Beantragung und Nutzung der Gemini Chat Completion API

{
  "id": "chatcmpl-20251122212413908150493uPhjTUO9",
  "model": "gemini-3.5-flash",
  "object": "chat.completion",
  "created": 1763817866,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I am a large language model, trained by Google.",
        "reasoning_content": "**My Reasoning: Answering the User's Question**\n\nOkay, here's how I'm going to approach answering the user's question, \"What model are you?\". The core is to be direct and informative. First, I have to be clear about my origin. Then, I need to make sure the explanation is accessible, given that the user may not be familiar with technical jargon. I need to explain what a \"large language model\" actually *does*, and provide relatable examples. I know the user might be looking for a specific name, like other models have, so I'll address that directly and then wrap it up with an invitation to continue.\n\nSo, here's my plan:\n\n1.  **Lead with the key info:** I'll begin by stating that I am a large language model created by Google. That is the fundamental, most critical piece of the puzzle.\n2.  **Define the buzzword:** Then, I'll explain that \"large language model\" in simple terms. I'll explain what I *do* - process and generate text; how I *do* it - by training on huge amounts of text data; and the *goal* - to be able to communicate like a human.\n3.  **Provide context:** After that, to make the concept even clearer, I'll provide a list of examples of my capabilities. I'll mention things like answering questions, summarizing texts, writing stories, translating languages, and brainstorming ideas.\n4.  **Acknowledge the lack of a personal name:** I'll anticipate the likely question about a model name (like ChatGPT) by clearly stating that I don't have a personal name and that it's best to think of me as an AI assistant from Google.\n5.  **End with an invitation:** Lastly, I'll end with a simple, friendly question to invite further interaction and to guide the conversation.\n\nWith this approach, I am confident I can successfully answer this important question.\n"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 932,
    "total_tokens": 940,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 8,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 921
    },
    "input_tokens": 0,
    "output_tokens": 0,
    "input_tokens_details": null,
    "claude_cache_creation_5_m_tokens": 0,
    "claude_cache_creation_1_h_tokens": 0
  }
}

import base64
import requests

url = "https://api.acedata.cloud/gemini/chat/completions"

# 把本地图片读成 base64 data URI
with open("image.jpg", "rb") as f:
    base64_image = base64.b64encode(f.read()).decode("utf-8")
data_uri = f"data:image/jpeg;base64,{base64_image}"

headers = {
    "accept": "application/json",
    "authorization": "Bearer {token}",
    "content-type": "application/json"
}

payload = {
    "model": "gemini-3.1-pro-preview",
    "messages": [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "请用一句话描述这张图片。"},
                {"type": "image_url", "image_url": {"url": data_uri}}
            ]
        }
    ]
}

response = requests.post(url, json=payload, headers=headers)
print(response.text)

payload = {
    "model": "gemini-3.1-pro-preview",
    "messages": [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "请用一句话描述这张图片。"},
                {"type": "image_url", "image_url": {"url": "https://cdn.acedata.cloud/4hfydw.jpg"}}
            ]
        }
    ]
}

import requests

url = "https://api.acedata.cloud/gemini/chat/completions"

headers = {
    "accept": "application/json",
    "authorization": "Bearer {token}",
    "content-type": "application/json"
}

payload = {
    "model": "gemini-2.5-pro",
    "messages": [{"role":"user","content":"Hello,What model are you?"}],
    "stream": True,
    "stream_options": {"include_usage": True}
}

response = requests.post(url, json=payload, headers=headers)
print(response.text)

data: {"id": "chatcmpl-20251122214038810722821kNjUTjtr", "object": "chat.completion.chunk", "created": 1763818842, "model": "gemini-2.5-pro", "system_fingerprint": null, "choices": [{"delta": {"content": "", "role": "assistant"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null}

data: {"id": "chatcmpl-20251122214038810722821kNjUTjtr", "object": "chat.completion.chunk", "created": 1763818842, "model": "gemini-2.5-pro", "system_fingerprint": null, "choices": [{"delta": {"reasoning_content": "**Define My Nature**\n\nMy thinking has started. The user wants to know my nature, asking a direct \"what are you?\" The initial step was straightforward: identifying the query. Now, I recall my fundamental identity: I'm a large language model. This is the core truth I aim to convey.\n\n\n"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null}

