TextGPTGPT-5.5

GPT-5.5 - Complete API Reference

Use OpenAI SDK format to call GPT-5.5 model

Synchronous processing mode, real-time response
Text conversation: Single or multi-turn contextual dialogue
System prompts: Customize AI role and behavior
Multimodal input: Supports text + image mixed input
Quick start? Check out Quick Start Guide

<Note> **BaseURL**: The default BaseURL is `https://api.starmagic.ai`, which has better support for text models and long-lived connections. `https://api.starmagic.ai` is the primary endpoint for multimodal services and serves as a fallback address for text models. </Note>

Authorization

AuthorizationstringheaderRequired

## All APIs require Bearer Token authentication ## **Get API Key:** Visit [API Key Management Page](https://starmagic.ai/app/api-keys) to get your API Key **Add to request header:** ``` Authorization: Bearer YOUR_API_KEY ```

Authorization: Bearer YOUR_API_KEY

Request body

application/json

modelenum<gpt-5.5>Required

Model name for chat completion

"gpt-5.5"

messagesobject[]Required

List of messages for the conversation, supports multi-turn dialogue and multimodal input (text, images)

[
  {
    "role": "user",
    "content": [
      null
    ]
  }
]

streamboolean

Whether to stream the response - `true`: Stream response, returns content chunk by chunk in real-time - `false`: Wait for complete response and return all at once

false

temperaturenumber

Sampling temperature, controls randomness of output **Notes**: - Lower values (e.g., 0.2): More deterministic and focused output - Higher values (e.g., 1.5): More random and creative output

0.7

top_pnumber

Nucleus sampling parameter **Notes**: - Controls sampling from tokens with cumulative probability - For example, 0.9 means sampling from tokens with top 90% cumulative probability - Default: 1.0 (considers all tokens) **Recommendation**: Do not adjust both temperature and top_p simultaneously

0.9

top_kinteger

Top-K sampling parameter **Notes**: - For example, 10 means only considering the top 10 most probable tokens during each sampling step - Smaller values make output more focused - Default: unlimited

Response

application/json

成功

Response body

idstring

Unique identifier for the chat completion

"chatcmpl-20251010015944503180122WJNB8Eid"

modelstring

The model used for completion

"gpt-5.5"

objectenum<chat.completion>

Response type

"chat.completion"

createdinteger

Unix timestamp when the completion was created

1760032810

choicesobject[]

List of completion choices

[
  {
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! I'm GPT-5.5, with enhanced reasoning and understanding capabilities. I excel at handling complex problems, multi-step reasoning, and code generation.\\n\\nKey features include:\\n- Stronger logical reasoning\\n- Better context understanding\\n- More accurate code generation"
    },
    "finish_reason": "stop"
  }
]

usageobject

Token usage statistics

{
  "prompt_tokens": 13,
  "completion_tokens": 1891,
  "total_tokens": 1904,
  "prompt_tokens_details": {
    "cached_tokens": 0,
    "text_tokens": 13,
    "audio_tokens": 0,
    "image_tokens": 0
  },
  "completion_tokens_details": {
    "text_tokens": 0,
    "audio_tokens": 0,
    "reasoning_tokens": 1480
  },
  "input_tokens": 0,
  "output_tokens": 0,
  "input_tokens_details": null
}

POST/v1/chat/completions

curl --request POST \
  --url https://api.starmagic.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "gpt-5.5",
  "messages": [
    {
      "role": "user",
      "content": "Please introduce yourself"
    }
  ]
}'

Response: 成功

{
  "id": "chatcmpl-20251010015944503180122WJNB8Eid",
  "model": "gpt-5.5",
  "object": "chat.completion",
  "created": 1760032810,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": null,
        "content": null
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 13,
    "completion_tokens": 1891,
    "total_tokens": 1904,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 13,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 1480
    },
    "input_tokens": 0,
    "output_tokens": 0,
    "input_tokens_details": null
  }
}

GPT-5.5 - 快速开始

MiniMax-M2.5 - 完整参数文档

[ { "index": 0, "message": { "role": "assistant", "content": "Hello! I'm GPT-5.5, with enhanced reasoning and understanding capabilities. I excel at handling complex problems, multi-step reasoning, and code generation.\\n\\nKey features include:\\n- Stronger logical reasoning\\n- Better context understanding\\n- More accurate code generation" }, "finish_reason": "stop" } ]

{ "prompt_tokens": 13, "completion_tokens": 1891, "total_tokens": 1904, "prompt_tokens_details": { "cached_tokens": 0, "text_tokens": 13, "audio_tokens": 0, "image_tokens": 0 }, "completion_tokens_details": { "text_tokens": 0, "audio_tokens": 0, "reasoning_tokens": 1480 }, "input_tokens": 0, "output_tokens": 0, "input_tokens_details": null }

curl --request POST \ --url https://api.starmagic.ai/v1/chat/completions \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data '{ "model": "gpt-5.5", "messages": [ { "role": "user", "content": "Please introduce yourself" } ] }'

{ "id": "chatcmpl-20251010015944503180122WJNB8Eid", "model": "gpt-5.5", "object": "chat.completion", "created": 1760032810, "choices": [ { "index": 0, "message": { "role": null, "content": null }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 13, "completion_tokens": 1891, "total_tokens": 1904, "prompt_tokens_details": { "cached_tokens": 0, "text_tokens": 13, "audio_tokens": 0, "image_tokens": 0 }, "completion_tokens_details": { "text_tokens": 0, "audio_tokens": 0, "reasoning_tokens": 1480 }, "input_tokens": 0, "output_tokens": 0, "input_tokens_details": null } }