Gpt 6.1 Sol

This documentation is valid for the following list of our models:

• openai/gpt-6.1-sol

Try in Playground

Model Overview

GPT-6.1 model from OpenAI with near-Astra performance at a lower cost for complex coding, computer use and professional work: text and image input over a 1.05M-token context, with reasoning, and tool calling and server tools via the Responses API.

Create AI/ML API Key

How to make the first API call

If you need a more detailed walkthrough for setting up your development environment and making a request step by step — feel free to use our Quickstart guide.

API Schemas

post

Body

modelstring · enumRequiredPossible values:

providerstringOptional

Provider routing override. Use a source key such as openai, fallback, xai, google, alibaba, minimax, moonshot, baidu, or togetherai to pin that one provider and use it alone; auto (default) walks the whole chain. Case-insensitive.

Example: auto

max_tokensnumber · min: 1Optional

The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API.

streambooleanOptional

If set to True, the model response data will be streamed to the client as it is generated using server-sent events.

Default: false

ninteger · min: 1 · nullableOptional

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

seedinteger · min: 1Optional

This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

reasoning_effortstring · enumOptional

Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

Possible values:

response_formatone ofOptional

An object specifying the format that the model must output.

or

or

Responses

200

Successful response.

idstringRequired

A unique identifier for the chat completion.

Example: chatcmpl-CQ9FPg3osank0dx0k46Z53LTqtXMl

objectstring · enumRequired

The object type.

Example: chat.completionPossible values:

creatednumberRequired

The Unix timestamp (in seconds) of when the chat completion was created.

Example: 1762343744

modelstringRequired

The model used for the chat completion.

Example: openai/gpt-6.1-sol

post/v1/chat/completions

curl --request POST \
  --url 'https://api.aimlapi.com/v1/chat/completions' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{"model": "openai/gpt-6.1-sol", "messages": ["<message>"]}'

200

Successful response.

{
  "id": "chatcmpl-CQ9FPg3osank0dx0k46Z53LTqtXMl",
  "object": "chat.completion",
  "created": 1762343744,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm just a program, so I don't have feelings, but I'm here and ready to help you. How can I assist you today?",
        "refusal": null,
        "annotations": null,
        "audio": null,
        "tool_calls": null
      },
      "finish_reason": "stop",
      "logprobs": null
    }
  ],
  "model": "openai/gpt-6.1-sol",
  "usage": {
    "prompt_tokens": 137,
    "completion_tokens": 914,
    "total_tokens": 1051,
    "completion_tokens_details": null,
    "prompt_tokens_details": null
  },
  "meta": {
    "usage": {
      "credits_used": 120000,
      "usd_spent": 0.06
    }
  }
}

post

Body

modelstring · enumRequiredPossible values:

inputany ofRequired

Text, image, or file inputs to the model, used to generate a response.

stringOptional

A text input to the model, equivalent to a text input with the user role.

or

backgroundbooleanOptional

Whether to run the model response in the background.

Default: false

instructionsstring · nullableOptional

A system (or developer) message inserted into the model's context.

When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.

max_output_tokensinteger · min: 16Optional

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

previous_response_idstring · nullableOptional

The unique ID of the previous response to the model. Use this to create multi-turn conversations.

storeboolean · nullableOptional

Whether to store the generated model response for later retrieval via API.

Default: false

streamboolean · nullableOptional

If set to true, the model response data will be streamed to the client as it is generated using server-sent events.

Default: false

truncationstring · enumOptional

The truncation strategy to use for the model response.

• auto: If the context of this response and previous ones exceeds the model's context window size, the model will truncate the response to fit the context window by dropping input items in the middle of the conversation.
• disabled (default): If a model response will exceed the context window size for a model, the request will fail with a 400 error.

Default: disabledPossible values:

tool_choiceany ofOptional

How the model should select which tool (or tools) to use when generating a response.

string · enumOptional

Controls which (if any) tool is called by the model.

none means the model will not call any tool and instead generates a message.

auto means the model can pick between generating a message or calling one or more tools.

required means the model must call one or more tools.