data: {"id": "chatcmpl-20251122214038810722821kNjUTjtr", "object": "chat.completion.chunk", "created": 1763818842, "model": "gemini-2.5-pro", "system_fingerprint": null, "choices": [{"delta": {"reasoning_content": "**Refining My Response**\n\nI've added the crucial information that I'm trained by Google to the basic \"large language model\" identity. My next step is considering what being a \"large language model\" actually entails, so I can explain my core capabilities. I'm focusing on providing context without going into specific technical details or model names. I want to convey my function in a way the user can easily understand.\n\n\n"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null}

data: {"id": "chatcmpl-20251122214038810722821kNjUTjtr", "object": "chat.completion.chunk", "created": 1763818842, "model": "gemini-2.5-pro", "system_fingerprint": null, "choices": [{"delta": {"reasoning_content": "**Confirming Core Identity**\n\nI'm now solidifying my response. The user's query about my model affiliation needs a focused answer. I've pinpointed that \"trained by Google\" is essential, providing key context. I'm resisting the urge to mention any specific model names, as it's not relevant. The aim is to deliver a direct, accurate statement. My goal remains a clear and concise reply, avoiding technical jargon and getting straight to the relevant point.\n\n\n"}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null}

data: {"id": "chatcmpl-20251122214038810722821kNjUTjtr", "object": "chat.completion.chunk", "created": 1763818842, "model": "gemini-2.5-pro", "system_fingerprint": null, "choices": [{"delta": {"content": "I am a large language model, trained by Google."}, "logprobs": null, "finish_reason": null, "index": 0}], "usage": null}

data: {"id": "chatcmpl-20251122214038810722821kNjUTjtr", "object": "chat.completion.chunk", "created": 1763818842, "model": "gemini-2.5-pro", "system_fingerprint": null, "choices": [{"delta": {}, "logprobs": null, "finish_reason": "stop", "index": 0}], "usage": null}

data: {"id": "chatcmpl-20251122214038810722821kNjUTjtr", "object": "chat.completion.chunk", "created": 1763818842, "model": "gemini-2.5-pro", "system_fingerprint": "", "choices": [], "usage": {"prompt_tokens": 8, "completion_tokens": 527, "total_tokens": 535, "prompt_tokens_details": {"cached_tokens": 0, "text_tokens": 8, "audio_tokens": 0, "image_tokens": 0}, "completion_tokens_details": {"text_tokens": 0, "audio_tokens": 0, "reasoning_tokens": 519}, "input_tokens": 0, "output_tokens": 0, "input_tokens_details": null, "claude_cache_creation_5_m_tokens": 0, "claude_cache_creation_1_h_tokens": 0}}

data: [DONE]

const options = {
  method: "POST",
  headers: {
    accept: "application/json",
    authorization: "Bearer {token}",
    "content-type": "application/json"
  },
  body: JSON.stringify({
    model: "gemini-2.5-pro",
    messages: [{ role: "user", content: "Hello, what model are you?" }],
    stream: true
  })
};

const response = await fetch("https://api.acedata.cloud/gemini/chat/completions", options);
const reader = response.body.getReader();
const decoder = new TextDecoder("utf-8");
while (true) {
  const { value, done } = await reader.read();
  if (done) break;
  process.stdout.write(decoder.decode(value));
}

JSONObject jsonObject = new JSONObject();
jsonObject.put("model", "gemini-2.5-pro");
jsonObject.put("messages", new JSONArray().put(new JSONObject().put("role", "user").put("content", "Hello, what model are you?")));
jsonObject.put("stream", true);
MediaType mediaType = MediaType.parse("application/json; charset=utf-8");
RequestBody body = RequestBody.create(jsonObject.toString(), mediaType);
Request request = new Request.Builder()
  .url("https://api.acedata.cloud/gemini/chat/completions")
  .post(body)
  .addHeader("accept", "application/json")
  .addHeader("authorization", "Bearer {token}")
  .addHeader("content-type", "application/json")
  .build();

