NUDG3 Chat API
The Chat API from NUDG3 — 6 operation(s) for chat.
The Chat API from NUDG3 — 6 operation(s) for chat.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/nudg3-ai:nudg3-ai-chat-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: Nudg3 Chat API
description: '# Nudg3 Brand Intelligence API
The Nudg3 API provides programmatic access to brand visibility analytics across AI providers.
## Public API v1
The Public API (`/api/v1/`) is designed for third-party integrations and provides:
### Analytics Endpoints (Tier 1 - Basic)
- Brand visibility scores and trends
- Sentiment analysis across AI responses
- Source citation tracking
- Prompt performance metrics
- Google AI Overview (AIO) coverage
### Export Endpoints (Tier 2 - Premium)
- Full response data exports (CSV/TSV)
- Source citations bulk download
- Dashboard time-series data
- Prompt-mention pair exports
## Authentication
### API Key (Public API v1)
```bash
curl -H "Authorization: Bearer nudg3_live_ak_xxx..." \
https://api.nudg3.com/api/v1/dashboard
```
### JWT (Dashboard API)
```bash
curl -H "Authorization: Bearer eyJ..." \
https://api.nudg3.com/analytics/dashboard
```
## Rate Limits
| Tier | Per Minute | Per Hour | Monthly Quota |
|------|------------|----------|---------------|
| Basic | 60 | 600 | 5,000 |
| Premium | 300 | 3,000 | 50,000 |
## Response Format
All responses follow a standard envelope:
```json
{
"success": true,
"data": { ... },
"message": "Success"
}
```
## Support
- Documentation: https://docs.nudg3.com
- API Status: https://status.nudg3.com
- Support: support@nudg3.com'
version: 1.1.0
termsOfService: https://nudg3.com/terms
contact:
name: Nudg3 API Support
url: https://nudg3.com/support
email: support@nudg3.com
license:
name: Proprietary
url: https://nudg3.com/license
servers:
- url: https://api.nudg3.com
description: Production API
- url: https://api-staging.nudg3.com
description: Staging API (for testing)
- url: http://localhost:8000
description: Local Development
tags:
- name: Chat
paths:
/chat/message:
post:
tags:
- Chat
summary: Send Chat Message
description: 'Send a message to the workspace chat agent.
The agent has access to analytics tools scoped to the authenticated user''s
workspace. It can answer questions about:
- Brand visibility and sentiment
- Competitor analysis
- Source citations
- Prompt performance
- Provider comparisons
**Security Model:**
- Requires valid JWT token
- Workspace access is validated against user permissions
- Agent receives workspace_id from session (never from user input)
**Request Body:**
- workspace_id: UUID of the workspace to query
- message: User''s question (1-2000 characters)
- conversation_id: Optional ID for multi-turn conversations
- conversation_history: Optional list of previous messages for HITL context
**Response:**
- message: Assistant''s response
- conversation_id: ID for continuing the conversation
- tool_calls: List of tools called to generate the response'
operationId: send_chat_message_chat_message_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ChatMessageRequest'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/SuccessResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- HTTPBearer: []
/chat/message/stream:
get:
tags:
- Chat
summary: Stream Chat Message
description: 'Stream chat response via Server-Sent Events (SSE).
This endpoint provides real-time streaming of AI agent responses,
enabling progressive rendering in the frontend.
**Security:**
- Firebase token validated from query parameter
- Workspace access verified before streaming
- Agent JWT created for backend API calls
**SSE Events:**
- `connecting` - Initial connection established
- `state_update` - Full state snapshot (messages, tool_calls_info)
- `tool_update` - Individual tool execution update
- `content_update` - AI response content update
- `blocked` - Content blocked by safety filters (reason, message, safety_ratings, request_id)
- `warning` - Non-fatal warning e.g. token budget exceeded (message, request_id)
- `error` - Error occurred (message, error_type, request_id)
- `end` - Stream completed successfully
**Note:** Token is passed as query parameter because the EventSource
API does not support custom headers.
