GET
/v1/schemas/jina/embeddings/v1%2Fbatch%2Fembeddings
Accept:
kind inputactivity embeddingshash dcf02f52…extracted Aug 15, 2026version currentsource upstream spec ↗
Request body
7 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| model* | enum | The embedding model to use for batch processing. | jina-embeddings-v5-text-nano | jina-embeddings-v5-text-small |
| input_url | string | URL to input JSONL file (GCS, S3, or HTTP). Either input_url or input must be provided. | nullable |
| input | object[] | Inline JSONL lines for small batches. Either input_url or input must be provided. | nullable |
| task | string | Task optimization: retrieval, text-matching, clustering, or classification. | nullable |
| dimensions | integer | Number of dimensions for output embeddings (1-1024). | 0 < n ≤ 1024 · nullable |
| normalized | boolean | If true (default), embeddings are L2-normalized to unit length. | nullable |
| webhook_url | string | URL to POST notification when job completes. | nullable |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"jina","endpointId":"v1/batch/embeddings","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}