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 Steps API

Per-step traces of an agent run.

Letta Steps 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 Steps. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, pricing, a changelog, and 14 JSON Schemas.

This API exposes 6 operations across 6 paths, and defines 46 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.

6 operations 6 paths 46 schemas 5 GET1 PATCH

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

Paths & Operations 6

Across 6 paths, the API surfaces 6 operations — 5 GET, 1 PATCH. Each is listed below with its method, path, parameters, and response codes.

Steps 6

Per-step traces of an agent run.

GET
/v1/steps/
List Steps
list_steps 15 params → 200422
GET
/v1/steps/{step_id}
Retrieve Step
retrieve_step 1 param → 200422
GET
/v1/steps/{step_id}/metrics
Retrieve Metrics for Step
retrieve_metrics_for_step 1 param → 200422
GET
/v1/steps/{step_id}/trace
Retrieve Trace for Step
retrieve_trace_for_step 1 param → 200422
PATCH
/v1/steps/{step_id}/feedback
Modify Feedback for Step
modify_feedback_for_step 1 param body → 200422
GET
/v1/steps/{step_id}/messages
List Messages for Step
list_messages_for_step 6 params → 200422

Schemas 46

The contract defines 46 schemas that model the data the API accepts and returns. The most detailed are Step (30 properties), Message (25 properties), ProviderTrace (17 properties), ToolReturnMessage (16 properties). Each schema is shown below with its type and property counts.

ApprovalReturn
object
4 properties 2 required
SystemMessage
object
A message generated by the system. Never streamed back on a response, only used for cursor pagination. Args: id (str): The ID of the message date (datetime): T…
11 properties 3 required
StopReasonType
string
CompactionStats
object
Statistics about a memory compaction operation.
6 properties 4 required
BillingContext
object
Billing context for LLM request cost tracking.
3 properties
EventMessage
object
A message for notifying the developer that an event that has occured (e.g. a compaction). Events are NOT part of the context window.
12 properties 4 required
ImageContent
object
2 properties 1 required
ToolReturnContent
object
4 properties 3 required
MessageRole
string
AssistantMessage
object
A message sent by the LLM in response to user input. Used in the LLM context. Args: id (str): The ID of the message date (datetime): The date the message was c…
11 properties 3 required
StepStatus
string
Status of a step execution
ToolCallDelta
object
3 properties
Message
object
Letta's internal representation of a message. Includes methods to convert to/from LLM provider formats. Attributes: id (str): The unique identifier of the mess…
25 properties 1 required
HiddenReasoningMessage
object
Representation of an agent's internal reasoning where reasoning content has been hidden from the response. Args: id (str): The ID of the message date (datetime…
12 properties 3 required
letta__schemas__letta_message__ToolReturn
object
6 properties 3 required
HTTPValidationError
object
1 property
TextContent
object
3 properties 1 required
LettaUserMessageContentUnion
Step
object
30 properties 1 required
ToolCallContent
object
5 properties 3 required
ToolReturnMessage
object
A message representing the return value of a tool call (generated by Letta executing the requested tool). Args: id (str): The ID of the message date (datetime)…
16 properties 5 required
OmittedReasoningContent
object
A placeholder for reasoning content we know is present, but isn't returned by the provider (e.g. OpenAI GPT-5 on ChatCompletions)
2 properties
ToolCallMessage
object
A message representing a request to call a tool (generated by the LLM to trigger tool execution). Args: id (str): The ID of the message date (datetime): The da…
12 properties 3 required
ApprovalResponseMessage
object
A message representing a response form the user indicating whether a tool has been approved to run. Args: id (str): The ID of the message date (datetime): The…
14 properties 2 required
LettaToolReturnContentUnion
ReasoningMessage
object
Representation of an agent's internal reasoning. Args: id (str): The ID of the message date (datetime): The date the message was created in ISO format name (Op…
13 properties 3 required
RedactedReasoningContent
object
Sent via the Anthropic Messages API
2 properties 1 required
Base64Image
object
4 properties 2 required
SummaryMessage
object
A message representing a summary of the conversation. Sent to the LLM as a user or system message depending on the provider.
12 properties 3 required
letta__schemas__message__ToolReturn-Output
object
5 properties 1 required
ValidationError
object
3 properties 3 required
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
LettaImage
object
5 properties 1 required
Function-Output
object
The function that the model called.
2 properties 2 required
UrlImage
object
2 properties 1 required
ProviderTrace
object
Letta's internal representation of a provider trace. Attributes: id (str): The unique identifier of the provider trace. requestjson (Dict[str, Any]): JSON cont…
17 properties 2 required
LettaAssistantMessageContentUnion
ModifyFeedbackRequest
object
2 properties
SummarizedReasoningContent
object
The style of reasoning content returned by the OpenAI Responses API
4 properties 2 required
ReasoningContent
object
Sent via the Anthropic Messages API
4 properties 2 required
FeedbackType
string
StepMetrics
object
12 properties 1 required
ToolCall
object
3 properties 3 required
ChatCompletionMessageFunctionToolCall-Output
object
A call to a function tool created by the model.
3 properties 3 required
UserMessage
object
A message sent by the user. Never streamed back on a response, only used for cursor pagination. Args: id (str): The ID of the message date (datetime): The date…
11 properties 3 required
SummarizedReasoningContentPart
object
2 properties 2 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

letta-steps-api-openapi.yml Raw ↑

Other APIs Letta publishes across the network.

Letta Code
Letta Admin API
Letta Agents API
Letta Archives 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
Where this information came from

This is an independent, third-party profile of Letta Steps 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.