/groq/models

POST /api/groq/models

Price: 10 credits

Get a GroqCloud model or Compound system by id: pricing, token limits, modalities, capabilities, quantization and usage guidance.

How to use it

The full record behind a groq/models/search row, for models and Compound systems alike. A system has no token price of its own: read `underlying_model_prices` and `tool_prices`. Enterprise models carry no price fields at all.

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 or Compound system id, or its GroqCloud docs page URL (examples: "openai/gpt-oss-120b", "groq/compound", "https://console.groq.com/docs/model/whisper-large-v3"; minLength: 1)

Response

• @type string (default: "GroqModel")
• id string required
• url string required
• name string required
• model_type string required
• description string nullable
• provider_name string nullable
• provider_image string nullable
• model_card_url string nullable
• tokens_per_second integer nullable
• input_modalities array (default: [])
• output_modalities array (default: [])
• capabilities array (default: [])
  • @type string (default: "GroqNamedValue")
  • name string required
  • value string nullable
  • url string nullable
  • text string nullable
• notices array (default: [])
• input_price number nullable
• cached_input_price number nullable
• output_price number nullable
• other_prices array (default: [])
  • @type string (default: "GroqNamedValue")
  • name string required
  • value string nullable
  • url string nullable
  • text string nullable
• underlying_model_prices array (default: [])
  • @type string (default: "GroqUnderlyingModelPrice")
  • model_name string required
  • input_price number nullable
  • output_price number nullable
  • input_price_text string nullable
  • output_price_text string nullable
• tool_prices array (default: [])
  • @type string (default: "GroqNamedValue")
  • name string required
  • value string nullable
  • url string nullable
  • text string nullable
• pricing_note string nullable
• context_window integer nullable
• max_output_tokens integer nullable
• max_file_size string nullable
• other_limits array (default: [])
  • @type string (default: "GroqNamedValue")
  • name string required
  • value string nullable
  • url string nullable
  • text string nullable
• quantization string nullable
• architecture string nullable
• performance string nullable
• use_cases array (default: [])
  • @type string (default: "GroqNamedValue")
  • name string required
  • value string nullable
  • url string nullable
  • text string nullable
• best_practices 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 GroqCloud model or system with that id 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.