Chat Completions API

POST https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT_PATH}/chat/completions

Function Overview: Create a model response for a given chat conversation

Request Parameters

Field	Meaning	Level	Format	Required	Remarks
messages	A list of messages comprising the conversation so far.	1	array	Yes	Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.
Developer message	Developer-provided instructions that the model should follow, regardless of messages sent by the user	2	object		With o1 models and newer, developer messages replace the previous system messages
content	The contents of the developer message	3	string or array	Yes
Text content	The contents of the developer message	4	string
Array of content parts	An array of content parts with a defined type	4	array		For developer messages, only type text is supported
text	The text content	5	string	Yes
type	The type of the content part	5	string	Yes
role	The role of the messages author, in this case developer	3	string	Yes
name	An optional name for the participant. Provides the model information to differentiate between participants of the same role	3	string
System message	Developer-provided instructions that the model should follow, regardless of messages sent by the user	2	object		With o1 models and newer, use developer messages for this purpose instead
content	The contents of the system message	3	string or array	Yes
Text content	The contents of the system message	4	string
Array of content parts	An array of content parts with a defined type	4	array		For system messages, only type text is supported
Text content part		5	object
text	The text content	6	string	Yes
type	The type of the content part	6	string	Yes
role	The role of the messages author, in this case system	3	string	Yes
name	An optional name for the participant. Provides the model information to differentiate between participants of the same role	3	string
User message	Messages sent by an end user, containing prompts or additional context information	2	object
content	The contents of the user message	3	string or array	Yes
Text content	The text contents of the message	4	string
Array of content parts	An array of content parts with a defined type	4	array		Supported options differ based on the model being used to generate the response. Can contain text, image, or audio inputs
Text content part		5	object
text	The text content	6	string	Yes
type	The type of the content part	6	string	Yes
Image content part		5	object
image_url		6	object	Yes
url	Either a URL of the image or the base64 encoded image data	7	string	Yes
detail	Specifies the detail level of the image	7	string		Defaults to auto
type	The type of the content part	6	string	Yes
role	The role of the messages author, in this case user	3	string	Yes
name	An optional name for the participant. Provides the model information to differentiate between participants of the same role	3	string
Assistant message	Messages sent by the model in response to user messages	2	object
role	The role of the messages author, in this case assistant	3	string	Yes
audio	Data about a previous audio response from the model	3	object or null
id	Unique identifier for a previous audio response from the model	4	string	Yes
content	The contents of the assistant message	3	string or array		Required unless tool_calls or function_call is specified
Text content	The contents of the assistant message	4	string
Array of content parts	An array of content parts with a defined type	4	array		Can be one or more of type text, or exactly one of type refusal
Text content part		5	object
text	The text content	6	string	Yes
type	The type of the content part	6	string	Yes
Refusal content part		5	object
refusal	The refusal message generated by the model	6	string	Yes
type	The type of the content part	6	string	Yes
function_call	Deprecated and replaced by tool_calls	3	object or null		The name and arguments of a function that should be called, as generated by the model
name	The name of the function to call	4	string	Yes
arguments	The arguments to call the function with, as generated by the model in JSON format	4	string	Yes	Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function
name	An optional name for the participant. Provides the model information to differentiate between participants of the same role	3	string
refusal	The refusal message by the assistant	3	string or null
tool_calls	The tool calls generated by the model, such as function calls	3	array
Function tool call	A call to a function tool created by the model	4	object
function	The function that the model called	5	object	Yes
arguments	The arguments to call the function with, as generated by the model in JSON format	6	string	Yes	Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function
name	The name of the function to call	6	string	Yes
id	The ID of the tool call	5	string	Yes
type	The type of the tool. Currently, only function is supported	5	string	Yes
Tool message		2	object
content	The contents of the tool message	3	string or array	Yes
Text content	The contents of the tool message	4	string
Array of content parts	An array of content parts with a defined type. For tool messages, only type text is supported	4	array
