/together/models/search

POST /api/together/models/search

Price: 20 credits

Search the Together AI model catalogue: provider, API model id, category tags, feature tags, listed prices and parameter size per model.

How to use it

Use it to see what Together AI hosts and what it charges. Each entry in `prices` names its own `unit` — 1M tokens for language models, image, video, min or MP for media models — so compare only prices with the same unit. Feed `alias` into together/models for the full specification, benchmarks and model card.

Parameters

• access-token string required

Request body

• timeout integer — Max scrapping execution timeout (in seconds) (default: 300; min: 20; max: 1500)
• query string nullable — Keep only models whose name, alias, API model id or provider contains this text (examples: "kimi")
• categories array nullable — Keep only models tagged with any of these categories (one of: "chat", "reasoning", "vision", "code", "llm", "image", "video", "audio", "transcribe", "moderation", "embeddings", "rerank"; examples: ["image"])
• providers array nullable — Keep only models from these providers, by provider name (examples: ["Qwen"])
• count integer required — Max number of models to return (min: 1)

Response

• @type string (default: "TogetherModelCard")
• alias string required
• url string required
• name string required
• image string nullable
• provider_name string nullable
• api_model_id string nullable
• primary_category string nullable
• categories array (default: [])
• features array (default: [])
• prices array (default: [])
  • @type string (default: "TogetherCardPrice")
  • label string required
  • unit string nullable
  • price number nullable
  • price_text string required
• parameters string nullable
• context_length string nullable
• deployment string nullable

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 — The entity was not found, or a precondition failed 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.