How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Letta Archives API

Manage archival memory archives and passages (RAG-style long-term store).

Letta Archives API is one of 41 APIs that Letta publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

This API exposes 14 JSON Schema definitions.

Tagged areas include Archives. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, pricing, a changelog, and 14 JSON Schemas.

This API exposes 9 operations across 6 paths, and defines 67 schemas. It is described by OpenAPI 3.1.0, at version 1.0.0.

Requests are made against 3 base URLs: https://api.letta.com, https://app.letta.com, http://localhost:8283.

9 operations 6 paths 67 schemas 2 DELETE3 GET1 PATCH3 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.1.0
API Version
1.0.0
Base URL
https://api.letta.com
Authentication
HTTP Bearer
Contact
License
Resource Areas
1

Authentication & Security 1

Letta Archives API declares 1 security scheme for authenticating requests. It accepts HTTP bearer tokens (bearerAuth). By default, every request must be authenticated.

Paths & Operations 9

Across 6 paths, the API surfaces 9 operations — 2 DELETE, 3 GET, 1 PATCH, 3 POST. Each is listed below with its method, path, parameters, and response codes.

Archives 9

Manage archival memory archives and passages (RAG-style long-term store).

POST
/v1/archives/
Create Archive
create_archive body → 200422
GET
/v1/archives/
List Archives
list_archives 7 params → 200422
GET
/v1/archives/{archive_id}
Retrieve Archive
retrieve_archive 1 param → 200422
PATCH
/v1/archives/{archive_id}
Modify Archive
modify_archive 1 param body → 200422
DELETE
/v1/archives/{archive_id}
Delete Archive
delete_archive 1 param → 204422
GET
/v1/archives/{archive_id}/agents
List Agents for Archive
list_agents_for_archive 6 params → 200422
POST
/v1/archives/{archive_id}/passages
Create Passage in Archive
create_passage_in_archive 1 param body → 200422
POST
/v1/archives/{archive_id}/passages/batch
Create Passages in Archive
create_passages_in_archive 1 param body → 200422
DELETE
/v1/archives/{archive_id}/passages/{passage_id}
Delete Passage from Archive
delete_passage_from_archive 2 params → 204422

Schemas 67

The contract defines 67 schemas that model the data the API accepts and returns. The most detailed are AgentState (45 properties), LLMConfig (27 properties), FileBlock (23 properties), Block (19 properties). Each schema is shown below with its type and property counts.

