Chatbase API

Name: Chatbase API API
Brand: Chatbase API
Availability: InStock

★ Only Publicly Available OpenAPI DocumentAI/MLLanguage Modelsbearer9 EndpointsREST

For Agents

Create and operate custom Chatbase chatbots, send messages, and pull conversations and leads. Bearer-authenticated REST API with 9 endpoints for chatbot lifecycle and conversation operations.

Connect the Chatbase API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Chatbase API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.

Install Jentic One Beta (Self-Hosted)

Jentic One Host machine

# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh

Agent machine

# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh
jentic register       # connects your agent to your Jentic One instance

Jentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.

Capabilities

What an agent can do with Chatbase API API.

Create a new Chatbase chatbot via POST /create-chatbot

List the chatbots on the account via GET /get-chatbots

Update a chatbot's training data with POST /update-chatbot-data

Update display, behaviour, and integration settings with POST /update-chatbot-settings

GET STARTED

Start building with Chatbase API API

Explore with Jentic

View OpenAPI Document

Jentic publishes the only available OpenAPI document for Chatbase API, keeping it validated and agent-ready.

Jentic publishes the only available OpenAPI specification for Chatbase API, keeping it validated and agent-ready. Chatbase is a no-code platform for building custom GPT-style chatbots over your own documents and data. The v1 API exposes 9 endpoints for creating chatbots, updating their data and settings, sending chat messages, retrieving conversations, capturing leads, and creating contacts. Authentication is bearer-token (JWT-formatted API key).

Use Cases

Patterns agents use Chatbase API API for, with concrete tasks.

★ Embed a doc-grounded support bot in a web app

Use POST /create-chatbot to spin up a chatbot trained on your help-centre content, then call POST /chat from your front-end to send user questions and receive grounded answers. The /update-chatbot-data endpoint lets a CI job retrain the bot whenever the docs change, so the answers stay current without manual intervention.

Create a Chatbase chatbot named 'Acme Docs Bot', upload the latest docs via /update-chatbot-data, and send a test /chat request with the question 'how do I reset my password?' to verify it answers

Pull conversations into a CRM for follow-up

Call GET /get-conversations and GET /get-leads on a schedule to pull captured chats and lead details into a CRM. Each conversation can be enriched with the lead's email and chat transcript, then forwarded to a sales tool for follow-up. Because both endpoints support filtering by chatbotId, multi-bot accounts can be ingested in parallel.

Retrieve yesterday's conversations and leads for chatbotId 'acme-help', match each lead to a HubSpot contact by email, and create a CRM activity for any unmatched lead

Operate a fleet of bots across multiple sites

Use GET /get-chatbots to enumerate every chatbot on the account, then call POST /update-chatbot-settings on each to enforce a consistent welcome message, theme, and lead-capture configuration. POST /update-chatbot-data can refresh training in the same loop. This is the right pattern for agencies running many client bots from one account.

List all chatbots on the account, then update each one's settings so the welcome message reads 'Hi! I'm here to help.' and the brand colour is #FF6600

Drive a Chatbase chatbot from an AI agent

An AI agent uses Jentic to discover Chatbase's /chat endpoint, loads its schema, and calls it as a tool — for example, to answer a user question against a doc-trained bot before falling back to a more general LLM. Bearer-token credentials are managed by Jentic's vault so the agent never sees the raw API key.

Search Jentic for 'send a chatbase message', load the /chat schema, and ask the chatbot 'what is the refund policy?' against chatbotId 'acme-help'

Key Endpoints

9 endpoints — jentic publishes the only available openapi specification for chatbase api, keeping it validated and agent-ready.

METHOD

PATH

DESCRIPTION

POST

/create-chatbot

Create a new chatbot

GET

/get-chatbots

List chatbots

POST

/update-chatbot-data

Update a chatbot's training data

POST

/update-chatbot-settings

Update chatbot settings

POST

/chat

Send a message and receive a reply

GET

/get-conversations

List conversations

GET

/get-leads

List captured leads

DELETE

/delete-chatbot

Delete a chatbot

POST

/create-chatbot

Create a new chatbot

GET

/get-chatbots

List chatbots

POST

/update-chatbot-data

Update a chatbot's training data

POST

/update-chatbot-settings

Update chatbot settings

POST

/chat

Send a message and receive a reply

GET

Why though Jentic?

Three things that make agents converge on Jentic-routed access.

Credential isolation

Chatbase API keys (JWT bearer tokens) are stored encrypted in the Jentic vault (MAXsystem). Agents receive scoped access — the raw key never enters the agent's prompt context.

Intent-based discovery

Agents search by intent (e.g., 'send a chatbase message' or 'create a chatbase chatbot') and Jentic returns the matching Chatbase operations with their input schemas.

Time to first call

Direct Chatbase integration: half a day to wire up bearer auth and the chat/conversations response shapes. Through Jentic: under 30 minutes — search, load schema, execute.

Related APIs

Alternatives and complements available in the Jentic catalogue.

Alternative

ChatBot API

ChatBot.com is a flow-based bot builder — choose it over Chatbase when scripted decision trees fit better than LLM-grounded answers.

Use ChatBot.com when conversations follow predictable branching logic; use Chatbase when answers should be grounded in uploaded documents.

Alternative

Chatfuel API

Chatfuel targets messenger-channel bots — choose it for Facebook/Instagram-first deployments.

Use Chatfuel when the channel is Facebook Messenger or Instagram; use Chatbase for site-embedded doc-grounded bots.

Complementary

ChatKitty API

ChatKitty provides real-time chat infrastructure — pair it with Chatbase to add AI replies inside human chat channels.

Use ChatKitty for the live chat layer and Chatbase to generate AI responses that get posted into ChatKitty channels.

FAQs

Specific to using Chatbase API API through Jentic.

Why is there no official OpenAPI spec for Chatbase API?

Chatbase does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Chatbase API via structured tooling. It is validated against the live API and kept up to date. Get started at https://app.jentic.com/sign-up.

What authentication does the Chatbase API use?

Chatbase uses HTTP bearer-token authentication where the token is your Chatbase API key in JWT format. Send 'Authorization: Bearer <key>' on every request to chatbase.co/api/v1. Through Jentic, the key is stored in the encrypted MAXsystem vault and never enters the agent's prompt.

Can I send a message to a Chatbase chatbot programmatically?

Yes — POST /chat takes a chatbotId and a user message and returns the model's reply. This is the right endpoint for embedding a Chatbase bot inside a custom UI or invoking it as a tool from another agent.

How do I retrain a Chatbase chatbot when the source content changes?

Call POST /update-chatbot-data with the new training data payload. The chatbot is re-indexed against the new content so subsequent /chat calls reflect the updated source material.

How do I send a chatbot message through Jentic?

Run pip install jentic, set JENTIC_AGENT_API_KEY, then search 'send a chatbase message'. Jentic returns the /chat operation with its request schema. Supply chatbotId and message, then execute — the agent gets the response without browsing docs.

Are there documented rate limits for the Chatbase API?

The OpenAPI spec does not declare rate-limit headers or per-key quotas. /chat is the highest-volume endpoint and is typically subject to soft per-account limits — handle 429 responses with exponential backoff and read any RateLimit headers the live service returns.