OkHttpClient client = new OkHttpClient();
Response response = client.newCall(request).execute();
System.out.println(response.body().string());

import requests

url = "https://api.acedata.cloud/gemini/chat/completions"

headers = {
    "accept": "application/json",
    "authorization": "Bearer {token}",
    "content-type": "application/json"
}

payload = {
    "model": "gemini-2.5-pro",
    "messages": [{"role":"user","content":"Hello"},{"role":"assistant","content":"Hello there! How can I help you today?"},{"role":"user","content":"What model are you?"}]
}

response = requests.post(url, json=payload, headers=headers)
print(response.text)

{
  "id": "chatcmpl-20251122214426669120974AKFwnJd1",
  "model": "gemini-2.5-pro",
  "object": "chat.completion",
  "created": 1763819072,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I am a large language model, trained by Google.",
        "reasoning_content": "Okay, here's how I'd approach this, thinking as a sophisticated AI:\n\nFirst, the user is directly querying my core identity: \"What model are you?\" That's a simple, straightforward question. My primary task is to provide accurate and helpful information, so I need to answer this immediately.\n\nRight off the bat, I know the answer. I *am* a large language model. That's my fundamental architecture and operational principle. I'm built on a vast network of connections and trained on a massive dataset.\n\nThen I must add the necessary context. Crucially, I have to provide the source of my training. I *was* trained by Google. That's a key identifier. It provides the user with valuable information about my origin and potential biases (though I'm trained to mitigate them).\n\nNow I must construct the response. My goal is to be factual, concise, and understandable.\n\nThe synthesized response is something like: \"I am a large language model, trained by Google.\"\n\nI have to assess the output: Does it meet the criteria? It's clear. It states what I am, it includes a critical piece of information on my origins, and it avoids jargon. No misleading promises.\n\nFinal verification: Does it actually answer the question? Yes. Is the information correct and truthful? Yes. Is it concise? Absolutely. Is the tone appropriate for any user? Yes. And, finally, this is the standard, approved response. Excellent.\n"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 16,
    "completion_tokens": 265,
    "total_tokens": 281,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 16,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 254
    },
    "input_tokens": 0,
    "output_tokens": 0,
    "input_tokens_details": null,
    "claude_cache_creation_5_m_tokens": 0,
    "claude_cache_creation_1_h_tokens": 0
  }
}

{
  "model": "gemini-3.1-pro-preview",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "图片的内容是什么？"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://cdn.acedata.cloud/qzx2z1.png"
          }
        }
      ]
    }
  ],
  "stream": false
}

{
    "id": "chatcmpl-20251206001815715692730UVZe38kB",
    "model": "gemini-3.1-pro-preview",
    "object": "chat.completion",
    "created": 1764951548,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "Dies ist ein Outdoor-Halbporträtfoto einer jungen Frau.\n\nIm Folgenden wird der Hauptinhalt des Bildes beschrieben:\n\n*   **Aussehen der Person**: Das Mädchen auf dem Foto hat langes, glattes, pechschwarzes und geschmeidiges Haar, zarte Gesichtszüge und helle Haut. Sie trägt ein sanftes Lächeln und blickt in die Kamera.\n*   **Kleidung und Styling**: Sie trägt ein cremeweißes oder hell apricotfarbenes Oberteil mit Puffärmeln, darüber kombiniert sie ein schwarzes Kleidungsstück (das wie ein Trägerkleid oder eine Weste aussieht).\n*   **Licht- und Schattenatmosphäre**: Das Sonnenlicht scheint von links hinten herüber und fällt auf ihr Haar, wodurch sich ein warmer goldgelber Lichtkranz bildet, der eine frische und ästhetische Atmosphäre schafft.\n*   **Hintergrund**: Der Hintergrund ist unscharf dargestellt, und man kann erkennen, dass es im Freien ist. Hinter ihr befinden sich eine leere Straße (Asphaltstraße) sowie grüne Bäume am Straßenrand.\n\nInsgesamt vermittelt dieses Foto ein süßes, sonniges und mädchenhaft-nachbarliches Gefühl."
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 1092,
        "completion_tokens": 1271,
        "total_tokens": 2363,
        "prompt_tokens_details": {
            "cached_tokens": 0,
            "text_tokens": 4,
            "audio_tokens": 0,
            "image_tokens": 0
        },
        "completion_tokens_details": {
            "text_tokens": 0,
            "audio_tokens": 0,
            "reasoning_tokens": 1072
        },
        "input_tokens": 0,
        "output_tokens": 0,
        "input_tokens_details": null,
        "claude_cache_creation_5_m_tokens": 0,
        "claude_cache_creation_1_h_tokens": 0
    }
}