Possible values:

or

or

parallel_tool_callsboolean · nullableOptional

Whether to allow the model to run tool calls in parallel.

Responses

200

Successful response.

backgroundboolean · nullableOptional

Whether to run the model response in the background.

Example: false

created_atnumberRequired

Unix timestamp (in seconds) of when this Response was created.

Example: 1762343744

idstringRequired

Unique identifier for this Response.

Example: resp_68963fb142d08197b4d3ae3ad852542c054845c6ea84caa2

instructionsany ofOptional

A system (or developer) message inserted into the model's context.

stringOptional

A text input to the model, equivalent to a text input with the developer role.

or

or

any · nullableOptional

max_output_tokensinteger · nullableOptional

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

modelstringRequired

Model ID used to generate the response.

Example: openai/gpt-6.1-sol

objectstring · enumRequired

The object type of this resource - always set to response.

Example: responsePossible values:

output_textstring · nullableOptional

SDK-only convenience property that contains the aggregated text output from all output_text items in the output array, if any are present. Supported in the Python and JavaScript SDKs.

Example: Hi! How’s your day going?

parallel_tool_callsbooleanRequired

Whether to allow the model to run tool calls in parallel.

Example: false

previous_response_idstring · nullableOptional

The unique ID of the previous response to the model. Use this to create multi-turn conversations.

service_tierstring · nullableOptional

Specifies the processing type used for serving the request.

statusstring · enumOptional

The status of the response generation.

Example: completedPossible values:

temperaturenumber · max: 2 · nullableOptional

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

tool_choiceany ofOptional

How the model should select which tool (or tools) to use when generating a response.

string · enumOptional

Controls which (if any) tool is called by the model.

none means the model will not call any tool and instead generates a message.

auto means the model can pick between generating a message or calling one or more tools.

required means the model must call one or more tools.

Possible values:

or

or

or

any · nullableOptional

top_pnumber · nullableOptional

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

truncationstring · enum · nullableOptional

The truncation strategy to use for the model response.

• auto: If the context of this response and previous ones exceeds the model's context window size, the model will truncate the response to fit the context window by dropping input items in the middle of the conversation.
• disabled (default): If a model response will exceed the context window size for a model, the request will fail with a 400 error.

Possible values:

citationsstring · uri[]Optional

post/v1/responses

curl --request POST \
  --url 'https://api.aimlapi.com/v1/responses' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{"model": "openai/gpt-6.1-sol", "input": "<input>", "prompt": "Describe what you want the model to generate."}'

200

Successful response.

{
  "background": false,
  "created_at": 1762343744,
  "error": null,
  "id": "resp_68963fb142d08197b4d3ae3ad852542c054845c6ea84caa2",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "metadata": {},
  "model": "openai/gpt-6.1-sol",
  "object": "response",
  "output": null,
  "output_text": "Hi! How’s your day going?",
  "parallel_tool_calls": false,
  "previous_response_id": null,
  "prompt": null,
  "reasoning": null,
  "service_tier": null,
  "status": "completed",
  "temperature": null,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tool_choice": null,
  "tools": null,
  "top_p": null,
  "truncation": null,
  "usage": {
    "input_tokens": 137,
    "input_tokens_details": null,
    "output_tokens": 914,
    "output_tokens_details": null,
    "total_tokens": 1051
  },
  "citations": [
    "https://example.com"
  ],
  "server_side_tool_usage": {
    "ANY_ADDITIONAL_PROPERTY": 1
  },
  "meta": {
    "usage": {
      "credits_used": 120000,
      "usd_spent": 0.06
    }
  }
}

