Model / inference API

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.

Website (opens in a new tab)

Checked 2026-11-05

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. Its pricing page, as listed on 5 November 2026, shows three plans. Chat is $25 per month with 4 concurrent units and 32K context. Developer is listed at $50 per month in credits, with 100 concurrent units and context up to 256K, though the billing wording was unclear to us. Business is custom, on annual contracts and sized to your GPUs. The page says 40,000 or more open models are available on every plan. The catch is concurrency: a coding agent that fans out several calls at once will hit the 4-unit limit on the cheapest plan. On data, both the page footer and the privacy policy say prompts and completions are never stored, though the policy collects usage counts such as tokens in and out. It does not say whether data is used for training, gives no retention period for account data, and says it does not transfer personal data internationally. Figures come from Featherless's pricing page and privacy policy. We have not run it ourselves. We would use it for model hopping on a fixed budget.

Mentioned here

Questions

How much does Featherless cost?

Flat monthly plans for open models: Chat is $25 a month with unlimited tokens and 32K context for interactive use, and Developer is $50 a month in credits billed per token with context up to 256K for agents and API traffic. Business is custom, on dedicated GPUs (checked 5 November 2026).

Is Featherless 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

  • 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

  • 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