Z.ai: GLM-4.5

byZ.ai
Official docs

GLM-4.5 is a reasoning model from Z.ai released on Jul 28, 2025. It reads text and writes text, with a 131K token context window and up to 98K tokens per reply.

Show more

It costs $0.60 per million input tokens and $2.20 per million output tokens. Cached input bills at $0.11, 82% less than fresh input.

It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.

16 providers serve it, including Hugging Face, Vercel AI Gateway and submodel. The lowest input price is $0.20 per million tokens at submodel.

Modalities
In / out price
$0.60 / $2.20 per 1M
Context
131K
Max output
98K
Released
Jul 28, 2025
Knowledge cutoff
Apr 2025
  • Tool calling
  • Structured output
  • Reasoning
  • Prompt caching
  • Open weights
  • Free to use

GLM-4.5 pricing

USD, as listed on Nov 18, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.

Input$0.60 / 1M tokens
Output$2.20 / 1M tokens
Cached input (read)$0.11 / 1M tokens
Cache write$0 / 1M tokens

GLM-4.5 providers

16 providers serve it, including Hugging Face, Vercel AI Gateway and submodel. The lowest input price is $0.20 per million tokens at submodel. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.

ProviderInput /MOutput /MCache read /MContextMax output
Zhipu AI First party$0.60$2.20$0.11131K98K
Hugging Face$0.60$2.20n/a131K98K
Vercel AI Gateway$0.60$2.20$0.11128K96K
submodel$0.20$0.80n/a131K131K
302.AI$0.286$1.14n/a131K98K
ZenMux$0.2911$1.16$0.0582128K96K
DevPass (LLM Gateway)$0.60$2.20$0.11128K98K
Impossibl$0.60$2.20$0.11131K98K
Jiekou.AI$0.60$2.20n/a131K98K
Kilo Gateway$0.60$2.20$0.11131K98K
LLM Gateway$0.60$2.20$0.11128K98K
Merge Gateway$0.60$2.20$0.11128K98K

Showing 12 of 16 providers: the lab first, then the major clouds, then the cheapest resellers.

What GLM-4.5 costs per month

Pick a workload close to yours or type your own volumes.

GLM-4.5 per month
$46.05
Without caching
$68.10
Per request
$0.0015

Supported request parameters

What you can set when you call GLM-4.5 through an OpenAI compatible API.

  • Toolstools
  • Structured outputsstructured_outputs
  • Reasoningreasoning
  • Temperaturetemperature

Alternatives to GLM-4.5

Models that take the same inputs and call tools, closest in price, cheaper ones first.

  • Reads text. Tool calling, structured output, reasoning. Served by 73 providers.

    by deepseekApr 24, 20261.05M context$0.66/M input tokens$1.98/M output tokens73 providers

  • Reads text, images and files. Tool calling, structured output, reasoning. Served by 4 providers.

    by amazonDec 2, 20251M context$0.33/M input tokens$2.75/M output tokens4 providers

  • Reads text. Tool calling, structured output, reasoning. Served by 21 providers.

    by nvidiaJun 4, 20261M context$0.50/M input tokens$2.20/M output tokens21 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 31 providers.

    by googleJul 21, 20261.05M context$0.30/M input tokens$2.50/M output tokens31 providers

  • Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 25 providers.

    by googleJun 17, 2025$0.30/M input tokens$2.50/M output tokens25 providers

  • Index 25.2

    Reads text, images and video. Tool calling, structured output, reasoning. Served by 27 providers.

    by qwenJun 2, 20261M context$0.40/M input tokens$1.60/M output tokens27 providers

More from Z.ai

  • Reads text, images and video. Tool calling, structured output, reasoning. Served by 3 providers.

    by z-aiNov 2, 2026$0.37/M input tokens$1.25/M output tokens3 providers

  • Reads text and images. Tool calling, reasoning.

    by z-aiOct 5, 2026$0.15/M input tokens$0.50/M output tokens

  • Reads text and images. Tool calling, reasoning.

    by z-aiOct 5, 2026$0.15/M input tokens$0.50/M output tokens

  • Reads text. Tool calling, reasoning.

    by z-aiSep 26, 2026$1.25/M input tokens$2.25/M output tokens

  • Reads text. Tool calling, reasoning. Served by 2 providers.

    by z-aiSep 23, 2026$1.68/M input tokens$5.28/M output tokens2 providers

  • Reads text and images. Tool calling, reasoning.

    by z-aiSep 19, 2026$0.15/M input tokens$0.50/M output tokens

All Z.ai models

GLM-4.5 questions

How much does the GLM-4.5 API cost?

$0.60 per million input tokens and $2.20 per million output tokens, with cached input at $0.11. The estimator on this page turns that into a monthly bill for your own workload.

What is the context window of GLM-4.5?

131,072 tokens of input, and it can write up to 98,304 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.

Which providers serve GLM-4.5?

16 providers serve it, including Hugging Face, Vercel AI Gateway and submodel. The lowest input price is $0.20 per million tokens at submodel. Prices differ by host, so the Providers table on this page lists each one with its input and output price.

Does GLM-4.5 support tool calling?

Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.

Is GLM-4.5 open source?

Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.

When was GLM-4.5 released?

Jul 28, 2025, with training data up to Apr 2025.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Nov 18, 2026. The summary is written from these facts.