Send Message Streaming

post/v1/agents/{agent_id}/messages/stream

Process a user message and return the agent's response. This endpoint accepts a message from a user and processes it through the agent. It will stream the steps of the response always, and stream the tokens if 'stream_tokens' is set to True.

Path ParametersExpand Collapse

agent_id: string

The ID of the agent in the format 'agent-'

minLength42

maxLength42

Body ParametersExpand Collapse

Deprecatedassistant_message_tool_kwarg: optional string

The name of the message argument in the designated message tool. Still supported for legacy agent types, but deprecated for letta_v1_agent onward.

Deprecatedassistant_message_tool_name: optional string

The name of the designated message tool. Still supported for legacy agent types, but deprecated for letta_v1_agent onward.

background: optional boolean

Whether to process the request in the background (only used when streaming=true).

Deprecatedenable_thinking: optional string

If set to True, enables reasoning before responses or tool calls from the agent.

include_pings: optional boolean

Whether to include periodic keepalive ping messages in the stream to prevent connection timeouts (only used when streaming=true).

include_return_message_types: optional array of MessageType

Only return specified message types in the response. If None (default) returns all messages.

Accepts one of the following:

"system_message"

"user_message"

"assistant_message"

"reasoning_message"

"hidden_reasoning_message"

"tool_call_message"

"tool_return_message"

"approval_request_message"

"approval_response_message"

input: optional string or array of TextContent { text, signature, type } or ImageContent { source, type } or ToolCallContent { id, input, name, 2 more } or 5 more

Syntactic sugar for a single user message. Equivalent to messages=[{'role': 'user', 'content': input}].

Accepts one of the following:

UnionMember0 = string

UnionMember1 = array of TextContent { text, signature, type } or ImageContent { source, type } or ToolCallContent { id, input, name, 2 more } or 5 more

Accepts one of the following:

TextContent = object { text, signature, type }

text: string

The text content of the message.

signature: optional string

Stores a unique identifier for any reasoning associated with this text content.

type: optional "text"

The type of the message.

Accepts one of the following:

"text"

ImageContent = object { source, type }

source: object { url, type } or object { data, media_type, detail, type } or object { file_id, data, detail, 2 more }

The source of the image.

Accepts one of the following:

URL = object { url, type }

url: string

The URL of the image.

type: optional "url"

The source type for the image.

Accepts one of the following:

"url"

Base64 = object { data, media_type, detail, type }

data: string

The base64 encoded image data.

media_type: string

The media type for the image.

detail: optional string

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: optional "base64"

The source type for the image.

Accepts one of the following:

"base64"

Letta = object { file_id, data, detail, 2 more }

file_id: string

The unique identifier of the image file persisted in storage.

data: optional string

The base64 encoded image data.

detail: optional string

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: optional string

The media type for the image.

type: optional "letta"

The source type for the image.

Accepts one of the following:

"letta"

type: optional "image"

The type of the message.

Accepts one of the following:

"image"

ToolCallContent = object { id, input, name, 2 more }

id: string

A unique identifier for this specific tool call instance.

input: map[unknown]

The parameters being passed to the tool, structured as a dictionary of parameter names to values.

The name of the tool being called.

signature: optional string

Stores a unique identifier for any reasoning associated with this tool call.

type: optional "tool_call"

Indicates this content represents a tool call event.

Accepts one of the following:

"tool_call"

ToolReturnContent = object { content, is_error, tool_call_id, type }

content: string

The content returned by the tool execution.

is_error: boolean

Indicates whether the tool execution resulted in an error.

tool_call_id: string

References the ID of the ToolCallContent that initiated this tool call.

type: optional "tool_return"

Indicates this content represents a tool return event.

Accepts one of the following:

"tool_return"

ReasoningContent = object { is_native, reasoning, signature, type }

Sent via the Anthropic Messages API

is_native: boolean

Whether the reasoning content was generated by a reasoner model that processed this step.

reasoning: string

The intermediate reasoning or thought process content.

signature: optional string

A unique identifier for this reasoning step.

type: optional "reasoning"

Indicates this is a reasoning/intermediate step.