**Example:**
```javascript
const eventSource = new EventSource(
`/chat/message/stream?workspace_id=${id}&message=${msg}&token=${token}`
);
eventSource.addEventListener(''content_update'', (e) => {
const data = JSON.parse(e.data);
updateContent(data.content);
});
```'
operationId: stream_chat_message_chat_message_stream_get
parameters:
- name: workspace_id
in: query
required: true
schema:
type: string
format: uuid
description: Workspace ID to query
title: Workspace Id
description: Workspace ID to query
- name: message
in: query
required: true
schema:
type: string
minLength: 1
maxLength: 2000
description: User's message
title: Message
description: User's message
- name: conversation_id
in: query
required: false
schema:
anyOf:
- type: string
- type: 'null'
description: Conversation ID for multi-turn
title: Conversation Id
description: Conversation ID for multi-turn
- name: model
in: query
required: false
schema:
type: string
description: AI model to use
default: claude-sonnet-4-5-20250929
title: Model
description: AI model to use
- name: enable_search
in: query
required: false
schema:
type: boolean
description: Enable web search
default: false
title: Enable Search
description: Enable web search
- name: agent_type
in: query
required: false
schema:
type: string
description: Agent graph to use
default: ask_nudg3
title: Agent Type
description: Agent graph to use
- name: token
in: query
required: true
schema:
type: string
description: Firebase ID token for authentication
title: Token
description: Firebase ID token for authentication
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/chat/{workspace_id}/quota:
get:
tags:
- Chat
summary: Get Chat Quota
description: 'Get current chat quota status for a workspace.
Returns allocated, used, remaining counts and next reset time.'
operationId: get_chat_quota_chat__workspace_id__quota_get
security:
- HTTPBearer: []
parameters:
- name: workspace_id
in: path
required: true
schema:
type: string
format: uuid
title: Workspace Id
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/chat/{workspace_id}/conversations:
get:
tags:
- Chat
summary: List Conversations
description: List past conversations for the current user in a workspace.
operationId: list_conversations_chat__workspace_id__conversations_get
security:
- HTTPBearer: []
parameters:
- name: workspace_id
in: path
required: true
schema:
type: string
format: uuid
title: Workspace Id
- name: limit
in: query
required: false
schema:
type: integer
maximum: 100
minimum: 1
default: 20
title: Limit
- name: offset
in: query
required: false
schema:
type: integer
minimum: 0
default: 0
title: Offset
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationListResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/chat/{workspace_id}/conversations/{thread_id}/messages:
get:
tags:
- Chat
summary: Get Conversation Messages
description: Get full message history for a conversation thread.
operationId: get_conversation_messages_chat__workspace_id__conversations__thread_id__messages_get
security:
- HTTPBearer: []
parameters:
- name: workspace_id
in: path
required: true
schema:
type: string
format: uuid
title: Workspace Id
- name: thread_id
in: path
required: true
schema:
type: string
title: Thread Id
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationMessagesResponse'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/chat/{workspace_id}/conversations/{thread_id}:
delete:
tags:
- Chat
summary: Delete Conversation
description: Delete a conversation thread.
operationId: delete_conversation_chat__workspace_id__conversations__thread_id__delete
security:
- HTTPBearer: []
parameters:
- name: workspace_id
in: path
required: true
schema:
type: string
format: uuid
title: Workspace Id
- name: thread_id
in: path
required: true
schema:
type: string
title: Thread Id
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
components:
schemas:
ConversationListResponse:
properties:
conversations:
items:
$ref: '#/components/schemas/ConversationListItem'
type: array
title: Conversations
count:
type: integer
title: Count
description: Number of conversations returned
type: object
required:
- count
title: ConversationListResponse
description: Response for listing conversations.
