OpenAI · Text

OpenClaw x Embedding

OpenAI Embedding models expose the standard OpenAI Embeddings API through RunAPI, so vector search and RAG pipelines can use the same RunAPI key as GPT chat and Responses traffic.

3 variants from $0.02 / 1M tokens Commercial OK
Get API Key View OpenClaw Docs

Prerequisite: npx runapi mcp install

Prompt

Prompt models

Use text-embedding-3-large when it matches the task: High-capacity text vectors for retrieval and ranking quality.

You have access to RunAPI task tools for Embedding.

Available Embedding models:
- text-embedding-3-large: High-capacity text vectors for retrieval and ranking quality
  endpoints: /v1/embeddings
  request fields: model, input
- text-embedding-3-small: Efficient text vectors for production semantic search
  endpoints: /v1/embeddings
  request fields: model, input
- text-embedding-ada-002: Broadly supported text embeddings for existing pipelines
  endpoints: /v1/embeddings
  request fields: model, input

Use the model ID and endpoint that match the user's request.
Example prompt: Embed these support articles and a customer query so I can rank the closest matches.
/v1/embeddings: Submit the request and verify the synchronous output. POST /v1/embeddings. Verify that the response contains a numeric embedding vector.

Public Versions and Endpoints

Model ID Endpoints Price Catalog
text-embedding-3-large
/v1/embeddings
$0.13 / 1M tokens Model detail
text-embedding-3-small
/v1/embeddings
$0.02 / 1M tokens Model detail
text-embedding-ada-002
/v1/embeddings
$0.10 / 1M tokens Model detail

Verify

Poll until the task reaches a terminal status

Select <model-id> to generate verification commands.

Configuration

Guide endpoint: <endpoint>

Select <model-id> to generate a request with the endpoint's public input contract.
How it works

Get Started in 3 Steps

  1. Choose a model ID

    Select a public catalog model ID and review its endpoint and current starting price.

  2. Configure RunAPI

    Set RUNAPI_API_KEY before making the endpoint request.

  3. Verify the result

    For asynchronous endpoints, poll the same endpoint until the Task reaches a terminal status.

What to Build with OpenClaw + Embedding

  • Structured results for your code

    Get machine-readable output instead of chat text, so your application can store it, compare it, or act on it directly.

  • Enriching your own data

    Run documents, images, or records through the model and keep the results next to the source data for later steps.

  • High-volume processing

    Send large batches of inputs with the same RunAPI key and collect the results programmatically.

Why Use Embedding Through RunAPI + OpenClaw

  • 3 variants, one API key

    Use one RunAPI connection to choose among the live model variants without changing your integration.

  • Clear usage pricing

    See current catalog pricing before you send a request, with no subscription or minimum spend required.

  • Direct responses

    Synchronous calls return the result in the same response, so your agent can use it immediately without task polling.

OpenClaw + Embedding Questions

Which embedding model should I use?

Use text-embedding-3-small for efficient production retrieval and text-embedding-3-large when recall quality matters more than vector size.

Can I shorten the embedding vector?

Yes — pass the dimensions parameter with text-embedding-3-large or text-embedding-3-small when you need smaller vectors.

Does the endpoint return the standard OpenAI response shape?

Yes — /v1/embeddings returns an OpenAI-compatible list response with embedding data, model, and usage.

Can embedding models be used with Chat Completions or Responses?

No — embedding models are only available on /v1/embeddings.

What inputs are supported?

Use a string, an array of strings, or token arrays following the OpenAI Embeddings API format.

Which model ID should I use?

Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.

Does this guide configure a chat model?

No. This Model Line uses the endpoint workflow shown here and is not presented as an agent chat model.

Start using Embedding with OpenClaw

Get API Key Read Quickstart

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.

Contact Us