Model / inference API

Z.AI

Z.ai sells the GLM model family through its open platform API, and it suits developers who want GLM 5.3 straight from the maker, with free small models for testing.

Website (opens in a new tab)

Checked 2026-11-05

Z.ai sells the GLM model family through its open platform API, and it suits developers who want GLM 5.3 straight from the maker, with free small models for testing. The pricing page, as listed on 5 November 2026, lists USD per million tokens. GLM 5.3 is $1.4 input and $4.4 output, with cached input at $0.26. GLM 5.3 Flash is $0.15 and $0.50, and GLM 5.3 FlashX is $0.37 and $1.25. GLM 4.7 Flash, GLM 4.5 Flash and GLM 4.6V Flash are listed as free. The catch is that the page does not mention the GLM Coding Plan, so for that subscription use our separate guide rather than this page. The privacy documents say the company does not store the content you or your end users provide or generate through the API, with inputs processed in real time, and that processing is generally in Singapore. They do not say whether API inputs are used for training. Figures come from Z.ai's pricing page and privacy documents. We have not run it ourselves. We would use it to price GLM 5.3 Flash for cheap agent steps, and the free Flash models for a first test.

Mentioned here

Questions

How much does Z.AI cost?

Pay per million tokens, with cached input billed lower: GLM-5.3 is $1.4 input and $4.4 output, GLM-5.3-Flash is $0.15 and $0.50, and GLM-5.3-FlashX is $0.37 and $1.25. Tools, image and video models are priced separately on the same page (checked 5 November 2026).

Is Z.AI OpenAI compatible?

Yes, it offers an OpenAI-compatible API, so most agents and SDKs can point at it by changing the base URL.

Reviews

Loading reviews…

Write a review

Your rating

Up to 1000 characters. Stars alone are enough.

Similar

  • Moonshot AI

    Moonshot AI sells the Kimi API through its developer platform, now at platform.kimi.ai, and it suits teams who want Kimi K3 and K3.1 Pro with a 1,048,576-token context window straight from the maker.

    • Model / inference API
    • OpenAI compatible

  • Featherless

    Featherless is a flat-rate subscription for open models, not a per-token meter, and it suits hobbyists and small teams who want to switch between many open models for one monthly price.

    • Model / inference API
    • OpenAI compatible

  • Minimax

    MiniMax sells its model API through the MiniMax Open Platform, and it suits developers who want M3 or M3.1 Flash directly from the maker at a low token rate.

    • Model / inference API
    • OpenAI compatible

  • AI21

    AI21 sells the Jamba model family through an API, and it suits teams that want a long-context model from a vendor that says it does not train on customer inputs.

    • Model / inference API

  • Databricks

    Databricks sells model serving inside its data platform, so it suits teams that already keep data and pipelines on Databricks and want hosted open models next to them.

    • Model / inference API
    • OpenAI compatible

  • Nvidia

    NVIDIA's API platform at build.nvidia.com hosts models as NIM microservices on its DGX Cloud for trying out, and it suits developers who want to test Nemotron and other models before deciding where to run them.

    • Model / inference API