/modelscope/models/search

POST /api/modelscope/models/search

Price: 10 credits

Search ModelScope models

How to use it

Search ModelScope models by keyword and filters: task, library, license, architecture, language, tag, organization, and inference state. Sort by trending, downloads, or likes. Returns matching models with downloads, likes, tasks, tags, libraries, and license.

Parameters

• access-token string required

Request body

• timeout integer — Max scrapping execution timeout (in seconds) (default: 300; min: 20; max: 1500)
• keyword string nullable — Free-text search keyword (examples: "qwen")
• organization string nullable — Filter by organization/owner namespace (examples: "Qwen")
• tasks array nullable — Filter by task codes (examples: ["text-generation","text-to-image-synthesis"])
• libraries array nullable — Filter by library codes (pytorch, safetensors, transformer, gguf, diffusers, lora, onnx, tensorflow, mlx, openvino, llamafile, sentence-transformers, ...) (examples: ["transformer","safetensors"])
• licenses array nullable — Filter by license codes (examples: ["apache-2.0","mit"])
• architectures array nullable — Filter by model architecture / model_type codes (examples: ["qwen2","llama"])
• languages array nullable — Filter by language codes (examples: ["zh","en"])
• tags array nullable — Filter by tag codes (examples: ["chat","code"])
• inference_state string nullable — Filter by inference API availability state (one of: "HOT", "STANDBY")
• sort string — Sort order (default: "trending"; one of: "trending", "downloads", "likes")
• count integer required — Max result count (min: 1)

Response

• @type string (default: "ModelScopeModel")
• id string required
• url string required
• name string nullable
• owner string nullable
• chinese_name string nullable
• description string nullable
• download_count integer nullable
• like_count integer nullable
• tasks array (default: [])
  • @type string (default: "ModelScopeTask")
  • name string required
  • chinese_name string nullable
  • domain string nullable
• tags array (default: [])
• libraries array (default: [])
• license string nullable
• license_name string nullable
• license_url string nullable
• languages array (default: [])
• model_type array (default: [])
• architectures array (default: [])
• model_size integer nullable
• tensor_types array (default: [])
• base_models array (default: [])
• base_model_relation string nullable
• domain array (default: [])
• frameworks array (default: [])
• created_by string nullable
• created_at integer nullable
• updated_at integer nullable
• revision string nullable
• image string nullable
• cover_images array (default: [])
• storage_size integer nullable
• visibility integer nullable
• readme string nullable
• related_arxiv_ids array (default: [])
• related_paper_ids array (default: [])
• organization object nullable
  • @type string (default: "ModelScopeOrganization")
  • id integer nullable
  • name string nullable
  • full_name string nullable
  • image string nullable
  • github_url string nullable
  • created_at integer nullable
  • updated_at integer nullable
• files array (default: [])
  • @type string (default: "ModelScopeInlineFile")
  • name string required
  • size integer nullable
  • sha256 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.