Embeddings

API version

2026-11-11 (latest)next (preview)

PreviewDownload OpenAPI (JSON)Versioning

Preview

next shows changes that are not released or not stable yet. Use the current version for production integrations.

Create embeddings

POST /api/v1/llm/v1/embeddings

768-dimensional float vectors from nebula-embed. Up to 256 inputs; each input at most 1,000 UTF-8 bytes, and the whole request at most 1,056 bytes including the task instruction added to each input. Metered at about 4 characters per token at the flat Nebula input rate. Requires llm:access or llm:embeddings.

Authentication

• API key in X-API-Key
• API key or session token in Authorization: Bearer

Headers

• Idempotency-Key string

  Run this exact request at most once in 24 hours. A replay with the same key and the same body, from the same organization, user and API key, is refused with 409 before any model call. See the Idempotency guide.

  Minimum length

  1

Request body

application/json Required

• model string

  Default

  nebula-embed

• input string or array of strings Required
• encoding_format string

  Only float is supported; anything else is 400. The OpenAI Python SDK sends base64 when this is omitted, so pass encoding_format="float" explicitly.

  One of

  float

  Default

  float

• dimensions integer

  One of

  768

  Default

  768

• task_type string

  The retrieval task the vectors are for. Use RETRIEVAL_DOCUMENT when indexing and RETRIEVAL_QUERY when searching.

  One of

  SEMANTIC_SIMILARITY RETRIEVAL_QUERY RETRIEVAL_DOCUMENT CODE_RETRIEVAL_QUERY CLASSIFICATION CLUSTERING

  Default

  SEMANTIC_SIMILARITY

• user string or null

Responses

• 200 The embeddings, in input order.

  application/json

  Body (application/json)

  • object string

    Always

    list

  • data array of objects
    3 fields in data

    • object string

      Always

      embedding

    • index integer
    • embedding array of numbers
  • model string
  • usage object
    2 fields in usage

    • prompt_tokens integer
    • total_tokens integer
• 400 The request was malformed or failed a server-side check.Error envelope
• 401 Missing, invalid, expired or revoked credentials.Error envelope
• 402 The organization has no spendable credit, or its self-service spend cap is reached. Top up or raise the cap in the console. This status currently carries message: "Error" and code: "INTERNAL_9001"; rely on the HTTP status.Error envelope
• 403 The credential is valid but lacks a required scope or permission.Error envelope
• 409 This exact request (same Idempotency-Key and body) already ran, so it was not run again. Send a new Idempotency-Key to run it again.Error envelope
• 429 A per-user limit was exceeded (the Platform API, embeddings or rerank). This response does not use the error envelope. Wait for Retry-After seconds.

  application/json

  Headers

  • X-Request-ID string

    The request's correlation id (yours, or one BreachLine generated). Quote it to support.

  • Retry-After integer

    Seconds to wait before retrying.

  Body (application/json)

  • detail string Required
  • retry_after integer Required

    Always

    60

• 503 A dependency is temporarily unavailable. Retry with backoff; honour Retry-After when present.Error envelope

Example

cURLCopy

curl -X POST "https://api.breachline.io/api/v1/llm/v1/embeddings" \
  -H "Authorization: Bearer $BREACHLINE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nebula-embed",
    "input": "Session cookie set without the Secure flag",
    "task_type": "RETRIEVAL_DOCUMENT"
  }'

Example 200 responseCopy

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [
        0
      ]
    }
  ],
  "model": "string",
  "usage": {
    "prompt_tokens": 0,
    "total_tokens": 0
  }
}