Text content part		5	object
text	The text content	6	string	Yes
type	The type of the content part	6	string	Yes
role	The role of the messages author, in this case tool	3	string	Yes
tool_call_id	Tool call that this message is responding to	3	string	Yes
model	Model ID used to generate the response, like gpt-4o or o3	1	string	Yes
frequency_penalty	Number between -2.0 and 2.0. Defaults to 0	1	number or null		Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim
logit_bias	Modify the likelihood of specified tokens appearing in the completion.Defaults to null	1	map		Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.
max_completion_tokens	An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.	1	integer or null
n	How many chat completion choices to generate for each input message.Defaults to 1	1	integer or null		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.
parallel_tool_calls	Whether to enable parallel function calling during tool use.Defaults to true	1	boolean
presence_penalty	Number between -2.0 and 2.0.Defaults to 0	1	number or null		Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
response_format	An object specifying the format that the model must output	1	object
Text	Default response format. Used to generate text responses	2	object
type	The type of response format being defined. Always text	3	string	Yes
JSON schema	JSON Schema response format. Used to generate structured JSON responses	2	object
json_schema	Structured Outputs configuration options, including a JSON Schema	3	object	Yes
name	The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64	4	string	Yes
description	A description of what the response format is for, used by the model to determine how to respond in the format	4	string
schema	The schema for the response format, described as a JSON Schema object	4	object
strict	Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true	4	boolean or null
type	The type of response format being defined. Always json_schema	3	string	Yes
JSON object	JSON object response format	2	object		An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so
type	The type of response format being defined. Always json_object	3	string	Yes
seed	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. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend	1	integer or null
stop	Not supported with latest reasoning models o3 and o4-mini.Defaults to null	1	string/array/null		Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence
store	Whether or not to store the output of this chat completion request for use in our model distillation or evals products.Defaults to false	1	boolean or null		Supports text and image inputs. Note: image inputs over 8MB will be dropped
stream	If set to true, the model response data will be streamed to the client as it is generated using server-sent events.Defaults to false	1	boolean or null
stream_options	Options for streaming response. Only set this when you set stream: true.Defaults to null	1	object or null
include_obfuscation	When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an obfuscation field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream	2	boolean
include_usage	If set, an additional chunk will be streamed before the data: [DONE] message. The usage field on this chunk shows the token usage statistics for the entire request, and the choices field will always be an empty array	2	boolean		All other chunks will also include a usage field, but with a null value. NOTE: If the stream is interrupted, you may not receive the final usage chunk which contains the total token usage for the request
temperature	What sampling temperature to use, between 0 and 2.Defaults to 1	1	number or null		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_choice	Controls which (if any) tool is called by the model	1	string or object		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. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool
Tool choice mode		2	string		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
Function tool choice	Specifies a tool the model should use. Use to force the model to call a specific function	2	object
function		3	object	Yes
name	The name of the function to call	4	string	Yes
type	For function calling, the type is always function	3	object	Yes
tools	A list of tools the model may call	1	array
Function tool	A function tool that can be used to generate a response	2	object
function		3	object	Yes
name	The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64	4	string	Yes
description	A description of what the function does, used by the model to choose when and how to call the function	4	string
parameters	The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format	4	object
strict	Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field	4	boolean or null		Only a subset of JSON Schema is supported when strict is true
type	The type of the tool. Currently, only function is supported	3	string	Yes
top_p	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass	1	number or null		So 0.1 means only the tokens comprising the top 10% probability mass are considered

