curl --location --request POST '/v1/messages' \
--header 'anthropic-beta;' \
--header 'anthropic-version: 2023-06-01' \
--header 'x-api-key: $ANTHROPIC_API_KEY' \
--header 'Content-Type: application/json' \
--data-raw '{
"model": "claude-3-7-sonnet-20250219",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Hello, world"
}
]
}'
{
"content": [
{
"text": "Hi! My name is Claude.",
"type": "text"
}
],
"id": "msg_013Zva2CMHLNnXjNJJKqJ2EF",
"model": "claude-3-7-sonnet-20250219",
"role": "assistant",
"stop_reason": "end_turn",
"stop_sequence": null,
"type": "message",
"usage": {
"input_tokens": 2095,
"output_tokens": 503
}
}
beta1,beta2
or specify the header multiple times for each beta.user
and assistant
conversational turns. When creating a new Message
, you specify the prior conversational turns with the messages
parameter, and the model then generates the next Message
in the conversation. Consecutive user
or assistant
turns in your request will be combined into a single turn.role
and content
. You can specify a single user
-role message, or you can include multiple user
and assistant
messages.assistant
role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response.user
message:[{"role": "user", "content": "Hello, Claude"}]
[
{"role": "user", "content": "Hello there."},
{"role": "assistant", "content": "Hi, I'm Claude. How can I help you?"},
{"role": "user", "content": "Can you explain LLMs in plain English?"},
]
[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("},
]
content
may be either a single string
or an array of content blocks, where each block has a specific type
. Using a string
for content
is shorthand for an array of one content block of type "text"
. The following input messages are equivalent:{"role": "user", "content": "Hello, Claude"}
{"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]}
{"role": "user", "content": [
{
"type": "image",
"source": {
"type": "base64",
"media_type": "image/jpeg",
"data": "/9j/4AAQSkZJRg...",
}
},
{"type": "text", "text": "What is in this image?"}
]}
base64
source type for images, and the image/jpeg
, image/png
, image/gif
, and image/webp
media types.system
parameter — there is no "system"
role for input messages in the Messages API.stop_reason
of "end_turn"
.stop_sequences
parameter. If the model encounters one of the custom sequences, the response stop_reason
value will be "stop_sequence"
and the response stop_sequence
value will contain the matched stop sequence.1.0
. Ranges from 0.0
to 1.0
. Use temperature
closer to 0.0
for analytical / multiple choice, and closer to 1.0
for creative and generative tasks.temperature
of 0.0
, the results will not be fully deterministic.thinking
content blocks showing Claude's thinking process before the final answer. Requires a minimum budget of 1,024 tokens and counts towards your max_tokens
limit.max_tokens
.false
. If set to true
, the model will output at most one tool use.tools
in your API request, the model may return tool_use
content blocks that represent the model's use of those tools. You can then run those tools using the tool input generated by the model and then optionally return results back to the model using tool_result
content blocks.name
: Name of the tool.description
: Optional, but strongly-recommended description of the tool.input_schema
: JSON schema for the tool input
shape that the model will produce in tool_use
output content blocks.tools
as:[
{
"name": "get_stock_price",
"description": "Get the current stock price for a given ticker symbol.",
"input_schema": {
"type": "object",
"properties": {
"ticker": {
"type": "string",
"description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
}
},
"required": ["ticker"]
}
}
]
tool_use
content blocks in the response like this:[
{
"type": "tool_use",
"id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
"name": "get_stock_price",
"input": { "ticker": "^GSPC" }
}
]
get_stock_price
tool with {"ticker": "^GSPC"}
as an input, and return the following back to the model in a subsequent user
message:[
{
"type": "tool_result",
"tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
"content": "259.75 USD"
}
]
temperature
.top_p
. You should either alter temperature
or top_p
, but not both.temperature
.type
that determines its shape.[{"type": "text", "text": "Hi, I'm Claude."}]
messages
ended with an assistant
turn, then the response content
will continue directly from that last turn. You can use this to constrain the model's output.messages
were:[
{"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"},
{"role": "assistant", "content": "The best answer is ("}
]
content
might be:[{"type": "text", "text": "B)"}]
page_location
, plain text results in char_location
, and content document results in content_block_location
."assistant"
.message_start
event and non-null otherwise."message"
.usage
will not match one-to-one with the exact visible content of an API request or response.output_tokens
will be non-zero, even for an empty string response from Claude.input_tokens
, cache_creation_input_tokens
, and cache_read_input_tokens
.