Generering av innhold med Gemini

POST

v1beta

models

{model}

{operator}

from google import genai

client = genai.Client(
    api_key="<COMETAPI_KEY>",
    http_options={"api_version": "v1beta", "base_url": "https://api.cometapi.com"},
)

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Explain how AI works in a few words",
)

print(response.text)

{
  "candidates": [
    {
      "content": {
        "role": "<string>",
        "parts": [
          {
            "text": "<string>",
            "functionCall": {
              "name": "<string>",
              "args": {}
            },
            "inlineData": {
              "mimeType": "<string>",
              "data": "<string>"
            },
            "thought": true
          }
        ]
      },
      "finishReason": "STOP",
      "safetyRatings": [
        {
          "category": "<string>",
          "probability": "<string>",
          "blocked": true
        }
      ],
      "citationMetadata": {
        "citationSources": [
          {
            "startIndex": 123,
            "endIndex": 123,
            "uri": "<string>",
            "license": "<string>"
          }
        ]
      },
      "tokenCount": 123,
      "avgLogprobs": 123,
      "groundingMetadata": {
        "groundingChunks": [
          {
            "web": {
              "uri": "<string>",
              "title": "<string>"
            }
          }
        ],
        "groundingSupports": [
          {
            "groundingChunkIndices": [
              123
            ],
            "confidenceScores": [
              123
            ],
            "segment": {
              "startIndex": 123,
              "endIndex": 123,
              "text": "<string>"
            }
          }
        ],
        "webSearchQueries": [
          "<string>"
        ]
      },
      "index": 123
    }
  ],
  "promptFeedback": {
    "blockReason": "SAFETY",
    "safetyRatings": [
      {
        "category": "<string>",
        "probability": "<string>",
        "blocked": true
      }
    ]
  },
  "usageMetadata": {
    "promptTokenCount": 123,
    "candidatesTokenCount": 123,
    "totalTokenCount": 123,
    "trafficType": "<string>",
    "thoughtsTokenCount": 123,
    "promptTokensDetails": [
      {
        "modality": "<string>",
        "tokenCount": 123
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "<string>",
        "tokenCount": 123
      }
    ]
  },
  "modelVersion": "<string>",
  "createTime": "<string>",
  "responseId": "<string>"
}

Oversikt

CometAPI støtter det opprinnelige Gemini API-formatet, og gir deg full tilgang til Gemini-spesifikke funksjoner som kontroll av tenking, Google Search-grounding, opprinnelige modaliteter for bildegenerering og mer. Bruk dette endepunktet når du trenger funksjonalitet som ikke er tilgjengelig gjennom OpenAI-compatible chat endpoint.

Hurtigstart

Bytt ut basis-URL og API-nøkkel i en hvilken som helst Gemini SDK eller HTTP-klient:

Innstilling	Google-standard	CometAPI
Base URL	`generativelanguage.googleapis.com`	`api.cometapi.com`
API Key	`$GEMINI_API_KEY`	`$COMETAPI_KEY`

Både x-goog-api-key og Authorization: Bearer-headere støttes for autentisering.

Thinking (resonnering)

Gemini-modeller kan utføre intern resonnering før de genererer et svar. Kontrollmetoden avhenger av modellgenerasjonen.

Gemini 3 (thinkingLevel)
Gemini 2.5 (thinkingBudget)

Gemini 3-modeller bruker thinkingLevel for å styre dybden på resonneringen. Tilgjengelige nivåer: MINIMAL, LOW, MEDIUM, HIGH.

curl "https://api.cometapi.com/v1beta/models/gemini-3.1-pro-preview:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "Explain quantum physics simply."}]}],
    "generationConfig": {
      "thinkingConfig": {"thinkingLevel": "LOW"}
    }
  }'

Gemini 2.5-modeller bruker thinkingBudget for finmasket kontroll på token-nivå:

0 — deaktiver thinking
-1 — dynamisk (modellen bestemmer, standard)
> 0 — spesifikt token-budsjett (f.eks. 1024, 2048)

curl "https://api.cometapi.com/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "Solve this logic puzzle step by step."}]}],
    "generationConfig": {
      "thinkingConfig": {"thinkingBudget": 2048}
    }
  }'

Bruk av thinkingLevel med Gemini 2.5-modeller (eller thinkingBudget med Gemini 3-modeller) kan føre til feil. Bruk riktig parameter for modellversjonen din.