Accepts one of the following:

"reasoning"

RedactedReasoningContent = object { data, type }

Sent via the Anthropic Messages API

data: string

The redacted or filtered intermediate reasoning content.

type: optional "redacted_reasoning"

Indicates this is a redacted thinking step.

Accepts one of the following:

"redacted_reasoning"

OmittedReasoningContent = object { signature, type }

A placeholder for reasoning content we know is present, but isn't returned by the provider (e.g. OpenAI GPT-5 on ChatCompletions)

signature: optional string

A unique identifier for this reasoning step.

type: optional "omitted_reasoning"

Indicates this is an omitted reasoning step.

Accepts one of the following:

"omitted_reasoning"

SummarizedReasoning = object { id, summary, encrypted_content, type }

The style of reasoning content returned by the OpenAI Responses API

id: string

The unique identifier for this reasoning step.

summary: array of object { index, text }

Summaries of the reasoning content.

index: number

The index of the summary part.

text: string

The text of the summary part.

encrypted_content: optional string

The encrypted reasoning content.

type: optional "summarized_reasoning"

Indicates this is a summarized reasoning step.

Accepts one of the following:

"summarized_reasoning"

max_steps: optional number

Maximum number of steps the agent should take to process the request.

messages: optional array of MessageCreate { content, role, batch_item_id, 5 more } or ApprovalCreate { approval_request_id, approvals, approve, 3 more }

The messages to be sent to the agent.

Accepts one of the following:

MessageCreate = object { content, role, batch_item_id, 5 more }

Request to create a message

content: array of LettaMessageContentUnion or string

The content of the message.

Accepts one of the following:

UnionMember0 = array of LettaMessageContentUnion

Accepts one of the following:

TextContent = object { text, signature, type }

text: string

The text content of the message.

signature: optional string

Stores a unique identifier for any reasoning associated with this text content.

type: optional "text"

The type of the message.

Accepts one of the following:

"text"

ImageContent = object { source, type }

source: object { url, type } or object { data, media_type, detail, type } or object { file_id, data, detail, 2 more }

The source of the image.

Accepts one of the following:

URL = object { url, type }

url: string

The URL of the image.

type: optional "url"

The source type for the image.

Accepts one of the following:

"url"

Base64 = object { data, media_type, detail, type }

data: string

The base64 encoded image data.

media_type: string

The media type for the image.

detail: optional string

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: optional "base64"

The source type for the image.

Accepts one of the following:

"base64"

Letta = object { file_id, data, detail, 2 more }

file_id: string

The unique identifier of the image file persisted in storage.

data: optional string

The base64 encoded image data.

detail: optional string

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: optional string

The media type for the image.

type: optional "letta"

The source type for the image.

Accepts one of the following:

"letta"

type: optional "image"

The type of the message.

Accepts one of the following:

"image"

ToolCallContent = object { id, input, name, 2 more }

id: string

A unique identifier for this specific tool call instance.

input: map[unknown]

The parameters being passed to the tool, structured as a dictionary of parameter names to values.

The name of the tool being called.

signature: optional string

Stores a unique identifier for any reasoning associated with this tool call.

type: optional "tool_call"

Indicates this content represents a tool call event.

Accepts one of the following:

"tool_call"

ToolReturnContent = object { content, is_error, tool_call_id, type }

content: string

The content returned by the tool execution.

is_error: boolean

Indicates whether the tool execution resulted in an error.

tool_call_id: string

References the ID of the ToolCallContent that initiated this tool call.

type: optional "tool_return"

Indicates this content represents a tool return event.

Accepts one of the following:

"tool_return"

ReasoningContent = object { is_native, reasoning, signature, type }

Sent via the Anthropic Messages API

is_native: boolean

Whether the reasoning content was generated by a reasoner model that processed this step.

reasoning: string

The intermediate reasoning or thought process content.

signature: optional string

A unique identifier for this reasoning step.

type: optional "reasoning"

Indicates this is a reasoning/intermediate step.

