GLM 4.5: pricing, context and benchmarks

What you need to know about GLM 4.5

Z.ai (Zhipu), based in China, put GLM 4.5 online on July 25, 2025. It accepts text as input and produces text. Its context window reaches 131,072 tokens, larger than 29 % of the models in the registry, and it can write up to 98,304 tokens in one go.

It has been available for about 15 months, long enough for its prices and scores to have settled.

GLM 4.5 pricing

On OpenRouter, GLM 4.5 costs $0.6 per million input tokens and $2.2 per million output tokens. Counting three tokens read for every token written, its average price is $1 per million, more expensive than 59 % of paid models (1.3 times the median of $0.76).

A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0023. At 1,000 tasks a day, budget $69 a month. The price calculator redoes this with your own volumes.

Tokens already sent and cached are billed at $0.11 per million.

Performance and benchmarks

Epoch AI does not yet publish a capabilities index for GLM 4.5. We therefore show no made-up performance rating: only price, context and features count towards its score.

Features, privacy and local use

• It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
• It can answer in an enforced JSON format (structured outputs).
• It is a reasoning model: it "thinks" before answering, which helps on hard tasks but uses more output tokens.
• Its knowledge stops at December 2024.

Its weights are open and downloadable from Hugging Face (mit licence): you can run it on your own machines without sending your data to a third party. With 358,337,791,296 billion parameters, it needs about 200,236,844,623 GB of memory at 4-bit quantisation. Check with the VRAM calculator. It was downloaded 113,824 times on Hugging Face last month.

Other Z.ai (Zhipu) models