ConversationMessagesResponse:
properties:
thread_id:
type: string
title: Thread Id
description: LangGraph thread ID
messages:
items:
$ref: '#/components/schemas/ConversationMessage'
type: array
title: Messages
status:
type: string
title: Status
description: 'Thread status: idle, busy, interrupted, error'
default: idle
type: object
required:
- thread_id
title: ConversationMessagesResponse
description: Response for getting conversation messages.
ChatMessageRequest:
properties:
workspace_id:
type: string
format: uuid
title: Workspace Id
description: The workspace ID to query data from
message:
type: string
maxLength: 2000
minLength: 1
title: Message
description: The user's message/question
conversation_id:
anyOf:
- type: string
- type: 'null'
title: Conversation Id
description: Optional conversation ID for multi-turn conversations
conversation_history:
anyOf:
- items:
$ref: '#/components/schemas/ChatMessage'
type: array
- type: 'null'
title: Conversation History
description: Previous messages in the conversation (user and assistant turns) for HITL context
model:
anyOf:
- type: string
enum:
- claude-haiku-4-5
- gemini-2.5-flash
- grok-4-fast
- type: 'null'
title: Model
description: 'AI model to use: claude-haiku-4-5 (default), gemini-2.5-flash, or grok-4-fast'
default: claude-haiku-4-5
enable_search:
type: boolean
title: Enable Search
description: Enable web search grounding via Brave Search. When enabled, the agent can search the web for current information.
default: false
type: object
required:
- workspace_id
- message
title: ChatMessageRequest
description: Request schema for sending a chat message.
examples:
- message: What's our brand visibility compared to competitors?
model: claude-haiku-4-5
workspace_id: 550e8400-e29b-41d4-a716-446655440000
ConversationMessage:
properties:
role:
type: string
title: Role
description: 'Message role: user or assistant'
content:
type: string
title: Content
description: Message content
type: object
required:
- role
- content
title: ConversationMessage
description: A single message from conversation history.
ChatMessage:
properties:
role:
type: string
enum:
- user
- assistant
title: Role
description: Role of the message sender
content:
type: string
title: Content
description: Message content
type: object
required:
- role
- content
title: ChatMessage
description: A single message in conversation history.
SuccessResponse:
properties:
status:
type: string
title: Status
description: Response status
default: success
message:
type: string
title: Message
data:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Data
type: object
required:
- message
title: SuccessResponse
description: Generic success response.
ConversationListItem:
properties:
thread_id:
type: string
title: Thread Id
description: LangGraph thread ID
title:
type: string
title: Title
description: Conversation title (first message truncated)
agent_type:
anyOf:
- type: string
- type: 'null'
title: Agent Type
description: Agent graph used
created_at:
type: string
title: Created At
description: ISO 8601 creation timestamp
updated_at:
type: string
title: Updated At
description: ISO 8601 last update timestamp
type: object
required:
- thread_id
- title
- created_at
- updated_at
title: ConversationListItem
description: A conversation summary for list display.
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
type: object
required:
- loc
- msg
- type
title: ValidationError
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
securitySchemes:
ApiKeyAuth:
type: http
scheme: bearer
bearerFormat: API Key
description: '
API Key authentication for Public API v1 endpoints.
**Format:** `nudg3_live_ak_xxx...` or `nudg3_test_ak_xxx...`
**Usage:**
```
Authorization: Bearer nudg3_live_ak_your_key_here
```
Or use the header:
```
X-API-Key: nudg3_live_ak_your_key_here
```
**Obtain API Keys:**
Generate API keys from your Nudg3 dashboard under Settings > API Keys.
**Tiers:**
- **Basic:** `read:analytics` scope - Analytics endpoints only
- **Premium:** `read:analytics` + `export:data` scopes - Analytics + Exports
'
BearerAuth:
type: http
scheme: bearer
bearerFormat: JWT
description: '
JWT authentication for internal dashboard endpoints.
Obtain tokens via `/auth/login` endpoint.
'
externalDocs:
description: Nudg3 API Documentation
url: https://docs.nudg3.com/api