{
  "model": "gemini-3.1-pro-preview",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Was ist der Inhalt des Videos?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://cdn.acedata.cloud/58yioe.mp4"
          }
        }
      ]
    }
  ],
  "stream": false
}

{
    "id": "chatcmpl-20251206002711949677736JC9yL8AE",
    "model": "gemini-3.1-pro-preview",
    "object": "chat.completion",
    "created": 1764952060,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "Der Inhalt dieses Videos ist voller Unterhaltung und zeigt hauptsächlich eine **orangefarbene Katze**, die in der Abenddämmerung selbstbewusst auf einer ländlichen Straße leicht dahintrabt.\n\nDie konkreten Details sind wie folgt:\n\n1.  **Bildinhalt**:\n    *   Der Hauptdarsteller ist eine orangefarbene getigerte Katze.\n    *   Der Hintergrund zeigt die Zeit des Sonnenuntergangs (oder des frühen Morgens), das Licht ist goldgelb und sanft. Am Straßenrand befinden sich ein Holzzaun und weites, offenes Land, und in der Ferne ist zudem die Silhouette eines Fußgängers zu sehen.\n    *   Die Kamera wurde aus einem niedrigen Winkel aufgenommen; mal wird die Katze gefilmt, wie sie direkt auf die Kamera zuläuft, mal ihr Rücken beim Weglaufen, außerdem gibt es Nahaufnahmen des Gesichts und der Musterung der Katze.\n\n2.  **Klangmerkmale (Kernpunkt)**:\n    *   Die Vertonung des Videos ist sehr charakteristisch. Obwohl das Bild eine leichtfüßig laufende Katze zeigt, ist der hinzugefügte Klang **schwerer und rhythmischer Hufschläge** (oder ein Klang ähnlich dem von Holzpantoffeln/High Heels, die auf den Boden schlagen).\n    *   Der Kontrast zwischen diesem Klang und dem Bild erzeugt ein Gefühl von Humor, als ob diese Katze sich selbst für ein galoppierendes Pferd hält.\n\nInsgesamt handelt es sich um ein Haustier-Video, das den Kontrast zwischen Ton und Bild nutzt, um einen niedlichen und humorvollen Effekt zu erzeugen."
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 915,
        "completion_tokens": 1423,
        "total_tokens": 2338,
        "prompt_tokens_details": {
            "cached_tokens": 0,
            "text_tokens": 5,
            "audio_tokens": 0,
            "image_tokens": 0
        },
        "completion_tokens_details": {
            "text_tokens": 0,
            "audio_tokens": 0,
            "reasoning_tokens": 1162
        },
        "input_tokens": 0,
        "output_tokens": 0,
        "input_tokens_details": null,
        "claude_cache_creation_5_m_tokens": 0,
        "claude_cache_creation_1_h_tokens": 0
    }
}

{
  "model": "gemini-3.1-pro-preview",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Was ist der Inhalt des Bildes?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://cdn.acedata.cloud/qzx2z1.png"
          }
        }
      ]
    }
  ],
  "stream": false
}

{
  "model": "gemini-3.1-pro-preview",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Was ist der Inhalt des Videos?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://cdn.acedata.cloud/58yioe.mp4"
          }
        }
      ]
    }
  ],
  "stream": false
}

{
  "success": false,
  "error": {
    "code": "api_error",
    "message": "fetch failed"
  },
  "trace_id": "2cf86e86-22a4-46e1-ac2f-032c0f2a4e89"
}