Messages - MemoryLake AI

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/router/anthropic/v1/messages?boundary_id=bnd-xxxxxx' \
  -H 'x-api-key: sk_xxxxxx' \
  -H 'anthropic-version: 2023-06-01' \
  -H 'Content-Type: application/json' \
  -d '{
    "max_tokens": 1024,
    "messages": [
      {
        "content": "What did I say my favourite city was?",
        "role": "user"
      }
    ],
    "model": "claude-haiku-4-5"
  }'

{
  "content": [
    {
      "text": "You said your favourite city is Lisbon.",
      "type": "text"
    }
  ],
  "id": "msg_abc123",
  "model": "claude-haiku-4-5",
  "role": "assistant",
  "stop_reason": "end_turn",
  "type": "message",
  "usage": {
    "input_tokens": 412,
    "output_tokens": 11
  }
}

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/router/anthropic/v1/messages?boundary_id=bnd-xxxxxx' \
  -H 'x-api-key: sk_xxxxxx' \
  -H 'anthropic-version: 2023-06-01' \
  -H 'Content-Type: application/json' \
  -d '{
    "max_tokens": 1024,
    "messages": [
      {
        "content": "What did I say my favourite city was?",
        "role": "user"
      }
    ],
    "model": "claude-haiku-4-5"
  }'

{
  "content": [
    {
      "text": "You said your favourite city is Lisbon.",
      "type": "text"
    }
  ],
  "id": "msg_abc123",
  "model": "claude-haiku-4-5",
  "role": "assistant",
  "stop_reason": "end_turn",
  "type": "message",
  "usage": {
    "input_tokens": 412,
    "output_tokens": 11
  }
}

POST /openapi/memorylake/router/anthropic/v1/messages

Anthropic Messages. With boundary_id, memories from that Boundary are added to the conversation before the model is called. Without it, the request goes to the model as is. With the Anthropic SDK, use the base URL that ends in /anthropic: the SDK adds /v1/messages itself. Set stream to true to receive server-sent events in the Anthropic format. Parameters not listed below are passed to the model unchanged.

Query Parameters

string

The Boundary whose memory this request uses. Omit it to call the model without memory.

Headers

string

Your MemoryLake API key, when you call the model with your own provider key. The provider key then goes in the provider’s usual key header. Your provider key is forwarded to the provider and never stored.

string

Anthropic API version. The Anthropic SDKs send it for you.

string

W3C trace context. When present, the request joins your trace and the same trace id comes back in X-Trace-ID.

Request Body

integer

required

Maximum tokens to generate

array

required

The conversation so far

Show Message object

string | array

required

Message text, or an array of content blocks

string

required

Who wrote the message. One of: user, assistant.

string

required

Model name, as listed under Available Models in the console

boolean

default:"false"

Stream the reply as server-sent events

string | array

System prompt

number

Sampling temperature

array

Tools the model may call, in the Anthropic format

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/router/anthropic/v1/messages?boundary_id=bnd-xxxxxx' \
  -H 'x-api-key: sk_xxxxxx' \
  -H 'anthropic-version: 2023-06-01' \
  -H 'Content-Type: application/json' \
  -d '{
    "max_tokens": 1024,
    "messages": [
      {
        "content": "What did I say my favourite city was?",
        "role": "user"
      }
    ],
    "model": "claude-haiku-4-5"
  }'

Response

array

Content blocks of the reply, such as text and tool calls

string

Message id

string

Model that answered

string

Always assistant

string

Why the model stopped, such as end_turn or max_tokens

string

Always message

object

Tokens used

Show Usage object

integer

Tokens in the input

integer

Tokens generated

{
  "content": [
    {
      "text": "You said your favourite city is Lisbon.",
      "type": "text"
    }
  ],
  "id": "msg_abc123",
  "model": "claude-haiku-4-5",
  "role": "assistant",
  "stop_reason": "end_turn",
  "type": "message",
  "usage": {
    "input_tokens": 412,
    "output_tokens": 11
  }
}

​Query Parameters

​Headers

​Request Body

​Response

Query Parameters

Headers

Request Body

Response