GET
/v1/schemas/llmgateway/embeddings/v1%2Fembeddings
Accept:
kind inputactivity embeddingshash 6bd150aa…extracted Nov 20, 2026version currentsource upstream spec ↗
Request body
5 properties · 2 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| input* | string | string[] | integer[] | … | Input text to embed. A single string, an array of strings, an array of token IDs, or an array of token-ID arrays. Cannot exceed the model's max input tokens (8192 for OpenAI text-embedding-3 and ada-002). | |
| model* | string | ID of the embedding model to use. | |
| encoding_format | enum | Format of the returned embeddings. `float` returns plain arrays, `base64` returns a packed base64 string. | float | base64 |
| dimensions | integer | Number of dimensions for the output embeddings. Only supported by models that allow shortening output (e.g. `text-embedding-3-*`, `gemini-embedding-*`, `qwen3-embedding-8b`). | n ≥ 0 |
| user | string | Opaque end-user identifier stored in log params.safety_identifier (up to 128 characters). Credits requests use LLM Gateway's fixed per-organization identifier upstream; BYOK requests omit it. |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"llmgateway","endpointId":"v1/embeddings","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}