/together/models

POST /api/together/models

Price: 10 credits

Get a Together AI model by alias: prices, specifications, modalities, deployment options, benchmarks and model card.

How to use it

The full record behind a together/models/search row. Media models carry `price` and `price_text` with their own unit instead of input and output token prices. `benchmarks` lists this model first, then rows for competitor closed-source models, when the model page publishes any.

Parameters

• access-token string required

Request body

• timeout integer — Max scrapping execution timeout (in seconds) (default: 300; min: 20; max: 1500)
• model string required — Model alias or model page URL (examples: "kimi-k3", "https://www.together.ai/models/kimi-k3"; minLength: 1)

Response

• @type string (default: "TogetherModel")
• alias string required
• url string required
• name string required
• description string nullable
• provider_name string nullable
• provider_url string nullable
• provider_image string nullable
• api_model_id string nullable
• category string nullable
• types array (default: [])
• use_cases array (default: [])
• features array (default: [])
• deployments array (default: [])
• input_modalities array (default: [])
• output_modalities array (default: [])
• intelligence_level string nullable
• speed_level string nullable
• parameters string nullable
• activated_parameters string nullable
• context_length string nullable
• quantization string nullable
• resolution_duration string nullable
• input_price number nullable
• cached_input_price number nullable
• output_price number nullable
• price number nullable
• input_price_text string nullable
• output_price_text string nullable
• price_text string nullable
• release_date string nullable
• updated_date string nullable
• external_url string nullable
• other_specifications array (default: [])
  • @type string (default: "TogetherNamedValue")
  • name string required
  • value string nullable
  • text string nullable
• highlights array (default: [])
  • @type string (default: "TogetherNamedValue")
  • name string required
  • value string nullable
  • text string nullable
• key_capabilities array (default: [])
  • @type string (default: "TogetherNamedValue")
  • name string required
  • value string nullable
  • text string nullable
• benchmarks array (default: [])
  • @type string (default: "TogetherBenchmarkRow")
  • model_name string required
  • image string nullable
  • group string nullable
  • scores array (default: [])
    • @type string (default: "TogetherBenchmarkScore")
    • benchmark string required
    • value string required
• sections array (default: [])
  • @type string (default: "TogetherNamedValue")
  • name string required
  • value string nullable
  • text string nullable
• related_model_aliases array (default: [])

Errors

• 422 — The request body did not validate Check the fields against this schema. A URN with the wrong prefix is the most common cause.
• 408 — The request ran past its time limit Raise `timeout` in the request body, up to the maximum this endpoint documents. Lowering `count` or turning off the `with_*` flags also helps, because less work finishes sooner.
• 412 — No Together AI model with that alias Retrying will not help: either the entity does not exist, or the input points at a different one.
• 429 — Too many requests: a rate limit or a usage window is exhausted When the response carries an X-Retry-After header, wait that many seconds and retry: the same number is in the body as `detail.retry_after`, and the limit clears once that window passes. The message in the body names the limit that was hit.
• 500 — Something broke on our side Retrying will not help. If it keeps happening, send us the X-Request-ID from the response headers.
• 529 — Rate limit reached, or the endpoint is overloaded Wait at least 30 seconds, then retry.

Response headers

• X-Error — Error message text (present only on error)
• X-Request-ID — Unique request identifier
• X-Execution-Time — Execution time in seconds
• X-Result-Count — How many records the body carries. 0 means an empty result, which is a normal answer and not by itself an error. A non-zero count can come back together with X-Error when the failure happened partway through — read this header and X-Error independently.
• X-Total-Available-Results — How many records exist for this query, when the endpoint can say. On a `dry_run` request this is the answer and the body is empty. It saturates: the endpoint's documented maximum means 'at least that many', any smaller number is exact.
• X-Warning — Present when the request body carried keys this endpoint does not document. They were ignored, so any filter you meant to apply through them did not apply. Check the spelling against this schema and retry.
• X-Retry-After — Seconds to wait before retrying. Present only on 429.