Model / inference API

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.

Website (opens in a new tab)

Checked 2026-11-05

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. Its pricing page, as listed on 5 November 2026, offers Pay As You Go, Free Trial and Custom Plan. Jamba Mini is $0.2 per million input tokens and $0.4 per million output tokens. Jamba Large is $2 and $8. The free trial gives $10 in credits for 7 days with no credit card. The catch is that these are the only two models priced on the page, and we did not read context sizes from it. On data, the privacy policy says that for business customers AI21 acts as a processor, so the customer agreement governs, and that AI21 does not use your inputs or outputs to train its foundational or generally available models unless agreed in writing or needed to provide the service. It says the service is not a storage product, so keep your own copies. Data may be processed in Israel, the United States, the EEA and the UK. Figures come from AI21's pricing page and privacy policy. We have not run it ourselves. We would use it to test Jamba on long documents, not as a coding agent default.

Mentioned here

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

  • 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.

    • 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

  • 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