Z
GLM 4.7OPEN
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.
Prices update automatically — checked daily against provider list prices.
- $0.74 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 26% of the 191 open-weight models tracked here
- 6 of 15 Z.AI models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for GLM 4.7, measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning.
For the same budget, GLM 4.7 delivers 5.5 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $1.56 per 1M tokens (median of 21) — this one costs $0.74.
Cheaper and better on this index: GLM 5.3 Flash · Gemini 3.7 Flash (batch) · GPT-5.6 Luna and 21 more
About this model
GLM 4.7 is an open-weight AI model by Z.AI. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is GLM 4.7?
GLM 4.7 is an AI language model from Z.AI. It is open-weight: you can download it and run it on your own hardware, for free. It scores 34.5 on the Artificial Analysis intelligence index.
Is GLM 4.7 free?
The weights are free and open — you can self-host GLM 4.7 and pay nothing per token. If you prefer a hosted API, list prices are $0.4 per million input tokens and $1.75 per million output tokens.
What is GLM 4.7 good at?
Independent benchmarks from Artificial Analysis give it GPQA 85.9%, MMLU-Pro 85.6%, Humanity's Last Exam 27.4%, Long Context Reasoning 68%, LiveCodeBench 89.4%, SciCode 45.1%, AIME 2025 95%, IFBench 67.9%, τ²-Bench 95.9%, τ-Bench Banking 12.2%, Terminal-Bench 45.3%, Terminal-Bench Hard 31.8%. It is particularly used for code generation.
Can I self-host GLM 4.7?
Yes. GLM 4.7 has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.