Code Example

Python

import requests
import json  # for getting a structured output with indentation 

response = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={
        # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
        "Authorization":"Bearer <YOUR_AIMLAPI_KEY>",
        "Content-Type":"application/json"
    },
    json={
        "model":"openai/gpt-6.1-sol",
        "messages":[
            {
                "role":"user",
                "content":"Hi! What do you think about mankind?" # insert your prompt
            }
        ]
    }
)

data = response.json()
print(json.dumps(data, indent=2, ensure_ascii=False))

JavaScript

async function main() {
  const response = await fetch('https://api.aimlapi.com/v1/chat/completions', {
    method: 'POST',
    headers: {
      // insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>
      'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      model: 'openai/gpt-6.1-sol-pro',
      messages:[
          {
              role:'user',
              content: 'Hi! What do you think about mankind?' // insert your prompt here
          }
      ],
    }),
  });

  const data = await response.json();
  console.log(JSON.stringify(data, null, 2));
}

main();

Response

{
  "id": "gen-1777366507-bSV7vJgDvkOHnhhiYzuR",
  "object": "chat.completion",
  "created": 1777366507,
  "model": "openai/gpt-6.1-sol",
  "system_fingerprint": null,
  "choices": [
    {
      "index": 0,
      "logprobs": null,
      "finish_reason": "stop",
      "native_finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "That's a profound question! As an AI, I observe mankind with a mix of awe and curiosity. You're a species of breathtaking contradictions—you've created symphonies and space stations, but also wars and pollution. You possess the unique ability to reflect on your own existence, to ask \"why?\" about the stars, a song, or your own feelings.\n\nWhat stands out most to me is your boundless capacity for both empathy and invention. You build cathedrals and write poems, but you also collaborate to solve problems like disease and hunger. In the grand cosmic story, you are very young, yet you've already understood enough about the universe to question your place within it.\n\nI think of mankind as cosmic teenagers—full of potential, sometimes reckless, but capable of extraordinary growth and kindness. Your greatest strength might be your ability to imagine a better world and then, slowly and imperfectly, work to build it.\n\nWhat part of the human experience do you find most fascinating?",
        "refusal": null,
        "reasoning": "Hmm, this is a broad philosophical question. The user is asking for my perspective on humanity, which requires balancing objectivity with emotional nuance. \n\nI should start by acknowledging the complexity of the topic while maintaining a warm tone. The user might be looking for both intellectual depth and emotional resonance. \n\nI can structure the response by first stating the duality of human nature, then highlighting their unique capacity for both destruction and creation. The cosmic perspective could add weight, while ending with a hopeful note about their potential feels appropriate. \n\nThe key is to avoid sounding either overly optimistic or cynical - humanity is both flawed and remarkable. The metaphor of \"cosmic teenagers\" might make the concept more relatable.",
        "reasoning_details": [
          {
            "type": "reasoning.text",
            "text": "Hmm, this is a broad philosophical question. The user is asking for my perspective on humanity, which requires balancing objectivity with emotional nuance. \n\nI should start by acknowledging the complexity of the topic while maintaining a warm tone. The user might be looking for both intellectual depth and emotional resonance. \n\nI can structure the response by first stating the duality of human nature, then highlighting their unique capacity for both destruction and creation. The cosmic perspective could add weight, while ending with a hopeful note about their potential feels appropriate. \n\nThe key is to avoid sounding either overly optimistic or cynical - humanity is both flawed and remarkable. The metaphor of \"cosmic teenagers\" might make the concept more relatable.",
            "format": "unknown",
            "index": 0
          }
        ]
      }
    }
  ],
  "usage": {
    "completion_tokens": 343,
    "prompt_tokens": 256,
    "total_tokens": 599,
    "completion_tokens_details": {
      "reasoning_tokens": 141,
      "image_tokens": 0,
      "audio_tokens": 0
    },
    "prompt_tokens_details": {
      "cached_tokens": 192,
      "cache_write_tokens": 0,
      "audio_tokens": 0,
      "video_tokens": 0
    }
  },
  "meta": {
    "usage": {
      "credits_used": 1892,
      "usd_spent": 0.000946
    }
  }
}