Accepts one of the following:

"reasoning"

RedactedReasoningContent = object { data, type }

Sent via the Anthropic Messages API

data: string

The redacted or filtered intermediate reasoning content.

type: optional "redacted_reasoning"

Indicates this is a redacted thinking step.

Accepts one of the following:

"redacted_reasoning"

OmittedReasoningContent = object { signature, type }

A placeholder for reasoning content we know is present, but isn't returned by the provider (e.g. OpenAI GPT-5 on ChatCompletions)

signature: optional string

A unique identifier for this reasoning step.

type: optional "omitted_reasoning"

Indicates this is an omitted reasoning step.

Accepts one of the following:

"omitted_reasoning"

UnionMember1 = string

role: "user" or "system" or "assistant"

The role of the participant.

Accepts one of the following:

"user"

"system"

"assistant"

batch_item_id: optional string

The id of the LLMBatchItem that this message is associated with

group_id: optional string

The multi-agent group that the message was sent in

The name of the participant.

otid: optional string

The offline threading id associated with this message

sender_id: optional string

The id of the sender of the message, can be an identity id or agent id

type: optional "message"

The message type to be created.

Accepts one of the following:

"message"

ApprovalCreate = object { approval_request_id, approvals, approve, 3 more }

Input to approve or deny a tool call request

Deprecatedapproval_request_id: optional string

The message ID of the approval request

approvals: optional array of object { approve, tool_call_id, reason, type } or ToolReturn { status, tool_call_id, tool_return, 3 more }

The list of approval responses

Accepts one of the following:

Approval = object { approve, tool_call_id, reason, type }

approve: boolean

Whether the tool has been approved

tool_call_id: string

The ID of the tool call that corresponds to this approval

reason: optional string

An optional explanation for the provided approval status

type: optional "approval"

The message type to be created.

Accepts one of the following:

"approval"

ToolReturn = object { status, tool_call_id, tool_return, 3 more }

status: "success" or "error"

Accepts one of the following:

"success"

"error"

tool_call_id: string

tool_return: string

stderr: optional array of string

stdout: optional array of string

type: optional "tool"

The message type to be created.

Accepts one of the following:

"tool"

Deprecatedapprove: optional boolean

Whether the tool has been approved

group_id: optional string

The multi-agent group that the message was sent in

Deprecatedreason: optional string

An optional explanation for the provided approval status

type: optional "approval"

The message type to be created.

Accepts one of the following:

"approval"

stream_tokens: optional boolean

Flag to determine if individual tokens should be streamed, rather than streaming per step (only used when streaming=true).

streaming: optional boolean

If True, returns a streaming response (Server-Sent Events). If False (default), returns a complete response.

Deprecateduse_assistant_message: optional boolean

Whether the server should parse specific tool call arguments (default send_message) as AssistantMessage objects. Still supported for legacy agent types, but deprecated for letta_v1_agent onward.

ReturnsExpand Collapse

LettaStreamingResponse = SystemMessage { id, content, date, 8 more } or UserMessage { id, content, date, 8 more } or ReasoningMessage { id, date, reasoning, 10 more } or 9 more

Streaming response type for Server-Sent Events (SSE) endpoints. Each event in the stream will be one of these types.

Accepts one of the following:

SystemMessage = object { id, content, date, 8 more }

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): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message content (str): The message content sent by the system

id: string

content: string

The message content sent by the system

date: string

is_err: optional boolean

message_type: optional "system_message"

The type of the message.

