/replicate/models

POST /api/replicate/models

Price: 5 credits

Get Replicate model details by identifier or URL

How to use it

Get full details of a Replicate AI model by identifier ('owner/name') or URL. Returns description, run count, pricing, hardware, official/commercial flags, source and paper links, the latest version, the full input/output schema, a default example run, and the readme.

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 identifier ('owner/name') or full model URL (examples: "black-forest-labs/flux-schnell", "https://replicate.com/lucataco/sdxl"; minLength: 1)

Response

• @type string (default: "ReplicateModel")
• id string required
• owner string required
• name string required
• url string required
• description string nullable
• run_count integer nullable
• image string nullable
• owner_avatar string nullable
• is_official boolean (default: false)
• is_pipeline boolean (default: false)
• is_commercial boolean (default: false)
• visibility string nullable
• user_type string nullable
• hardware string nullable
• run_state string nullable
• pricing string nullable
• price_p50 string nullable
• price_tiers array (default: [])
  • @type string (default: "ReplicatePriceTier")
  • price string required
  • unit string nullable
  • note string nullable
  • metric string nullable
  • price_type string nullable
• github_url string nullable
• paper_url string nullable
• weights_url string nullable
• license_url string nullable
• latest_version_id string nullable
• latest_version_created_at integer nullable
• input_schema array (default: [])
  • @type string (default: "ReplicateModelInput")
  • name string required
  • input_type string nullable
  • display_name string nullable
  • param_description string nullable
  • default_value any
  • minimum number nullable
  • maximum number nullable
  • enum_values array (default: [])
  • order integer nullable
• output_schema object nullable
• default_example object nullable
  • @type string (default: "ReplicateExample")
  • id string required
  • status string nullable
  • input object (default: {})
  • output any
  • error string nullable
  • created_at integer nullable
  • completed_at integer nullable
  • predict_time number nullable
  • created_by string nullable
  • version_id string nullable
• readme 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 — Model not found 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.