Evidence checked Nov 10, 2026

Verified Nov 10, 2026 via GLM-4.5: glm-4-5-model-projectAI models

GLM-4.5

The publisher describes GLM-4.5 as a foundation model with 355 billion total and 32 billion active parameters.

Verified facts
7
Offers
1
Sources
1
Pricing
Free offer

Overview

Model scope

The publisher describes GLM-4.5 as a foundation model with 355 billion total parameters and 32 billion active parameters. Its project describes thinking and non-thinking modes for different response workflows. These are supplier descriptions, not independently measured model quality or latency.

This entry counts the GLM-4.5 family once. Air, base, reasoning and quantized variants have different properties and should be checked individually rather than counted as copies of the same family.

Read the full editorial overview

Deployment and evidence

The project repository includes an Apache 2.0 code licence, while its README describes separate model-weight licensing. The exact model-weight licence was not independently verified; check the terms of the model asset before use.

The selected source does not establish comparable hosting charges, performance or service availability. Its README does list H100 GPU counts for GLM-4.5 inference in BF16 and FP8, and for using the full 128K context, under assumptions it states, including server memory above 1T; these are publisher figures for those configurations, not a capacity test or a universal requirement. No model weights, API key, account, inference run, benchmark or deployment test was used.

Sources

GLM-4.5: glm-4-5-model-source · Evidence: documentation · Not checked

Plans & prices

Prices as listed by GLM-4.5, before any tax or fee the pricing page does not state.

Scroll the table sideways for every column.

PlanRate period not statedCoverage limits
Plan: Self-hosted
FreeTax: Confirm at checkoutUpfront: not established
ConditionsPublisher project README at commit 170f20b captured 9 November 2026; supplier description, not a deployment, inference or independent test. The README says the GLM-4.5 and GLM-4.5-Air base, hybrid-reasoning and FP8 models are released under the MIT open-source license and can be used commercially. Applies to the downloaded open weights run on your own infrastructure; hardware, hosting, the Z.ai API Platform and other third-party services are priced separately and are not covered here.
Unknown fees: Infrastructure and third-party servicesVerified Nov 19, 2026
The README lists GLM-4.5 inference on 16 H100 GPUs in BF16 or 8 in FP8 (GLM-4.5-Air: 4 or 2), and 32 H100 in BF16 or 16 in FP8 (GLM-4.5-Air: 8 or 4) to use the full 128K context.
ConditionsPublisher project README at commit 170f20b captured 9 November 2026; supplier description, not a deployment, inference or independent test. Figures are the README's "full-featured" NVIDIA GPU inference configurations under the assumptions it lists just above the tables (MTP layers with speculative decoding, no CPU offload, inference batch size up to 8, FP8-capable devices, server memory above 1T), not a capacity or performance test. Ascend NPU and AMD GPU guides are linked separately.
Verified Nov 10, 2026

GLM-4.5: glm-4-5-model-project

Documented facts

Each fact comes from official documentation and shows when it was verified.

  • Who it is for

    The publisher describes GLM-4.5 as a foundation model with 355 billion total and 32 billion active parameters.

    Verified Nov 4, 2026 · GLM-4.5: glm-4-5-model-source

  • Coverage limits

    The captured GLM-4.5 project describes thinking and non-thinking modes.

    Verified Nov 4, 2026 · GLM-4.5: glm-4-5-model-source

  • API model identifier

    zai-org/GLM-4.5

    Publisher project README at commit 170f20b captured 9 November 2026; supplier description, not a deployment, inference or independent test. Hugging Face repository name of the GLM-4.5 weights in the README's download table; FP8, Air and Base variants have their own repository names.

    Verified Nov 10, 2026 · GLM-4.5: glm-4-5-model-project

  • Context window

    128,000 tokens in the context window

    Publisher project README at commit 170f20b captured 9 November 2026; supplier description, not a deployment, inference or independent test. The README says the GLM-4.5 models can use their full 128K context length on the larger GPU configurations it lists; GLM-4.6 expands the context to 200K tokens and is a different model. Hosted API limits may differ.

    Verified Nov 10, 2026 · GLM-4.5: glm-4-5-model-project

  • Availability

    GLM-4.5 (355B-A32B, BF16) open weights are listed on Hugging Face and ModelScope.

    Publisher project README at commit 170f20b captured 9 November 2026; supplier description, not a deployment, inference or independent test. The README's download table also has separate entries for the FP8, Air and Base variants. Download listing, not a statement of current hosted availability; the README also points to the Z.ai API Platform for GLM-4.7 API services. Licence is covered by the separate pricing fact.

    Verified Nov 10, 2026 · GLM-4.5: glm-4-5-model-project

Applies to the facts above: Publisher project README at captured revision, 4 November 2026. Model and configuration specific; source estimates are not independent tests or universal deployment guarantees. Separate model licence page unavailable.

Not confirmed in our sources

We have not confirmed these terms for GLM-4.5 in the linked documentation. That does not mean GLM-4.5 lacks them; confirm them before you rely on them.

  • Provider
  • Modalities
  • Maximum output
  • Input token rate
  • Output token rate

Sources & methodology

Facts come from the linked documentation. Documentation checks are not hands-on tests, and readable sources can have incomplete coverage.

GLM-4.5: glm-4-5-model-projectraw.githubusercontent.com
Retrieved Nov 10, 2026

Discovered an undocumented discrepancy or pricing shift? Submit a correction request.

Submit correction

GLM-4.5 alternatives

Other AI models tools to weigh. Different billing units do not establish a cost winner, so compare plans side by side.

GLM-4.5 comparisons

Compare two products in the same category using their documented terms and sources.