Messages

POST /v1/messages serves the Anthropic Messages shape over the same memory wrapper as Chat, so an application built on the Anthropic SDK gets memory by changing its base URL.

from anthropic import Anthropic

client = Anthropic(
    api_key="anona_live_YOUR_KEY",
    base_url="https://api.anonalabs.com",
    default_headers={"X-Anona-Space-Id": "support-bot"},
)

msg = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=512,
    messages=[{"role": "user", "content": "What plan am I on?"}],
)
print(msg.content[0].text)

The key can be sent as x-api-key (what the Anthropic SDK does) or as Authorization: Bearer, the same Anona key either way.

The shape is a wire format, not a provider. model is a hint: the model that actually answers is the one this deployment serves, and you never supply a provider key.

Request

POST https://api.anonalabs.com/v1/messages
x-api-key: anona_live_...
Content-Type: application/json

{
  "model": "claude-sonnet-4-6",
  "space_id": "support-bot",
  "max_tokens": 512,
  "system": "Answer in one sentence.",
  "messages": [
    { "role": "user", "content": "What plan am I on?" }
  ]
}

Field	Type	Default	Description
`messages`	array	required	Each `content` is a string or a list of typed blocks; text blocks are used, others are skipped.
`max_tokens`	integer	required	Required by this API shape, and forwarded to the model.
`system`	string or array	none	Becomes the system prompt. The memory block is prepended to it.
`model`	string	deployment default	Optional.
`stream`	boolean	`false`	Emit the Anthropic event stream.
`temperature`	float	none	Optional.

All memory tunables apply here, in the body or as X-Anona-* headers.

Response

{
  "id": "msg_...",
  "type": "message",
  "role": "assistant",
  "content": [{ "type": "text", "text": "You're on the Scale plan." }],
  "model": "claude-sonnet-4-6",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": { "input_tokens": 42, "output_tokens": 9 },
  "memories_injected": 3,
  "space_id": "support-bot"
}

memories_injected and space_id are the Anona additions, and also arrive as the X-Anona-Memories-Injected and X-Anona-Space-Id response headers.

Streaming

"stream": true emits the Anthropic named-event sequence:

message_start
content_block_start
content_block_delta      ← one per token, {"type": "text_delta", "text": "..."}
content_block_stop
message_delta            ← stop_reason and output token count
message_stop

with client.messages.stream(
    model="claude-sonnet-4-6",
    max_tokens=512,
    messages=[{"role": "user", "content": "What plan am I on?"}],
) as stream:
    for text in stream.text_stream:
        print(text, end="")

As on Chat, a failure before the first token is a normal JSON error with a real status code; the turn is recorded and billed after the stream ends.

API Essentials

Memory (data plane)

LLM Proxy (drop-in)

Account (control plane)

Request

Response

Streaming

​Request

​Response

​Streaming

Request

Response

Streaming