Retrieve recent usage events and billing activity for your account

Get Recent Usage

API Reference

Dashboard

X-API-Key

Backboard API

Get API Key

Build conversational AI applications with persistent memory and intelligent document processing.

Introduction

Get started with Backboard API in under 5 minutes

Quickstart

Learn how to authenticate your API requests

Authentication

Navigate the Backboard.io dashboard to track usage, manage assistants, and explore the platform's features.

How messages, threads, and assistants stack together in Backboard.

Architecture

Frequently asked questions about Backboard and its features.

Install Backboard R-CLI, sign in, open a project, and run your first session in the terminal.

R-CLI Overview

Control which tools R-CLI runs automatically, which ask first, and which are blocked outright.

Permissions

Undo, redo, and rewind the file changes R-CLI makes, without relying on git.

Checkpoints

Load reusable workflows from your repo, your personal library, or skills.sh, and let the agent find new ones on demand.

Skills and Discovery

Add external tools through MCP servers, and run local commands at session events with hooks.

MCP Servers and Hooks

Attach files by dragging them onto the terminal, or paste images from your clipboard with Ctrl+V.

Attachments

Change the model, thinking mode, memory, and session toggles from one panel or with individual commands.

Session Settings

Every R-CLI slash command, startup flag, keyboard shortcut, and configuration file.

Command Reference

Explore the Backboard SDK with detailed examples for tool calls, documents, memory, streaming, and thinking.

SDK Overview

Send your first message in one call — no assistant or thread setup needed.

First Message

Use thread_id to keep chat history in one place. Use assistant_id when you want the same AI profile (and memory) across multiple chats.

Continuing conversations

Use the SDK to create, list, update, and delete assistants—the saved AI profiles your threads attach to.

Create & update assistants

Define custom functions for your assistant to call, handle tool call requests, and submit outputs.

Tool Calls

Generate images and videos without a conversation-model call.

Stateless Calls

Text-to-image, image editing, and multi-image references.

Stateless Image API

Text, frames, source videos, and image/audio/video reference combinations.

Stateless Video API

Generate, edit, and reuse images in assistant conversations.

Image Tool

Generate videos in conversations from text, frames, source clips, and media references.

Video Tool

Upload, list, poll, and delete documents. Query their contents with RAG.

Documents

Enable persistent memory so your assistant remembers facts across conversations. Manage memories programmatically.

Memory

Enable real-time web search in conversations via the SDK.

Web Search

Enable step-by-step reasoning in conversations via the SDK

Thinking (Reasoning)

Classify requests, estimate probabilities, and score inputs with TypeSafe Jev using the Python and TypeScript SDKs.

System One Models

Upload audio, receive a spoken answer, and stream the STT/TTS pipeline with Python and Node.js.

Voice (TTS & STT)

Build a voice conversation with Python or Node.js: audio in, streamed speech out, and tools.

Realtime Audio

Each assistant is your AI’s saved identity—instructions, tools, documents, memory, and embeddings—in one place.

Assistant profiles

One thread is one ongoing chat—message history, tool calls, and context—stays together until you delete it.

Conversation threads

How to send a message, stream the response, and understand every field in the request and response.

Send Message

Monitor your credit balance and API usage

Billing & Usage

How tool calling works: define tools, handle requests, submit outputs, and loop for multi-round calls.

Tool Calling

Understand assistant image generation, reusable multimodal references, model-specific controls, and stored outputs.

Generate video clips inside a normal conversation with a separate video model.

Enable real-time web search in conversations

Enable models to reason step-by-step before answering

Classify requests, estimate probabilities, and score inputs with TypeSafe Jev using cURL, Python, and TypeScript.

Transcribe audio, speak an answer, or build a live pipeline with separate speech and text models.

Start a voice conversation, send audio, receive speech as it streams, and use tools.

Models

Let your users log in or sign up using a Backboard account

SSO (Single Sign On)

Create Assistant

List Assistants

Get Assistant

Update Assistant

Clone Assistant

Delete Assistant

Create Thread for Assistant

List Threads for Assistant

List Assistant Documents

Upload Document to Assistant

Connect a thread to a native audio model over WebSocket.

Submit Tool Outputs

Submit Tool Outputs (Legacy)

Cancel Run

List Threads

Get Thread

Delete Thread

List Thread Documents

Upload Document to Thread

Add Message to Thread (Legacy)

Get Document Status

Delete Document

List Memories

Search through stored memories using semantic or keyword-based queries

Search Memories

Add Memory

Get Memory

Update Memory

Delete Memory

Reset All Memories

Get Memory Stats

Get Memory Operation Status

List Models

Get Model

List Providers

List Models by Provider

List Embedding Models

List Embedding Providers

Get Embedding Model

List Image Models

List Image Providers

Get Image Model

List Video Models

Get Video Model

Authorize

Token

User Info

Revoke Token

Assistant

AssistantCloneRequest

AssistantCloneResponse

AssistantCreate

AssistantDeleteResponse

AssistantUpdate

AttachmentInfo

Body_upload_document_to_assistant_assistants__assistant_id__documents_post

Body_upload_document_to_thread_threads__thread_id__documents_post

CreditWallet

DocumentDeleteResponse

DocumentRead

DocumentStatus

DocumentStatusResponse

Schema specifically for reading embedding model information.

EmbeddingModelRead

Response schema for listing embedding models.

EmbeddingModelsListResponse

EvaluationResponse

EvaluationUsage

FunctionDefinition

GeneratedMediaInfo

HTTPValidationError

Schema for reading image generation model information.

ImageModelRead

Response schema for listing image generation models.

ImageModelsListResponse

Schema for listing memories with optional pagination

MemoriesListResponse

MemoryCreate

MemoryDeleteResponse

MemoryOperationStatusResponse

Schema for memory responses from backboard_memory

MemoryResponse

MemorySearchRequest

MemorySearchResponse

Schema for a single memory search result (no metadata, used in search responses)

MemorySearchResultItem

MemoryUpdate

Response for message operations - includes content at top level for easy access

MessageResponse

MessageRole

MessageStatus

MessageWithAttachments

Schema for reading model information including pricing.

ModelRead

ModelsListResponse

PaginatedUsageSummaryResponse

PaginationMeta

ProvidersListResponse

RetrievedMemory

STT result: transcript, input audio URL, billing dimensions, and raw provider output.

STTUsageInfo

SubmitToolOutputsRequest

Simplified tool-output submission. Three fields, no escape hatches.

Shares the canonical ``{tool_call_id, output}`` entry shape with the
original ``submit-tool-outputs`` endpoint. The only differences vs. the
original are:

1. ``thread_id`` lives in the body instead of the URL.
2. ``run_id`` is resolved server-side to the latest ``REQUIRES_ACTION``
   run on the thread — callers never pass it.

If you need to pin to a specific ``run_id`` or override the assistant's
tool list for a run, use the original
``POST /threads/{thread_id}/runs/{run_id}/submit-tool-outputs`` instead.

​Query Parameters

​Response

Query Parameters

Response