Nexra
All connectors
Implemented
AI, documents, knowledge & search
OpenAI logo

OpenAI

Embeddings, schema-validated data extraction, content moderation and file metadata from your OpenAI project.

Generate text from business data using your OpenAI project.

Build a flow with OpenAIProvider API documentation

Source actions

2

Destination actions

4

Data types

6

Validation status

Implemented · fixture tested.

Implementation is checked against provider-shaped fixtures for every action, authentication failures, rate limits, pagination and duplicate safety. Provider sandbox and authorised account validation are recorded separately when credential-backed runs are completed.

What you can map

embeddings
  • Create embeddings
    Destination
    Not retried automatically

    Vector embeddings for one text or a list of texts, one record per input in order.

extraction
  • Extract structured data
    Destination
    Not retried automatically

    Extracts a JSON object that conforms to your schema from input text using the Responses API with Structured Outputs.

files
  • List files
    Source

    File metadata in the project (no file contents).

models
  • List Models
    Source

    List operation for Models.

moderation
  • Classify content for moderation
    Destination
    Not retried automatically

    Classifies text with the moderation model and returns flagged categories and scores.

text
  • Create Text
    Destination
    Not retried automatically

    Create operation for Text.

Authentication

Project API key

Plans and access

OpenAI API platform projects with billing enabled. Model availability and rate limits follow the project's usage tier and the key's project permissions.

Test environment

There is no sandbox; use a separate project with a low spend limit for testing.

Rate limits

Requests and tokens per minute per model, by usage tier; HTTP 429 with x-ratelimit-* headers.

Provider events

OpenAI webhooks for background responses, batches and fine-tuning jobs. Nexra event triggers are not yet available; flows run on demand or on a schedule.

Before you build a flow

  • Authenticated model discovery and bounded text generation. Select a model available to your key. Generation sends mapped content to the provider and incurs provider charges. Automatic retries are disabled; inspect usage before repeating an uncertain request. No agents, tool calls, image generation or embeddings. Credential-backed validation remains pending.
  • Embeddings, extraction and generation are billable and are never retried automatically; check usage before repeating an uncertain request.
  • Extraction sends store=false so OpenAI does not retain the response for later retrieval.
  • Batch, fine-tuning, file upload and assistant operations are not implemented.
  • Moderation is free but sends content to OpenAI; it is a destination step that must be enabled per connection.