Get Model
jina.get_model
ActionAI & modelsconnection required
Calls the Jina AI API with the connection's credentials.
Fetch one model's metadata: modalities, context length, pricing and the datacenters that serve it.
Connection
- Required
- Yes — the node will not save without one
- Auth type
- Bearer token
- Providers
- Jina AI
- Secret shape
- the API key, or {"api_key": "…"}
- Config it needs
- base_url, default_embedding_model, default_reranker_model
- Resolved by
- config.connection_id, else node.connection_id
Configuration
1 field, 1 required. A dotted path is a nested object and name[] an array of objects — the editor renders the same tree.
| Field | Type | Required | Default | Constraints | Example |
|---|---|---|---|---|---|
model_id Model to look up, with or without the 'jina-ai/' prefix. | string | Yes | — | — | jina-embeddings-v3 |
Example configuration
Every value below is the contract’s own example or default — nothing invented.
{
"model_id": "jina-embeddings-v3"
}Output
One shape.
result
| Field | Type | Example |
|---|---|---|
id Model id. | string | — |
name Human-readable model name. | string | — |
description What the model is for. | string | — |
context_length Maximum context in tokens. | number | — |
max_output_length Maximum embedding dimensions. | number | — |
input_modalities Inputs the model accepts. | array | — |
output_modalities What the model produces. | array | — |
pricing Per-token pricing. | object | — |
{
"context_length": 0,
"description": "",
"id": "",
"input_modalities": [],
"max_output_length": 0,
"name": "",
"output_modalities": [],
"pricing": {}
}See Get Model run in a workflow.
In a technical demo we add the Jina AI connection, drop the node on the canvas and let Workflow Health pre-flight it before the first real run.