Return Result

Returns a chat completion object. If streaming is enabled in the request, it returns a streaming sequence of chat completion chunk objects

Example Request and Response Result

Default

Example

HTTP Python Node JS csharp

curl

curl https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT_PATH}/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {YOUR_ACCESS_KEY}" \
  -d '{
    "model": "gpt-5",
    "messages": [
      {
        "role": "developer",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'

python

from openai import OpenAI
client = OpenAI()

completion = client.chat.completions.create(
  model="gpt-5",
  messages=[
    {"role": "developer", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ]
)

print(completion.choices[0].message)

node js

import OpenAI from "openai";

const openai = new OpenAI();

async function main() {
  const completion = await openai.chat.completions.create({
    messages: [{ role: "developer", content: "You are a helpful assistant." }],
    model: "gpt-5",
    store: true,
  });

  console.log(completion.choices[0]);
}

main();

csharp

using System;
using System.Collections.Generic;

using OpenAI.Chat;

ChatClient client = new(
    model: "gpt-4.1",
    apiKey: Environment.GetEnvironmentVariable("YOUR_ACCESS_KEY")
);

List messages =
[
    new SystemChatMessage("You are a helpful assistant."),
    new UserChatMessage("Hello!")
];

ChatCompletion completion = client.CompleteChat(messages);

Console.WriteLine(completion.Content[0].Text);

Response Result

{
  "id": "chatcmpl-B9MBs8CjcvOU2jLn4n570S5qMJKcT",
  "object": "chat.completion",
  "created": 1741569952,
  "model": "gpt-4.1-2025-04-14",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you today?",
        "refusal": null,
        "annotations": []
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 19,
    "completion_tokens": 10,
    "total_tokens": 29,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "audio_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 0,
      "audio_tokens": 0,
      "accepted_prediction_tokens": 0,
      "rejected_prediction_tokens": 0
    }
  },
  "service_tier": "default"
}

Streaming Request

Example

HTTP Python Node JS csharp

curl

curl https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT_PATH}/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {YOUR_ACCESS_KEY}" \
  -d '{
    "model": "gpt-5",
    "messages": [
      {
        "role": "developer",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello!"
      }
    ],
    "stream": true
  }'

python

from openai import OpenAI
client = OpenAI()

completion = client.chat.completions.create(
  model="gpt-5",
  messages=[
    {"role": "developer", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ],
  stream=True
)

for chunk in completion:
  print(chunk.choices[0].delta)

print(completion.choices[0].message)

node js

import OpenAI from "openai";

const openai = new OpenAI();

async function main() {
  const completion = await openai.chat.completions.create({
    model: "gpt-5",
    messages: [
      {"role": "developer", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    stream: true,
  });

  for await (const chunk of completion) {
    console.log(chunk.choices[0].delta.content);
  }
}

main();

csharp

using System;
using System.ClientModel;
using System.Collections.Generic;
using System.Threading.Tasks;

using OpenAI.Chat;

ChatClient client = new(
    model: "gpt-4.1",
    apiKey: Environment.GetEnvironmentVariable("{YOUR_ACCESS_KEY}")
);

List messages =
[
    new SystemChatMessage("You are a helpful assistant."),
    new UserChatMessage("Hello!")
];

AsyncCollectionResult completionUpdates = client.CompleteChatStreamingAsync(messages);

await foreach (StreamingChatCompletionUpdate completionUpdate in completionUpdates)
{
    if (completionUpdate.ContentUpdate.Count > 0)
    {
        Console.Write(completionUpdate.ContentUpdate[0].Text);
    }
}

Response Result

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}]}

....

{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}

Functions

Example

HTTP Python Node JS csharp

curl

curl https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT_PATH}/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer {YOUR_ACCESS_KEY}" \
-d '{
  "model": "gpt-4.1",
  "messages": [
    {
      "role": "user",
      "content": "What is the weather like in Boston today?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and state, e.g. San Francisco, CA"
            },
            "unit": {
              "type": "string",
              "enum": ["celsius", "fahrenheit"]
            }
          },
          "required": ["location"]
        }
      }
    }
  ],
  "tool_choice": "auto"
}'

python

from openai import OpenAI
client = OpenAI()

tools = [
  {
    "type": "function",
    "function": {
      "name": "get_current_weather",
      "description": "Get the current weather in a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. San Francisco, CA",
          },
          "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
        },
        "required": ["location"],
      },
    }
  }
]
messages = [{"role": "user", "content": "What's the weather like in Boston today?"}]
completion = client.chat.completions.create(
  model="gpt-5",
  messages=messages,
  tools=tools,
  tool_choice="auto"
)