Accepts one of the following:

"system_message"

otid: optional string

run_id: optional string

sender_id: optional string

seq_id: optional number

step_id: optional string

UserMessage = object { id, content, date, 8 more }

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 the message was created in ISO format name (Optional[str]): The name of the sender of the message content (Union[str, List[LettaUserMessageContentUnion]]): The message content sent by the user (can be a string or an array of multi-modal content parts)

id: string

content: array of LettaUserMessageContentUnion or string

The message content sent by the user (can be a string or an array of multi-modal content parts)

Accepts one of the following:

UnionMember0 = array of LettaUserMessageContentUnion

Accepts one of the following:

TextContent = object { text, signature, type }

text: string

The text content of the message.

signature: optional string

Stores a unique identifier for any reasoning associated with this text content.

type: optional "text"

The type of the message.

Accepts one of the following:

"text"

ImageContent = object { source, type }

source: object { url, type } or object { data, media_type, detail, type } or object { file_id, data, detail, 2 more }

The source of the image.

Accepts one of the following:

URL = object { url, type }

url: string

The URL of the image.

type: optional "url"

The source type for the image.

Accepts one of the following:

"url"

Base64 = object { data, media_type, detail, type }

data: string

The base64 encoded image data.

media_type: string

The media type for the image.

detail: optional string

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

type: optional "base64"

The source type for the image.

Accepts one of the following:

"base64"

Letta = object { file_id, data, detail, 2 more }

file_id: string

The unique identifier of the image file persisted in storage.

data: optional string

The base64 encoded image data.

detail: optional string

What level of detail to use when processing and understanding the image (low, high, or auto to let the model decide)

media_type: optional string

The media type for the image.

type: optional "letta"

The source type for the image.

Accepts one of the following:

"letta"

type: optional "image"

The type of the message.

Accepts one of the following:

"image"

UnionMember1 = string

date: string

is_err: optional boolean

message_type: optional "user_message"

The type of the message.

Accepts one of the following:

"user_message"

otid: optional string

run_id: optional string

sender_id: optional string

seq_id: optional number

step_id: optional string

ReasoningMessage = object { id, date, reasoning, 10 more }

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 (Optional[str]): The name of the sender of the message source (Literal["reasoner_model", "non_reasoner_model"]): Whether the reasoning content was generated natively by a reasoner model or derived via prompting reasoning (str): The internal reasoning of the agent signature (Optional[str]): The model-generated signature of the reasoning step

id: string

date: string

reasoning: string

is_err: optional boolean

message_type: optional "reasoning_message"

The type of the message.

Accepts one of the following:

"reasoning_message"

otid: optional string

run_id: optional string

sender_id: optional string

seq_id: optional number

signature: optional string

source: optional "reasoner_model" or "non_reasoner_model"

Accepts one of the following:

"reasoner_model"

"non_reasoner_model"

step_id: optional string

HiddenReasoningMessage = object { id, date, state, 9 more }

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): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message state (Literal["redacted", "omitted"]): Whether the reasoning content was redacted by the provider or simply omitted by the API hidden_reasoning (Optional[str]): The internal reasoning of the agent

id: string

date: string

state: "redacted" or "omitted"

Accepts one of the following:

"redacted"

"omitted"

hidden_reasoning: optional string

is_err: optional boolean

message_type: optional "hidden_reasoning_message"

The type of the message.

Accepts one of the following:

"hidden_reasoning_message"

otid: optional string

run_id: optional string

sender_id: optional string

seq_id: optional number

step_id: optional string

ToolCallMessage = object { id, date, tool_call, 9 more }

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 date the message was created in ISO format name (Optional[str]): The name of the sender of the message tool_call (Union[ToolCall, ToolCallDelta]): The tool call

id: string

date: string

Deprecatedtool_call: ToolCall { arguments, name, tool_call_id } or ToolCallDelta { arguments, name, tool_call_id }

Accepts one of the following:

ToolCall = object { arguments, name, tool_call_id }

arguments: string

tool_call_id: string

ToolCallDelta = object { arguments, name, tool_call_id }

arguments: optional string

tool_call_id: optional string

is_err: optional boolean

message_type: optional "tool_call_message"

The type of the message.

