Are GLM-4.7's weights open and can I run it locally?

Yes, the weights are publicly available on Hugging Face at zai-org/GLM-4.7, so you can download and self-host the model. Check the repository licence before using it in a commercial product.

What does GLM-4.7 cost and how long is its context?

Z.ai's API charges $0.60 per million input tokens and $2.20 per million output tokens, with a 204,800-token context window.

How does GLM-4.7 differ from GLM-4.6?

GLM-4.7 focuses its improvements on agentic coding, tool use and reasoning: the maker reports gains of roughly 6 points on SWE-bench Verified, 13 points on SWE-bench Multilingual, 16 points on Terminal Bench 2.0, and 12 points on the HLE reasoning benchmark compared to GLM-4.6.

GLM 4.7

5539°

#llm #z-ai #reasoning #coding #agents #math

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Z.ai | 204,800 token context | $0.60/M input, $2.20/M output. GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.

Guides for this model

Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs

Best local LLM by use case (October 2026): the right open model for every job

How much VRAM do I actually need for local AI?

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

GLM-4.7 is Z.ai's current flagship text model, built around agentic coding and multi-step reasoning. It carries open weights and a 204,800-token context, and its benchmark gains over GLM-4.6 are substantial across coding, math and tool use. It suits developers who want a capable, self-hostable alternative to the closed frontier models without paying frontier prices.

Known for

Strong agentic coding, including multilingual repo-level tasks via SWE-bench
Thinking-before-acting support in Claude Code, Cline, Roo Code and similar frameworks
Solid math and reasoning gains over its predecessor on AIME and HMMT benchmarks
Tool use and web browsing improvements measured on τ²-Bench and BrowseComp
Open weights available on Hugging Face for local or self-hosted deployment

Watch out for

Output tokens cost $2.20/M, so long agentic runs with many tool calls add up quickly.
The maker has not published a licence summary on the model card; check terms before commercial use.
Gemini 3.0 Pro and GPT-5-High outperform it on several benchmarks in the maker's own comparison table.

Best for

Prompts to try

Fix a real GitHub issue

Here is a Python repository with a bug: the function `parse_config` in `config.py` raises a KeyError when the config file is missing the `timeout` key. Write a minimal, production-ready fix, add a unit test that covers the missing-key case, and explain in one paragraph why your approach is safer than a bare dict lookup.

Multi-step reasoning puzzle

A farmer has 17 sheep. All but 9 die. He then buys enough sheep to double his herd, sells a third of the total, and gives 4 to his neighbour. How many sheep does he have? Show every step of your reasoning before giving the final number, and flag any ambiguity in the problem statement.

Agentic plan with tool calls

You are working in a terminal. I need you to write a bash script that: checks whether Python 3.11 or higher is installed, creates a virtual environment if one does not exist, installs the packages in a requirements.txt I will provide, and runs pytest. Output the script, then walk through what each block does and what could go wrong at each step.

Compare with

GLM 5.3 FlashX
API-only model
1,048,576 token context · $0.37/M input, $1.25/M output
GLM 5V Turbo
API-only model
202,752 token context · $1.20/M input, $4.00/M output
GLM 5.3 Prime
API-only model
1,000,000 token context · $2.80/M input, $8.80/M output
GLM 5.3 Flash
Open-weights model
1,048,576 token context · $0.02/M input, $0.72/M output

More text models from z-ai

Questions people ask

Are GLM-4.7's weights open and can I run it locally?: Yes, the weights are publicly available on Hugging Face at zai-org/GLM-4.7, so you can download and self-host the model. Check the repository licence before using it in a commercial product.
What does GLM-4.7 cost and how long is its context?: Z.ai's API charges $0.60 per million input tokens and $2.20 per million output tokens, with a 204,800-token context window.
How does GLM-4.7 differ from GLM-4.6?: GLM-4.7 focuses its improvements on agentic coding, tool use and reasoning: the maker reports gains of roughly 6 points on SWE-bench Verified, 13 points on SWE-bench Multilingual, 16 points on Terminal Bench 2.0, and 12 points on the HLE reasoning benchmark compared to GLM-4.6.

Captain's verdict
A genuinely capable open-weights coding and reasoning model that earns its place on the shortlist without requiring a closed-API commitment.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

Qwen3 30B A3B Thinking 2507

TEXT / LLM

Seed 2.0 Mini

TEXT / LLM

AI Models for Image, Video & Text Generation

GLM 4.7 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm z-ai reasoning coding agents math local

Browse by Model Family