curl -X POST 'https://api.anthropic.com/v1/messages?beta=true' \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H 'anthropic-version: 2023-06-01' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "example-model",
  "messages": [
    {
      "clear_at": "next_user_message",
      "content": "example-content",
      "output_config": {
        "effort": "low"
      },
      "role": "user"
    }
  ],
  "max_tokens": 0
}'

# POST /v1/messages?beta=true (Claude API)
Base URL: https://api.anthropic.com
Auth: x-api-key; Anthropic API key; required.
Status: Beta.
Request formats: application/json.
Last verified: 2026-10-20

> Create a Message

## Critical Gotchas
* Authentication uses the `x-api-key` header and requests also require an `anthropic-version` header.
* The official OpenAPI URL is discovered from the SDK repository manifest and must remain under Anthropic's trusted Stainless storage prefix.

## cURL
curl -X POST 'https://api.anthropic.com/v1/messages?beta=true' \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H 'anthropic-version: 2023-06-01' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "example-model",
  "messages": [
    {
      "clear_at": "next_user_message",
      "content": "example-content",
      "output_config": {
        "effort": "low"
      },
      "role": "user"
    }
  ],
  "max_tokens": 0
}'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| model | body | string | Yes | The model that will complete your prompt.  See [models](https://docs.anthropi... |
| messages | body | object[] | Yes | Input messages.  Our models are trained to operate on alternating `user` and... |
| max_tokens | body | integer | Yes | The maximum number of tokens to generate before stopping.  Note that our mode... |
| cache_control | body | object | No | Top-level cache control automatically applies a cache_control marker to the l... |
| container | body | object | No | Container identifier for reuse across requests. |
| context_management | body | object | No | Context management configuration.  This allows you to control how Claude mana... |
| diagnostics | body | object | No | Request-level diagnostics. Supply `previous_message_id` to have the response... |
| fallback_credit_token | body | string | No | The `fallback_credit_token` from a prior refusal's `stop_details`.  When a pr... |
Other params: fallbacks, inference_geo, mcp_servers, metadata, output_config, output_format, service_tier, speed, stop_sequences, stream, system, temperature, thinking, tool_choice, tools, top_k, top_p

## Response example
{"id":"string","type":"message"}

---
Need an API key? Get one at https://console.anthropic.com/settings/keys

POST

POST /v1/messages?beta=true — Claude API

Beta

Anthropic API key (required); https://api.anthropic.com

Claude API

Create a Message

Base URL: https://api.anthropic.com
Auth: x-api-key: <ANTHROPIC_API_KEY>
Last verified: 2026-10-20 · upstream hash matched

Actions Try in browser→

Agents: curl -H "Accept: text/markdown" this URL
→ 418 tokens · Vary: Accept

Critical gotchas

Authentication uses the x-api-key header and requests also require an anthropic-version header.

The official OpenAPI URL is discovered from the SDK repository manifest and must remain under Anthropic's trusted Stainless storage prefix.

cURL

curl -X POST 'https://api.anthropic.com/v1/messages?beta=true' \  -H "x-api-key: $ANTHROPIC_API_KEY" \  -H 'anthropic-version: 2023-06-01' \  -H 'Content-Type: application/json' \  -d '{  "model": "example-model",  "messages": [    {      "clear_at": "next_user_message",      "content": "example-content",      "output_config": {        "effort": "low"      },      "role": "user"    }  ],  "max_tokens": 0}'

