Messages

Create Anthropic Messages API requests against Baseten Model APIs.

Python

Python

import anthropic
import os

API_KEY = os.environ["BASETEN_API_KEY"]

client = anthropic.Anthropic(
    base_url="https://inference.baseten.co",
    api_key=API_KEY,
    default_headers={"Authorization": f"Bearer {API_KEY}"},
)

response = client.messages.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.content[0].text)

200

{
  "id": "<string>",
  "type": "<string>",
  "role": "<string>",
  "content": [
    {
      "type": "<string>",
      "text": "<string>"
    }
  ],
  "model": "<string>",
  "usage": {
    "input_tokens": 123,
    "output_tokens": 123
  },
  "stop_sequence": "<string>"
}

Download the OpenAPI schema for code generation and client libraries.

Model APIs accept requests in the Anthropic Messages API format at https://inference.baseten.co/v1/messages.

Call with the Anthropic SDK

The Anthropic SDK sends the API key as x-api-key by default. Baseten reads Authorization, so override default_headers when creating the client:

Python

import anthropic
import os

API_KEY = os.environ["BASETEN_API_KEY"]

client = anthropic.Anthropic(
    base_url="https://inference.baseten.co",
    api_key=API_KEY,
    default_headers={"Authorization": f"Bearer {API_KEY}"},
)

response = client.messages.create(
    model="deepseek-ai/DeepSeek-V4-Pro",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.content[0].text)

cURL

curl https://inference.baseten.co/v1/messages \
  -H "Content-Type: application/json" \
  -H "Authorization: Api-Key $BASETEN_API_KEY" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4-Pro",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Authorizations

Authorization · string · header · required

Pass your Baseten API key using either the Api-Key or Bearer scheme: Authorization: Api-Key YOUR_API_KEY or Authorization: Bearer YOUR_API_KEY. The Anthropic SDK's default x-api-key header is not accepted; override default_headers to send Authorization instead.

Body

application/json

Request body for creating a message.

model · string · required

The model slug to use. Find available models at Model APIs.

messages · InputMessage · object[] · required

The conversation history as an ordered list of input messages. Alternating user and assistant roles are expected; the final message must be from the user.

Show child attributes

max_tokens · integer · required

The maximum number of tokens to generate in the response. Required by the Messages API. The response may be shorter if it finishes naturally or hits a stop sequence.

Required range: x >= 1

system · string TextBlock · object[]

A system prompt that sets the model's behavior. Pass either a single string or an array of text content blocks.

temperature · number · default: 1

Controls randomness. Lower values are more deterministic. Range: 0 to 1.

Required range: 0 <= x <= 1

top_p · number

Nucleus sampling: only consider tokens with cumulative probability up to this value.

Required range: x <= 1

top_k · integer

Limits token selection to the top K most probable tokens at each step.

Required range: x >= 0

stop_sequences · string[]

Custom text sequences that will stop generation. When a stop sequence is hit, stop_reason is stop_sequence and stop_sequence contains the matched string.

stream · boolean · default: false

If true, the response is streamed as server-sent events. Each event has a type such as message_start, content_block_delta, or message_stop.

tools · ToolDefinition · object[]

A list of tools the model may call. Each tool has a name, description, and input_schema (a JSON Schema object).

Show child attributes

tool_choice · ToolChoice · object

Controls which tool (if any) the model must call.

ToolChoice

ToolChoice

ToolChoice

ToolChoice

Show child attributes

metadata · Metadata · object

An object describing metadata about the request. Supports user_id for abuse detection.

Show child attributes

Response

200

application/json

Successful response

The message response returned by the model.

id · string · required

A unique identifier for this message, such as msg_abc123.

type · string · required

The object type, always message.

Allowed value: "message"

role · string · required

The role of the generated message, always assistant.

Allowed value: "assistant"

content · (TextBlock · object | ToolUseBlock · object)[] · required

An array of content blocks generated by the model. Text responses contain a single text block; responses that invoke tools contain tool_use blocks.

A text content block.

TextBlock

ToolUseBlock

Show child attributes

model · string · required

The model slug that produced the response.

stop_reason · enum<string> · required

Why the model stopped generating: end_turn (natural stop), max_tokens (hit the max_tokens limit), stop_sequence (matched a stop_sequences entry), or tool_use (model invoked a tool).

Available options: end_turn, max_tokens, stop_sequence, tool_use

usage · Usage · object · required

Token usage statistics for the request.

Show child attributes

stop_sequence · string | null

The stop sequence that was matched, if stop_reason is stop_sequence. Otherwise null.