document analysis and generation

Use case

Structured output generation via supported providers

Use case

Cost-optimized inference via deepinfra pricing

Use case

Production serving via Hugging Face Inference Providers

Use case

Chat with AI models directly via HuggingChat

Capability

Text Generation

Availability

Where it runs and where to get it

Source checked

Documented product formats, platforms and official distribution destinations. Availability can vary by region and plan.

Cost / license

zai-org/GLM-5.2 on deepinfra (cheapest): $0.93 input per 1M tokens, $3.00 output per 1M to · zai-org/GLM-5.2 on novita, together, and fireworks-ai: $1.40 input per 1M tokens, $4.40 ou · zai-org/GLM-5.2 on scaleway: $2.05 input per 1M tokens, $6.27 output per 1M tokenstrue

Platforms

Hugging Facezai-org/GLM-5.2 is offered by multiple Inference Providers including novita, together, firListed on Hugging Face Models hub (ZH language filter)HuggingChat
Implementation details

Adoption notes

Deploymentzai-org/GLM-5.2 can be served via Hugging Face Inference Providers including direct servin · Multiple inference providers available, including Groq, Novita, Cerebras, Nscale, fal, Tog
Licensetrue
Model supportzai-org/GLM-5.2 is a model listed on the Hugging Face Inference Providers supported models · GLM-5.2 · zai-org/GLM-5.2 · zai-org/GLM-5
Data controlNot disclosed by source
Learning curveIntermediate
Primary use casesConversational AI with function calling, Long-document analysis and generation, Structured output generation via supported providers, Cost-optimized inference via deepinfra pricing, Production serving via Hugging Face Inference Providers, Chat with AI models directly via HuggingChat

What to verify before adopting

  • Generated content may be inaccurate or false
Evolution and major updates

GLM 5 timeline

A concise history of software releases and material product changes. Events appear only when a dated source supports what changed.

1 dated update
Latest first · exact dates

Showing the newest updates and meaningful milestones. Open an entry for its summary and source.

  1. Release note

    Hugging Face repository published

    Open details

    The public model repository was created on Hugging Face. This repository date may differ from the model's original release date.

    View source [8]
Citation ledger

Recorded sources

16 unique pages

Facts, answers, structured details, milestones and primary resource links cite this shared ledger. Each external page appears once; release tags from the same GitHub project are grouped under one release history.

  1. 1huggingface.co/models 12 facts · 2 answers · Official site
  2. 2huggingface.co/inference/models 10 facts · 2 answers · Official site
  3. 3huggingface.co/chat/models/zai-org/GLM-5 5 facts · 3 answers · Official site
  4. 4huggingface.co/models 6 facts · 1 answer · Official site
  5. 5huggingface.co/models 7 facts · Official site
  6. 6huggingface.co/models 5 facts · 1 answer · Official site
  7. 7huggingface.co/models 6 facts · Official site
  8. 8huggingface.co/zai-org/GLM-5 4 facts · 1 milestone · Official site
  9. 9huggingface.co/blog Official site
  10. 10huggingface.co/docs Documentation
  11. 11huggingface.co/docs/hub/eval-results Documentation
  12. 12huggingface.co/docs/inference-providers/index Documentation
  13. 13huggingface.co/docs/safetensors/index Documentation
  14. 14huggingface.co/pricing Pricing
  15. 15huggingface.co/privacy Security
  16. 16huggingface.co/support Official site
Research status54 substantive facts · 16 source pages · quality score 88/100