| name | keirouter-embeddings |
| description | Generate vector embeddings via KeiRouter /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text. |
KeiRouter — Embeddings
Requires KEIROUTER_URL (and KEIROUTER_KEY if auth enabled). See https://raw.githubusercontent.com/mydisha/keirouter/main/skills/keirouter/SKILL.md for setup.
Discover
curl $KEIROUTER_URL/v1/models/embedding | jq '.data[].id'
curl "$KEIROUTER_URL/v1/models/info?id=openai/text-embedding-3-small"
Endpoint
POST $KEIROUTER_URL/v1/embeddings
| Field | Required | Notes |
|---|
model | yes | from /v1/models/embedding |
input | yes | string OR array of strings |
encoding_format | no | float (default) / base64 |
dimensions | no | OpenAI v3 only |
Examples
curl -X POST $KEIROUTER_URL/v1/embeddings \
-H "Authorization: Bearer $KEIROUTER_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"openai/text-embedding-3-small","input":["hello","world"]}'
JS:
const r = await fetch(`${process.env.KEIROUTER_URL}/v1/embeddings`, {
method: "POST",
headers: { "Authorization": `Bearer ${process.env.KEIROUTER_KEY}`, "Content-Type": "application/json" },
body: JSON.stringify({ model: "gemini/text-embedding-004", input: "RAG chunk text" }),
});
const { data } = await r.json();
console.log(data[0].embedding.length);
Response shape
{ "object": "list", "model": "openai/text-embedding-3-small",
"data": [
{ "object": "embedding", "index": 0, "embedding": [0.0123, -0.045, ...] },
{ "object": "embedding", "index": 1, "embedding": [...] }
],
"usage": { "prompt_tokens": 5, "total_tokens": 5 } }
Provider quick reference
| Provider | Notes |
|---|
| OpenAI, Mistral, Voyage, Fireworks, Together, Nebius, NVIDIA, Jina | Native OpenAI shape — dimensions works only on OpenAI v3 (text-embedding-3-*) |
| Gemini | Server auto-converts to embedContent/batchEmbedContents — send OpenAI shape |
| Custom OpenAI | Custom baseUrl from credentials |
Batch (input as array) is faster; some providers cap batch size.
