Z
GLM 4.6OPEN
GLM 4.6 (Z.AI): live API pricing, context window and the best open-source alternatives, tracked daily by olud.ai.
Prices update automatically — checked daily against provider list prices.
- $0.76 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 23% of the 191 open-weight models tracked here
- 7 of 15 Z.AI models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for GLM 4.6, measured by Artificial Analysis. Higher is better. Measurement mode: Non-reasoning.
For the same budget, GLM 4.6 delivers 3.8 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $0.83 per 1M tokens (median of 12) — this one costs $0.76.
Cheaper and better on this index: GLM 5.3 Flash · Gemini 3.7 Flash · Gemini 3.7 Flash (batch) and 48 more
About this model
GLM 4.6 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 4.6?
GLM 4.6 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 23.4 on the Artificial Analysis intelligence index.
Is GLM 4.6 free?
The weights are free and open — you can self-host GLM 4.6 and pay nothing per token. If you prefer a hosted API, list prices are $0.43 per million input tokens and $1.75 per million output tokens.
What is GLM 4.6 good at?
Independent benchmarks from Artificial Analysis give it GPQA 63.2%, MMLU-Pro 78.4%, Humanity's Last Exam 5.5%, Long Context Reasoning 28.3%, LiveCodeBench 56.1%, SciCode 33.1%, AIME 2025 44.3%, IFBench 36.7%, τ²-Bench 76.9%, Terminal-Bench Hard 28.8%. It is particularly used for mathematical reasoning.
Can I self-host GLM 4.6?
Yes. GLM 4.6 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.