print(completion)

node js

import OpenAI from "openai";

const openai = new OpenAI();

async function main() {
  const messages = [{"role": "user", "content": "What's the weather like in Boston today?"}];
  const tools = [
      {
        "type": "function",
        "function": {
          "name": "get_current_weather",
          "description": "Get the current weather in a given location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA",
              },
              "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
            },
            "required": ["location"],
          },
        }
      }
  ];

  const response = await openai.chat.completions.create({
    model: "gpt-4.1",
    messages: messages,
    tools: tools,
    tool_choice: "auto",
  });

  console.log(response);
}

main();

csharp

using System;
using System.Collections.Generic;

using OpenAI.Chat;

ChatClient client = new(
    model: "gpt-4.1",
    apiKey: Environment.GetEnvironmentVariable("{YOUR_ACCESS_KEY}")
);

ChatTool getCurrentWeatherTool = ChatTool.CreateFunctionTool(
    functionName: "get_current_weather",
    functionDescription: "Get the current weather in a given location",
    functionParameters: BinaryData.FromString("""
        {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA"
                },
                "unit": {
                    "type": "string",
                    "enum": [ "celsius", "fahrenheit" ]
                }
            },
            "required": [ "location" ]
        }
    """)
);

List messages =
[
    new UserChatMessage("What's the weather like in Boston today?"),
];

ChatCompletionOptions options = new()
{
    Tools =
    {
        getCurrentWeatherTool
    },
    ToolChoice = ChatToolChoice.CreateAutoChoice(),
};

ChatCompletion completion = client.CompleteChat(messages, options);

Response Result

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1699896916,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": null,
        "tool_calls": [
          {
            "id": "call_abc123",
            "type": "function",
            "function": {
              "name": "get_current_weather",
              "arguments": "{\n\"location\": \"Boston, MA\"\n}"
            }
          }
        ]
      },
      "logprobs": null,
      "finish_reason": "tool_calls"
    }
  ],
  "usage": {
    "prompt_tokens": 82,
    "completion_tokens": 17,
    "total_tokens": 99,
    "completion_tokens_details": {
      "reasoning_tokens": 0,
      "accepted_prediction_tokens": 0,
      "rejected_prediction_tokens": 0
    }
  }
}

Logprobs

Example

HTTP Python Node JS csharp

curl

curl https://genaiapi.cloudsway.net/v1/ai/{ENDPOINT_PATH}/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer {YOUR_ACCESS_KEY}" \
  -d '{
    "model": "gpt-5",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ],
    "logprobs": true,
    "top_logprobs": 2
  }'

python

from openai import OpenAI
client = OpenAI()

completion = client.chat.completions.create(
  model="gpt-5",
  messages=[
    {"role": "user", "content": "Hello!"}
  ],
  logprobs=True,
  top_logprobs=2
)

print(completion.choices[0].message)
print(completion.choices[0].logprobs)

node js

import OpenAI from "openai";

const openai = new OpenAI();

async function main() {
  const completion = await openai.chat.completions.create({
    messages: [{ role: "user", content: "Hello!" }],
    model: "gpt-5",
    logprobs: true,
    top_logprobs: 2,
  });

  console.log(completion.choices[0]);
}

main();

csharp

using System;
using System.Collections.Generic;

using OpenAI.Chat;

ChatClient client = new(
    model: "gpt-4.1",
    apiKey: Environment.GetEnvironmentVariable("{YOUR_ACCESS_KEY}")
);

List messages =
[
    new UserChatMessage("Hello!")
];

ChatCompletionOptions options = new()
{
    IncludeLogProbabilities = true,
    TopLogProbabilityCount = 2
};

ChatCompletion completion = client.CompleteChat(messages, options);

Console.WriteLine(completion.Content[0].Text);

