Text Generation (Claude)
/api/v1/messagesHeader Parameters
Use Bearer Token authentication. Format: Authorization: Bearer sk-xxxxxx
Request Body
application/json
Model name, fixed values: claude-opus-4-6, claude-opus-4-5-20251101, claude-haiku-4-5-20251001, claude-sonnet-4-5-20250929
Array of conversation messages (excluding system messages). The role of each message must be either "user" or "assistant", and they must alternate (the first message must be "user").
Message Role
"system" | "user" | "assistant" | "tool"Message content supports a string or an array of content blocks.
Maximum Output Tokens
System prompt, string or array of content blocks
Whether to use streaming response, default false
Randomness Control (0.0–1.0)
Nucleus Sampling (0.0–1.0)
Top-K Sampling
Stop Word List
An array containing one or more tool objects for the model to invoke during Function Calling.
Tool Name
The description of this tool is optional, but highly recommended.
The JSON schema for the tool input shape that the model will generate in the tool_use output content block.
Tool selection strategy. Set this parameter to force a specific tool calling method for certain types of queries, such as always using a specific tool or disabling all tools. Optional values: auto: The model autonomously selects the tool. none: Set the tool_choice parameter to none if no tool calls are desired; {"type": "function", "function": {"name": "the_function_to_call"}}: To force a call to a specific tool, set the tool_choice parameter to {"type": "function", "function": {"name": "the_function_to_call"}}, where the_function_to_call is the name of the specified tool function.
Type, possible values: none, auto, any, tool
The name of the tool to use. Used when the type is tool.
Extended thinking mode, format: {"type": "enabled", "budget_tokens": 5000}
Optional values: enabled, disabled, adaptive. To turn on extended thinking, add a thinking object, with the type parameter set to enabled and the budget_tokens to a specified token budget for extended thinking. For Claude Opus 4.6 and Claude Sonnet 4.6, use type: "adaptive" instead. See Adaptive thinking for details. While type: "enabled" with budget_tokens is still functional on these models, it is deprecated and will be removed in a future release. The budget_tokens parameter determines the maximum number of tokens Claude is allowed to use for its internal reasoning process. In Claude 4 and later models, this limit applies to full thinking tokens, and not to the summarized output. Larger budgets can improve response quality by enabling more thorough analysis for complex problems, although Claude may not use the entire budget allocated, especially at ranges above 32k.
Determine the number of tokens Claude can use for its internal reasoning process. A larger budget enables more thorough analysis of complex problems, improving response quality.
Options "summarized" or "omitted". Controls how thinking content is displayed in the response. When set to omitted, thinking is returned normally. When set to summarized, the thinking content is edited, but a signature is returned for multi-turn continuity. Defaults to summarized.
Request metadata, such as {"user_id": "user-123"}
An external identifier for the user who is associated with the request.
This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number.
maxLength512
Response Body
application/json
Success
TypeScript Definitions
Use the response body type in TypeScript.
Unique object identifier.
For Messages, this is always "message".
Conversational role of the generated message.
This will always be "assistant".
The model that will complete your prompt.
Content generated by the model.
The reason that we stopped.
Which custom stop sequence was generated, if any.
Billing and rate-limit usage.
The number of input tokens which were used.
The number of output tokens which were used.
The number of input tokens used to create the cache entry.
The number of input tokens read from the cache.
curl -X POST "https://api.ygw.ai/api/v1/messages" \ -H "Authorization: string" \ -H "Content-Type: application/json" \ -d '{ "model": "string", "messages": [ { "role": "system", "content": "string" } ], "max_tokens": 0 }'{
"id": "string",
"type": "string",
"role": "string",
"model": "string",
"content": [
{
"type": "string",
"text": "string"
}
],
"stop_reason": "string",
"stop_sequence": null,
"usage": {
"input_tokens": 0,
"output_tokens": 0,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0
}
}