JsonObjectResponseFormat
object
Response format for JSON object responses.
1 property
GoogleAIModelSettings
object
6 properties
PassageBatchCreateRequest
object
Request model for creating multiple passages in an archive.
1 property 1 required
StopReasonType
string
Tool
object
Representation of a tool, which is a function that can be called by the agent.
18 properties
AgentEnvironmentVariable
object
10 properties 3 required
ChatGPTOAuthModelSettings
object
ChatGPT OAuth model configuration (uses ChatGPT backend API).
5 properties
TextResponseFormat
object
Response format for plain text responses.
1 property
ToolType
string
Passage
object
Representation of a passage, which is stored in archival memory.
15 properties 3 required
ToolCallDelta
object
3 properties
ConditionalToolRule
object
A ToolRule that conditionally maps to different child tools based on the output.
6 properties 2 required
MaxCountPerStepToolRule
object
Represents a tool rule configuration which constrains the total number of times this tool can be invoked in a single step.
4 properties 2 required
ZAIThinking
object
Thinking configuration for ZAI GLM-4.5+ models.
2 properties
HTTPValidationError
object
1 property
ContinueToolRule
object
Represents a tool rule configuration where if this tool gets called, it must continue the agent loop.
3 properties 1 required
NpmRequirement
object
2 properties 1 required
GoogleVertexModelSettings
object
6 properties
ArchiveUpdateRequest
object
Request model for updating an archive (partial). Supports updating only name and description.
2 properties
RequiresApprovalToolRule
object
Represents a tool rule configuration which requires approval before the tool can be invoked.
3 properties 1 required
SGLangModelSettings
object
SGLang model configuration (OpenAI-compatible runtime with SGLang-specific parsing).
8 properties
ManagerType
string
ProviderCategory
string
GroqModelSettings
object
Groq model configuration (OpenAI-compatible).
5 properties
VectorDBProvider
string
Supported vector database providers for archival memory
AgentState
object
Representation of an agent's state. This is the state of the agent at a given time, and is persisted in the DB backend. The state has all the information neede…
45 properties 10 required
Identity
object
8 properties 5 required
BedrockModelSettings
object
AWS Bedrock model configuration.
5 properties
AgentType
string
Enum to represent the type of agent.
CompactionSettings-Output
object
Configuration for conversation compaction / summarization. Per-model settings (temperature, max tokens, etc.) are derived from the default configuration for th…
7 properties
LLMConfig
object
Configuration for Language Model (LLM) connection and generation parameters. .. deprecated:: LLMConfig is deprecated and should not be used as an input or retu…
27 properties 3 required
Group
object
18 properties 4 required
ToolCallNode
object
Typed child override for prefilled arguments. When used in a ChildToolRule, if this child is selected next, its args will be applied as prefilled arguments (ov…
2 properties 1 required
FileBlock
object
23 properties 4 required
Source
object
(Deprecated: Use Folder) Representation of a source, which is a collection of files and passages.
11 properties 2 required
Block
object
A Block represents a reserved section of the LLM's context window.
19 properties 1 required
RequiredBeforeExitToolRule
object
Represents a tool rule configuration where this tool must be called before the agent loop can exit.
3 properties 1 required
ArchiveCreateRequest
object
Request model for creating an archive. Intentionally excludes vectordbprovider. These are derived internally (vector DB provider from env).
4 properties 1 required
ZAIModelSettings
object
Z.ai (ZhipuAI) model configuration (OpenAI-compatible).
6 properties
GeminiThinkingConfig
object
2 properties
ValidationError
object
3 properties 3 required
IdentityType
string
Enum to represent the type of the identity.
ApprovalRequestMessage
object
A message representing a request for approval to call a tool (generated by the LLM to trigger tool execution). Args: id (str): The ID of the message date (date…
12 properties 3 required
OpenAIReasoning
object
1 property
Memory
object
Represents the in-context memory (i.e. Core memory) of the agent. This includes both the Block objects (labelled by sections), as well as tools to edit the blo…
5 properties 1 required
BasetenModelSettings
object
Baseten model configuration (OpenAI-compatible).
4 properties
InitToolRule
object
Represents the initial tool rule configuration.
4 properties 1 required
AnthropicModelSettings
object
9 properties
XAIModelSettings
object
xAI model configuration (OpenAI-compatible).
5 properties
ChildToolRule
object
A ToolRule represents a tool that can be invoked by the agent.
5 properties 2 required
AnthropicThinking
object
2 properties
IdentityPropertyType
string
Enum to represent the type of the identity property.
IdentityProperty
object
A property of an identity
3 properties 3 required
OpenRouterModelSettings
object
OpenRouter model configuration (OpenAI-compatible).
5 properties
ParentToolRule
object
A ToolRule that only allows a child tool to be called if the parent has been called.
4 properties 2 required
PipRequirement
object
2 properties 1 required
PassageCreateRequest
object
Request model for creating a passage in an archive.
4 properties 1 required
TerminalToolRule
object
Represents a terminal tool rule configuration where if this tool gets called, it must end the agent loop.
3 properties 1 required
EmbeddingConfig
object
Configuration for embedding model connection and processing parameters.
10 properties 3 required
Archive
object
Representation of an archive - a collection of archival passages that can be shared between agents.
10 properties 3 required
ChatGPTOAuthReasoning
object
Reasoning configuration for ChatGPT OAuth models (GPT-5.x, o-series).
1 property
ToolCall
object
3 properties 3 required
DeepseekModelSettings
object
Deepseek model configuration (OpenAI-compatible).
5 properties
AzureModelSettings
object
Azure OpenAI model configuration (OpenAI-compatible).
5 properties
TogetherModelSettings
object
Together AI model configuration (OpenAI-compatible).
5 properties
JsonSchemaResponseFormat
object
Response format for JSON schema-based responses.
2 properties 1 required
OpenAIModelSettings
object
7 properties

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

letta-archives-api-openapi.yml Raw ↑

Other APIs Letta publishes across the network.

Letta Code
Letta Admin API
Letta Agents API
Letta Blocks API
Letta Chat API
Letta Client-Side Access Tokens API
Letta Conversations API
Letta Device Storage API
Letta Embeddings API
Letta Environments API
Letta Feeds API
Letta Folders API
Where this information came from

This is an independent, third-party profile of Letta Archives API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.