Response Result

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1702685778,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you today?"
      },
      "logprobs": {
        "content": [
          {
            "token": "Hello",
            "logprob": -0.31725305,
            "bytes": [72, 101, 108, 108, 111],
            "top_logprobs": [
              {
                "token": "Hello",
                "logprob": -0.31725305,
                "bytes": [72, 101, 108, 108, 111]
              },
              {
                "token": "Hi",
                "logprob": -1.3190403,
                "bytes": [72, 105]
              }
            ]
          },
          {
            "token": "!",
            "logprob": -0.02380986,
            "bytes": [
              33
            ],
            "top_logprobs": [
              {
                "token": "!",
                "logprob": -0.02380986,
                "bytes": [33]
              },
              {
                "token": " there",
                "logprob": -3.787621,
                "bytes": [32, 116, 104, 101, 114, 101]
              }
            ]
          },
          {
            "token": " How",
            "logprob": -0.000054669687,
            "bytes": [32, 72, 111, 119],
            "top_logprobs": [
              {
                "token": " How",
                "logprob": -0.000054669687,
                "bytes": [32, 72, 111, 119]
              },
              {
                "token": "<|end|>",
                "logprob": -10.953937,
                "bytes": null
              }
            ]
          },
          {
            "token": " can",
            "logprob": -0.015801601,
            "bytes": [32, 99, 97, 110],
            "top_logprobs": [
              {
                "token": " can",
                "logprob": -0.015801601,
                "bytes": [32, 99, 97, 110]
              },
              {
                "token": " may",
                "logprob": -4.161023,
                "bytes": [32, 109, 97, 121]
              }
            ]
          },
          {
            "token": " I",
            "logprob": -3.7697225e-6,
            "bytes": [
              32,
              73
            ],
            "top_logprobs": [
              {
                "token": " I",
                "logprob": -3.7697225e-6,
                "bytes": [32, 73]
              },
              {
                "token": " assist",
                "logprob": -13.596657,
                "bytes": [32, 97, 115, 115, 105, 115, 116]
              }
            ]
          },
          {
            "token": " assist",
            "logprob": -0.04571125,
            "bytes": [32, 97, 115, 115, 105, 115, 116],
            "top_logprobs": [
              {
                "token": " assist",
                "logprob": -0.04571125,
                "bytes": [32, 97, 115, 115, 105, 115, 116]
              },
              {
                "token": " help",
                "logprob": -3.1089056,
                "bytes": [32, 104, 101, 108, 112]
              }
            ]
          },
          {
            "token": " you",
            "logprob": -5.4385737e-6,
            "bytes": [32, 121, 111, 117],
            "top_logprobs": [
              {
                "token": " you",
                "logprob": -5.4385737e-6,
                "bytes": [32, 121, 111, 117]
              },
              {
                "token": " today",
                "logprob": -12.807695,
                "bytes": [32, 116, 111, 100, 97, 121]
              }
            ]
          },
          {
            "token": " today",
            "logprob": -0.0040071653,
            "bytes": [32, 116, 111, 100, 97, 121],
            "top_logprobs": [
              {
                "token": " today",
                "logprob": -0.0040071653,
                "bytes": [32, 116, 111, 100, 97, 121]
              },
              {
                "token": "?",
                "logprob": -5.5247097,
                "bytes": [63]
              }
            ]
          },
          {
            "token": "?",
            "logprob": -0.0008108172,
            "bytes": [63],
            "top_logprobs": [
              {
                "token": "?",
                "logprob": -0.0008108172,
                "bytes": [63]
              },
              {
                "token": "?\n",
                "logprob": -7.184561,
                "bytes": [63, 10]
              }
            ]
          }
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 9,
    "total_tokens": 18,
    "completion_tokens_details": {
      "reasoning_tokens": 0,
      "accepted_prediction_tokens": 0,
      "rejected_prediction_tokens": 0
    }
  },
  "system_fingerprint": null
}