Messages

Messages

post

Send a structured list of input messages with text and/or image content, and the model will generate the next message in the conversation.

The Messages API can be used for either single queries or stateless multi-turn conversations.

Header parameters

x-api-keystringRequired

Your unique API key for authentication.

Example: sk-lh7cVWdVZx7lFkVmf92yFaz3uwWwiwMXfOESPnbpLtPKB3Oi

Body

application/json

modelstringRequired

The model that will complete your prompt.

Example: claude-3-7-sonnet-20250219

max_tokensinteger · min: 1Required

The maximum number of tokens to generate before stopping.

Example: 1024

stop_sequencesstring[]Optional

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.

streambooleanOptional

Whether to incrementally stream the response using server-sent events.

temperaturenumber · max: 1Optional

Amount of randomness injected into the response.

Default: 1

top_knumberOptional

Only sample from the top K options for each subsequent token.

Example: 5

top_pnumber · max: 1Optional

Use nucleus sampling.

Example: 0.7

Responses

200Success

application/json

modelstringRequired

idstringRequired

typestringRequired

rolestringRequired

stop_reasonstringRequired

stop_sequencenullRequired

post

/v1/messages

HTTPcURLJavaScriptPython

POST /v1/messages HTTP/1.1
Host: llm.onerouter.pro
x-api-key: text
Content-Type: application/json
Accept: */*
Content-Length: 715

{
  "model": "claude-3-7-sonnet@20250219",
  "messages": [
    {
      "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?"
    }
  ],
  "max_tokens": 1024,
  "stop_sequences": [],
  "stream": false,
  "system": [
    {
      "text": "Today's date is 2024-06-01.",
      "type": "text"
    }
  ],
  "temperature": 1,
  "thinking": {
    "type": "disabled"
  },
  "tool_choice": {
    "type": "auto"
  },
  "tools": [
    {
      "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"
        ]
      }
    }
  ],
  "top_k": 5,
  "top_p": 0.7
}

200Success

{
  "model": "claude-3-7-sonnet-20250219",
  "id": "msg_bdrk_01HMw9DPvsUxr3nFe4XEBoPg",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "# Large Language Models (LLMs) in Plain English\n\nLLMs, or Large Language Models, are advanced AI systems that understand and generate human language. Here's how they work in simple terms:\n\n## What are LLMs?\n- They're massive computer programs trained on enormous amounts of text from books, articles, websites, and other sources\n- Think of them as incredibly sophisticated pattern-recognition systems for language\n\n## How do they work?\n- LLMs learn by analyzing billions or even trillions of examples of human writing\n- They identify patterns in how words appear together and in what contexts\n- When you ask a question, they predict what text should come next based on all the patterns they've learned\n\n## What makes them \"large\"?\n- The \"large\" refers to their size - they contain billions or trillions of adjustable parameters\n- These parameters are like knobs that get fine-tuned during training\n- More parameters generally allow for more nuanced understanding of language\n\n## What can LLMs do?\n- Generate human-like text responses to questions\n- Summarize information\n- Translate between languages\n- Write different types of content (essays, stories, code)\n- Have conversations that seem natural\n\n## Limitations\n- They don't truly \"understand\" meaning the way humans do\n- They can make up information (hallucinate)\n- They don't have real-world experience or consciousness\n- They reflect biases present in their training data\n\nI'm an example of an LLM - I was created by Anthropic and trained on a wide variety of texts to be helpful, harmless, and honest in my interactions."
    }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 445,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0,
    "output_tokens": 357
  }
}