Accepts one of the following:

"tool_call_message"

otid: optional string

run_id: optional string

sender_id: optional string

seq_id: optional number

step_id: optional string

tool_calls: optional array of ToolCall { arguments, name, tool_call_id } or ToolCallDelta { arguments, name, tool_call_id }

Accepts one of the following:

UnionMember0 = array of ToolCall { arguments, name, tool_call_id }

arguments: string

tool_call_id: string

ToolCallDelta = object { arguments, name, tool_call_id }

arguments: optional string

tool_call_id: optional string

ToolReturnMessage = object { id, date, status, 13 more }

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): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message tool_return (str): The return value of the tool (deprecated, use tool_returns) status (Literal["success", "error"]): The status of the tool call (deprecated, use tool_returns) tool_call_id (str): A unique identifier for the tool call that generated this message (deprecated, use tool_returns) stdout (Optional[List(str)]): Captured stdout (e.g. prints, logs) from the tool invocation (deprecated, use tool_returns) stderr (Optional[List(str)]): Captured stderr from the tool invocation (deprecated, use tool_returns) tool_returns (Optional[List[ToolReturn]]): List of tool returns for multi-tool support

id: string

date: string

Deprecatedstatus: "success" or "error"

Accepts one of the following:

"success"

"error"

Deprecatedtool_call_id: string

Deprecatedtool_return: string

is_err: optional boolean

message_type: optional "tool_return_message"

The type of the message.

Accepts one of the following:

"tool_return_message"

otid: optional string

run_id: optional string

sender_id: optional string

seq_id: optional number

Deprecatedstderr: optional array of string

Deprecatedstdout: optional array of string

step_id: optional string

tool_returns: optional array of ToolReturn { status, tool_call_id, tool_return, 3 more }

status: "success" or "error"

Accepts one of the following:

"success"

"error"

tool_call_id: string

tool_return: string

stderr: optional array of string

stdout: optional array of string

type: optional "tool"

The message type to be created.

Accepts one of the following:

"tool"

AssistantMessage = object { id, content, date, 8 more }

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 created in ISO format name (Optional[str]): The name of the sender of the message content (Union[str, List[LettaAssistantMessageContentUnion]]): The message content sent by the agent (can be a string or an array of content parts)

id: string

content: array of LettaAssistantMessageContentUnion { text, signature, type } or string

The message content sent by the agent (can be a string or an array of content parts)

Accepts one of the following:

UnionMember0 = array of LettaAssistantMessageContentUnion { text, signature, type }

text: string

The text content of the message.

signature: optional string

Stores a unique identifier for any reasoning associated with this text content.

type: optional "text"

The type of the message.

Accepts one of the following:

"text"

UnionMember1 = string

date: string

is_err: optional boolean

message_type: optional "assistant_message"

The type of the message.

Accepts one of the following:

"assistant_message"

otid: optional string

run_id: optional string

sender_id: optional string

seq_id: optional number

step_id: optional string

ApprovalRequestMessage = object { id, date, tool_call, 9 more }

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 (datetime): The date the message was created in ISO format name (Optional[str]): The name of the sender of the message tool_call (ToolCall): The tool call

id: string

date: string

Deprecatedtool_call: ToolCall { arguments, name, tool_call_id } or ToolCallDelta { arguments, name, tool_call_id }

The tool call that has been requested by the llm to run

Accepts one of the following:

ToolCall = object { arguments, name, tool_call_id }

arguments: string

tool_call_id: string

ToolCallDelta = object { arguments, name, tool_call_id }

arguments: optional string

tool_call_id: optional string

is_err: optional boolean

message_type: optional "approval_request_message"

The type of the message.