Parameters

Name	In	Type	Required	Description
model	body	string	Yes	The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
messages	body	object[]	Yes	Input messages. Our models are trained to operate on alternating `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. Each input message must be an object with a `role` and `content`. You can specify a single `user`-role message, or you can include multiple `user` and `assistant` messages. If the final message uses the `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. Example with a single `user` message: ```json [{"role": "user", "content": "Hello, Claude"}] ``` Example with multiple conversational turns: ```json [ {"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?"}, ] ``` Example with a partially-filled response from Claude: ```json [ {"role": "user", "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"}, {"role": "assistant", "content": "The best answer is ("}, ] ``` Each input message `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: ```json {"role": "user", "content": "Hello, Claude"} ``` ```json {"role": "user", "content": [{"type": "text", "text": "Hello, Claude"}]} ``` See [input examples](https://platform.claude.com/docs/en/build-with-claude/working-with-messages). Note that if you want to include a [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role), you can use the top-level `system` parameter — there is no `"system"` role for input messages in the Messages API. There is a limit of 100,000 messages in a single request.
cache_control	body	object	No	Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request.
container	body	object	No	Container identifier for reuse across requests.
context_management	body	object	No	Context management configuration. This allows you to control how Claude manages context across multiple requests, such as whether to clear function results or not.
diagnostics	body	object	No	Request-level diagnostics. Supply `previous_message_id` to have the response include `diagnostics.cache_miss_reason` explaining any prompt-cache divergence from that prior request.
fallback_credit_token	body	string	No	The `fallback_credit_token` from a prior refusal's `stop_details`. When a preceding request was refused and returned a `fallback_credit_token`, pass that code here on the retry to have the retry's cache-creation tokens for the prefix that was warm on the refused model billed at the cache-read rate. Must be redeemed by the same organization and workspace, with the same request body (optionally extended by one appended `assistant` message whose content is the partial text — with any trailing whitespace stripped from the final text block — and paired server-tool blocks streamed before the refusal; the appended-assistant form is not available for requests with `output_format` set or forced `tool_choice`), on an eligible fallback model, on the same platform, and within 5 minutes of the refusal; a mismatch is a 400. A token minted mid-server-tool-loop whose partial content was continuable may only be redeemed with the appended-assistant form — if an exact-body retry is rejected with a 400 saying the token must be redeemed by continuing the partial response, retry with the appended-assistant form instead. When the appended-assistant form is used on a model that otherwise disallows assistant-turn prefill, this token also authorizes that one prefill.
fallbacks	body	object[]	No	Opt-in server-side retry on one or more substitute models when the requested model declines for policy reasons. Tried in order: if the first entry also declines, the second is tried, and so on. The string "default" requests the requested model's server-defined default fallback configuration.
inference_geo	body	string	No	Specifies the geographic region for inference processing. If not specified, the workspace's `default_inference_geo` is used.
max_tokens	body	integer	Yes	The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate. Set to `0` to populate the [prompt cache](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#pre-warming-the-cache) without generating a response. Different models have different maximum values for this parameter. See [models](https://platform.claude.com/docs/en/about-claude/models/overview) for details.
mcp_servers	body	object[]	No	MCP servers to be utilized in this request
metadata	body	object	No	Request body field metadata.
output_config	body	object	No	Request body field output_config.
output_format	body	object	No	Deprecated: Use `output_config.format` instead. See [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) A schema to specify Claude's output format in responses. This parameter will be removed in a future release.
service_tier	body	string	No	Determines whether to use priority capacity (if available) or standard capacity for this request. Anthropic offers different levels of service for your API requests. See [service-tiers](https://platform.claude.com/docs/en/api/service-tiers) for details.
speed	body	string	No	The inference speed mode for this request. `"fast"` enables high output-tokens-per-second inference.
stop_sequences	body	string[]	No	Custom text sequences that will cause the model to stop generating. Our models will normally stop when they have naturally completed their turn, which will result in a response `stop_reason` of `"end_turn"`. If you want the model to stop generating when it encounters custom strings of text, you can use the `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.
stream	body	boolean	No	Whether to incrementally stream the response using server-sent events. See [streaming](https://platform.claude.com/docs/en/build-with-claude/streaming) for details.
system	body	string	No	System prompt. A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role. See our [guide to system prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices#give-claude-a-role).
temperature	body	number	No	Amount of randomness injected into the response. Defaults to `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. Note that even with `temperature` of `0.0`, the results will not be fully deterministic.
thinking	body	object	No	Configuration for enabling Claude's extended thinking. When enabled, responses include `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. See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details.
tool_choice	body	object	No	How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.
tools	body	object[]	No	Definitions of tools that the model may use. If you include `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. There are two types of tools: client tools and server tools. The behavior described below applies to client tools. For [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools), see their individual documentation as each has its own behavior (e.g., the [web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool)). Each tool definition includes: * `name`: Name of the tool. * `description`: Optional, but strongly-recommended description of the tool. * `input_schema`: [JSON schema](https://json-schema.org/draft/2020-12) for the tool `input` shape that the model will produce in `tool_use` output content blocks. For example, if you defined `tools` as: ```json [ { "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"] } } ] ``` And then asked the model "What's the S&P 500 at today?", the model might produce `tool_use` content blocks in the response like this: ```json [ { "type": "tool_use", "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "name": "get_stock_price", "input": { "ticker": "^GSPC" } } ] ``` You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an input, and return the following back to the model in a subsequent `user` message: ```json [ { "type": "tool_result", "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", "content": "259.75 USD" } ] ``` Tools can be used for workflows that include running client-side tools and functions, or more generally whenever you want the model to produce a particular JSON structure of output. See our [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) for more details.
top_k	body	integer	No	Only sample from the top K options for each subsequent token. Used to remove "long tail" low probability responses. [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277). Recommended for advanced use cases only.
top_p	body	number	No	Use nucleus sampling. In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by `top_p`. Recommended for advanced use cases only.

Response 200 OK

{
  "id": "string",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "citations": null,
      "text": "string",
      "type": "text"
    }
  ],
  "model": "string",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "stop_details": null,
  "usage": {
    "cache_creation": null,
    "cache_creation_input_tokens": null,
    "cache_read_input_tokens": null,
    "fallback_credit": null,
    "inference_geo": null,
    "input_tokens": 0,
    "iterations": null,
    "output_tokens": 0,
    "output_tokens_details": null,
    "server_tool_use": null,
    "service_tier": null,
    "speed": null
  },
  "input_transformations": [
    {
      "path": "string",
      "reason": "model_binding_mismatch",
      "type": "thinking_dropped"
    }
  ],
  "diagnostics": null,
  "context_management": null,
  "container": null
}

Get a free Claude API key → sponsored

Affiliate link - we may earn a commission, at no extra cost to you.