The Continuity Layer
Inference APIs · Together AI

Together AI: what it charges, what it allows, and what it keeps

thecontinuitylayer.com/inference-apis/together-ai

A hosted inference platform that serves open models through one API, billed per token.

B3½/5
Score · #9 of 14
Inference host
Kind
Checked 3 November 2026
  1. 1

    Does Together AI publish a per-token price?

    Yes

    Yes, by Together AI's own page.

    The public pricing page lists serverless rates per model without a sign-in; gpt-oss-120B costs $0.15 per 1M input tokens and $0.60 per 1M output tokens.

    Yes means: Per-token prices are on a public page with no sign-in. Partly means only some models are priced in public, or the price sits on a model page rather than the pricing page.

    Together AI's own pageChecked 3 November 2026together.ai ↗
  2. 2

    Does Together AI publish its rate limits?

    No

    No, by Together AI's own page.

    The rate-limits doc publishes no request or token limits per tier; it calls serverless use best-effort and says busy periods can return 429 or 503 errors.

    Yes means: The docs give request or token numbers for each tier or model. Partly means some numbers, such as a concurrency cap or the top tiers only; no means the numbers are only shown inside a signed-in account.

    Together AI's own pageChecked 3 November 2026docs.together.ai ↗
  3. 3

    Does Together AI train on your API prompts by default?

    No

    No, by Together AI's own page.

    Sharing data to train models is opt-in and off by default, though stored prompts may still be used for product improvements.

    Yes means: Here no is the good answer: the provider's page says what you send its API is not used for training unless you opt in. Yes means it is unless you opt out; partly means it depends on the plan, the tier or the upstream provider.

    Together AI's own pageChecked 3 November 2026docs.together.ai ↗
  4. 4

    Does Together AI say how long it keeps your prompts and outputs?

    Partly

    Partly, by Together AI's own page.

    Prompts and responses are stored by default with no stated time limit; customers can delete them or turn on zero data retention.

    Yes means: A stated period, or a statement that nothing is kept by default. Partly means a period for some users or requests but not others.

    Together AI's own pageChecked 3 November 2026docs.together.ai ↗
  5. 5

    Does Together AI run a public status page?

    Yes

    Yes, by Together AI's own page.

    A public status page shows component uptime, incidents and subscription options.

    Yes means: A public page shows current uptime and past incidents.

    Together AI's own pageChecked 3 November 2026status.together.ai ↗

Every grade above is read from Together AI's own page on the day shown. If a page has changed, tell us.