Accepts one of the following:

"approval_request_message"

otid: optional string

run_id: optional string

sender_id: optional string

seq_id: optional number

step_id: optional string

tool_calls: optional array of ToolCall { arguments, name, tool_call_id } or ToolCallDelta { arguments, name, tool_call_id }

The tool calls that have been requested by the llm to run, which are pending approval

Accepts one of the following:

UnionMember0 = array of ToolCall { arguments, name, tool_call_id }

arguments: string

tool_call_id: string

ToolCallDelta = object { arguments, name, tool_call_id }

arguments: optional string

tool_call_id: optional string

ApprovalResponseMessage = object { id, date, approval_request_id, 11 more }

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 date the message was created in ISO format name (Optional[str]): The name of the sender of the message approve: (bool) Whether the tool has been approved approval_request_id: The ID of the approval request reason: (Optional[str]) An optional explanation for the provided approval status

id: string

date: string

Deprecatedapproval_request_id: optional string

The message ID of the approval request

approvals: optional array of object { approve, tool_call_id, reason, type } or ToolReturn { status, tool_call_id, tool_return, 3 more }

The list of approval responses

Accepts one of the following:

Approval = object { approve, tool_call_id, reason, type }

approve: boolean

Whether the tool has been approved

tool_call_id: string

The ID of the tool call that corresponds to this approval

reason: optional string

An optional explanation for the provided approval status

type: optional "approval"

The message type to be created.

Accepts one of the following:

"approval"

ToolReturn = object { status, tool_call_id, tool_return, 3 more }

status: "success" or "error"

Accepts one of the following:

"success"

"error"

tool_call_id: string

tool_return: string

stderr: optional array of string

stdout: optional array of string

type: optional "tool"

The message type to be created.

Accepts one of the following:

"tool"

Deprecatedapprove: optional boolean

Whether the tool has been approved

is_err: optional boolean

message_type: optional "approval_response_message"

The type of the message.

Accepts one of the following:

"approval_response_message"

otid: optional string

Deprecatedreason: optional string

An optional explanation for the provided approval status

run_id: optional string

sender_id: optional string

seq_id: optional number

step_id: optional string

Ping = object { message_type }

Ping messages are a keep-alive to prevent SSE streams from timing out during long running requests.

message_type: "ping"

The type of the message.

Accepts one of the following:

"ping"

StopReason = object { stop_reason, message_type }

The stop reason from Letta indicating why agent loop stopped execution.

stop_reason: StopReasonType

The reason why execution stopped.

Accepts one of the following:

"end_turn"

"error"

"llm_api_error"

"invalid_llm_response"

"invalid_tool_call"

"max_steps"

"no_tool_call"

"tool_rule"

"cancelled"

"requires_approval"

message_type: optional "stop_reason"

The type of the message.

Accepts one of the following:

"stop_reason"

UsageStatistics = object { completion_tokens, message_type, prompt_tokens, 3 more }

Usage statistics for the agent interaction.

Attributes: completion_tokens (int): The number of tokens generated by the agent. prompt_tokens (int): The number of tokens in the prompt. total_tokens (int): The total number of tokens processed by the agent. step_count (int): The number of steps taken by the agent.

completion_tokens: optional number

The number of tokens generated by the agent.

message_type: optional "usage_statistics"

Accepts one of the following:

"usage_statistics"

prompt_tokens: optional number

The number of tokens in the prompt.

run_ids: optional array of string

The background task run IDs associated with the agent interaction

step_count: optional number

The number of steps taken by the agent.

total_tokens: optional number

The total number of tokens processed by the agent.

Send Message Streaming

curl https://api.letta.com/v1/agents/$AGENT_ID/messages/stream \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer $LETTA_API_KEY" \
    -d '{}'

{
  "id": "id",
  "content": "content",
  "date": "2019-12-27T18:11:19.117Z",
  "is_err": true,
  "message_type": "system_message",
  "name": "name",
  "otid": "otid",
  "run_id": "run_id",
  "sender_id": "sender_id",
  "seq_id": 0,
  "step_id": "step_id"
}

Returns Examples

{
  "id": "id",
  "content": "content",
  "date": "2019-12-27T18:11:19.117Z",
  "is_err": true,
  "message_type": "system_message",
  "name": "name",
  "otid": "otid",
  "run_id": "run_id",
  "sender_id": "sender_id",
  "seq_id": 0,
  "step_id": "step_id"
}