Tokatlas

外觀

English
Chat

檔案分析 ​

使用 Chat Completions API 分析圖像、音訊與檔案。

Chat Completions API 透過 messages 陣列中的內容部分支援多模態輸入。使用者訊息可包含文字、圖像、音訊與檔案。

端點與驗證方式同建立聊天回應。

請先確認所選模型支援對應媒體類型。file_id 必須來自同一服務與帳戶可讀取的上傳結果；本頁未定義上傳端點，不可直接使用其他供應商的檔案 ID。網址須可由服務端存取，本機路徑不能當作遠端檔案網址。

目前本地網關的 /v1/files 上傳路由尚未實作。首次串接請使用本頁的 URL 或 Base64 輸入方式；只有已確認部署環境支援上傳，且已取得同帳戶可讀取的檔案 ID 時，才使用 file_id 範例。

內容部分類型 ​

類型說明
text文字提示（必須包含 text 欄位）
image_url透過 URL 或 Base64 資料輸入圖像；可選 detail：auto、low、high
input_audio透過 Base64 資料輸入音訊；format：wav 或 mp3
file使用 file_id，或以 file_data 搭配 filename 傳入檔案；檔名本身不包含檔案內容

圖像分析 ​

透過 URL 分析圖像：

json
{
  "model": "gpt-5",
  "messages": [
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "What is in this image?"},
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/image.jpg",
            "detail": "auto"
          }
        }
      ]
    }
  ],
  "max_completion_tokens": 300,
  "stream": false
}

Base64 編碼圖像：

json
{
  "model": "gpt-5",
  "messages": [
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "Describe this image."},
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/jpeg;base64,/9j/4AAQSkZJRg..."
          }
        }
      ]
    }
  ]
}

音訊分析 ​

以 Base64 編碼的內容部分傳送音訊：

json
{
  "model": "gpt-4o-audio-preview",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_audio",
          "input_audio": {
            "data": "<base64-encoded-audio>",
            "format": "wav"
          }
        },
        {"type": "text", "text": "Transcribe and summarize this audio."}
      ]
    }
  ]
}

支援的音訊格式：wav、mp3。

檔案分析 ​

使用 Files API 傳回的檔案 ID 分析文件：

json
{
  "model": "gpt-5",
  "messages": [
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "Summarize this document"},
        {
          "type": "file",
          "file": {
            "file_id": "file-abc123"
          }
        }
      ]
    }
  ]
}

請求範例 ​

執行方式見多語言範例說明。先設定 API_KEY，並替換模型、檔案網址及 ID 占位值；四種方式會顯示相同請求的原始回應。

bash
curl --fail-with-body --silent --show-error --max-time 180 \
  --request POST \
  --url "https://api.tokatlas.ai/v1/chat/completions" \
  --header "Authorization: Bearer $API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "gpt-5",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/image.jpg"
          }
        }
      ]
    }
  ],
  "stream": false
}'
python
import os
import requests

headers = {
    'Authorization': 'Bearer ' + os.environ["API_KEY"],
    'Content-Type': 'application/json',
}
payload = {'model': 'gpt-5',
 'messages': [{'role': 'user',
               'content': [{'type': 'text', 'text': 'What is in this image?'},
                           {'type': 'image_url',
                            'image_url': {'url': 'https://example.com/image.jpg'}}]}],
 'stream': False}
response = requests.request(
    'POST', 'https://api.tokatlas.ai/v1/chat/completions', headers=headers,
    json=payload,
    timeout=180,
)
response.raise_for_status()
print(response.text)
js
if (!process.env.API_KEY) throw new Error("Set API_KEY first.");
const response = await fetch("https://api.tokatlas.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "gpt-5",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/image.jpg"
          }
        }
      ]
    }
  ],
  "stream": false
}),
  signal: AbortSignal.timeout(180_000),
});
if (!response.ok) {
  throw new Error(`HTTP ${response.status}: ${await response.text()}`);
}
console.log(await response.text());
java
import java.net.URI;
import java.net.http.*;
import java.time.Duration;

public class Example {
    public static void main(String[] args) throws Exception {
        String apiKey = System.getenv("API_KEY");
        if (apiKey == null || apiKey.isBlank()) {
            throw new IllegalArgumentException("Set API_KEY first.");
        }
        String payload = String.join("\n",
            "{",
            "  \"model\": \"gpt-5\",",
            "  \"messages\": [",
            "    {",
            "      \"role\": \"user\",",
            "      \"content\": [",
            "        {",
            "          \"type\": \"text\",",
            "          \"text\": \"What is in this image?\"",
            "        },",
            "        {",
            "          \"type\": \"image_url\",",
            "          \"image_url\": {",
            "            \"url\": \"https://example.com/image.jpg\"",
            "          }",
            "        }",
            "      ]",
            "    }",
            "  ],",
            "  \"stream\": false",
            "}"
        );
        HttpClient client = HttpClient.newBuilder()
            .connectTimeout(Duration.ofSeconds(30)).build();
        HttpRequest request = HttpRequest.newBuilder()
            .uri(URI.create("https://api.tokatlas.ai/v1/chat/completions"))
            .timeout(Duration.ofSeconds(180))
            .header("Authorization", "Bearer " + apiKey)
            .header("Content-Type", "application/json")
            .method("POST", HttpRequest.BodyPublishers.ofString(payload))
            .build();
        HttpResponse<String> response = client.send(
            request, HttpResponse.BodyHandlers.ofString());
        if (response.statusCode() < 200 || response.statusCode() >= 300) {
            throw new IllegalStateException("HTTP " + response.statusCode() + ": "
                + response.body());
        }
        System.out.println(response.body());
    }
}

回應範例 ​

json
{
  "code": 200,
  "data": {
    "id": "chatcmpl-B9MHDbslfkBeAs8l4bebGdFOJ6PeG",
    "object": "chat.completion",
    "created": 1741570283,
    "model": "gpt-5",
    "choices": [
      {
        "index": 0,
        "message": {
          "role": "assistant",
          "content": "The image shows a wooden boardwalk path running through a lush green field or meadow. The sky is bright blue with some scattered clouds.",
          "refusal": null
        },
        "finish_reason": "stop"
      }
    ],
    "usage": {
      "prompt_tokens": 1117,
      "completion_tokens": 46,
      "total_tokens": 1163,
      "prompt_tokens_details": {
        "image_tokens": 1100
      }
    }
  }
}

相關主題 ​