Claude · Anthropic

Schema-shaped data extraction with Claude, token counting and Message Batches status for your Anthropic workspace.

Summarise and process business text with Claude.

Build a flow with Claude · Anthropic Provider API documentation

Source actions

Destination actions

Data types

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

extraction

Extract structured data
Destination
Not retried automatically
Extracts a JSON object matching your schema from input text by forcing a Claude tool call.

message batches

Get message batch
Source
Processing status and request counts for one message batch.
List message batches
Source
Message batches in the workspace, newest first, with processing counts.

message tokens

Count message tokens
Source
Counts the input tokens a message would use, including system prompt and optional extraction schema, without running the model.

models

List Models
Source
List operation for Models.

text

Create Text
Destination
Not retried automatically
Create operation for Text.

Authentication

Workspace API key

Plans and access

Anthropic API (Claude Console) organisations with credits or billing. Keys are scoped to a workspace; model access and limits follow the usage tier.

Test environment

Use a separate workspace with a spend limit for testing.

Rate limits

Requests, input tokens and output tokens per minute per model; token counting and batches have separate limits. HTTP 429 with retry-after.

Provider events

None for the Messages API. 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.
Extraction is billable and never retried automatically; check usage before repeating an uncertain request.
Extraction uses native structured outputs (output_config.format json_schema); schemas must use the JSON Schema subset Anthropic documents. Check the valid flag for refusals or truncated output.
Message batches are read only; creating, cancelling and downloading batch results are not implemented.