Streaming

Bruk streamGenerateContent?alt=sse som operator for å motta Server-Sent Events mens modellen genererer innhold. Hver SSE-hendelse inneholder en data:-linje med et JSON-objekt av typen GenerateContentResponse.

curl "https://api.cometapi.com/v1beta/models/gemini-2.5-flash:streamGenerateContent?alt=sse" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  --no-buffer \
  -d '{
    "contents": [{"parts": [{"text": "Write a short poem about the stars"}]}]
  }'

Systeminstruksjoner

Styr modellens oppførsel gjennom hele samtalen med systemInstruction:

curl "https://api.cometapi.com/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "What is 2+2?"}]}],
    "systemInstruction": {
      "parts": [{"text": "You are a math tutor. Always show your work."}]
    }
  }'

JSON Mode

Tving strukturert JSON-utdata med responseMimeType. Du kan eventuelt oppgi et responseSchema for streng skjemavalidering:

curl "https://api.cometapi.com/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "List 3 planets with their distances from the sun"}]}],
    "generationConfig": {
      "responseMimeType": "application/json"
    }
  }'

Google Search Grounding

Aktiver nettsøk i sanntid ved å legge til et googleSearch-verktøy:

curl "https://api.cometapi.com/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -d '{
    "contents": [{"parts": [{"text": "Who won the euro 2024?"}]}],
    "tools": [{"google_search": {}}]
  }'

Svaret inkluderer groundingMetadata med kilde-URL-er og konfidenspoeng.

Response Example

Et typisk svar fra CometAPIs Gemini-endepunkt:

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [{"text": "Hello"}]
      },
      "finishReason": "STOP",
      "avgLogprobs": -0.0023
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 5,
    "candidatesTokenCount": 1,
    "totalTokenCount": 30,
    "trafficType": "ON_DEMAND",
    "thoughtsTokenCount": 24,
    "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 5}],
    "candidatesTokensDetails": [{"modality": "TEXT", "tokenCount": 1}]
  },
  "modelVersion": "gemini-2.5-flash",
  "createTime": "2026-03-25T04:21:43.756483Z",
  "responseId": "CeynaY3LDtvG4_UP0qaCuQY"
}

Feltet thoughtsTokenCount i usageMetadata viser hvor mange tokens modellen brukte på intern resonnering, selv når tenkeutdata ikke er inkludert i svaret.

Viktige forskjeller fra OpenAI-kompatibelt endepunkt

Funksjon	Gemini Native (`/v1beta/models/...`)	OpenAI-Compatible (`/v1/chat/completions`)
Tenkekontroll	`thinkingConfig` med `thinkingLevel` / `thinkingBudget`	Ikke tilgjengelig
Google Search-grounding	`tools: [\{"google_search": \{\}\}]`	Ikke tilgjengelig
Google Maps-grounding	`tools: [\{"googleMaps": \{\}\}]`	Ikke tilgjengelig
Modality for bildegenerering	`responseModalities: ["IMAGE"]`	Ikke tilgjengelig
Auth-header	`x-goog-api-key` eller `Bearer`	Kun `Bearer`
Svarformat	Gemini native (`candidates`, `parts`)	OpenAI-format (`choices`, `message`)

Autorisasjoner

x-goog-api-key

string

header

påkrevd

Your CometAPI key passed via the x-goog-api-key header. Bearer token authentication (Authorization: Bearer <key>) is also supported.

Stien-parametere

model

string

påkrevd

The Gemini model ID to use. See the Models page for current Gemini model IDs.

Eksempel:

"gemini-2.5-flash"

operator

enum<string>

påkrevd

The operation to perform. Use generateContent for synchronous responses, or streamGenerateContent?alt=sse for Server-Sent Events streaming.

Tilgjengelige alternativer:

generateContent,

streamGenerateContent?alt=sse

Eksempel:

"generateContent"

Kropp

application/json

contents

object[]

påkrevd

The conversation history and current input. For single-turn queries, provide a single item. For multi-turn conversations, include all previous turns.

Show child attributes

systemInstruction

object

System instructions that guide the model's behavior across the entire conversation. Text only.

Show child attributes

tools

object[]

Tools the model may use to generate responses. Supports function declarations, Google Search, Google Maps, and code execution.

Show child attributes

toolConfig

object

Configuration for tool usage, such as function calling mode.

Show child attributes

safetySettings

object[]

Safety filter settings. Override default thresholds for specific harm categories.

Show child attributes

generationConfig

object

Configuration for model generation behavior including temperature, output length, and response format.

Show child attributes

cachedContent

string

The name of cached content to use as context. Format: cachedContents/{id}. See the Gemini context caching documentation for details.

Svar

200 - application/json

Successful response. For streaming requests, the response is a stream of SSE events, each containing a GenerateContentResponse JSON object prefixed with data:.

candidates

object[]

The generated response candidates.

Show child attributes

promptFeedback

object

Feedback on the prompt, including safety blocking information.

Show child attributes

usageMetadata

object

Token usage statistics for the request.

Show child attributes

modelVersion

string

The model version that generated this response.

createTime

string

The timestamp when this response was created (ISO 8601 format).

responseId

string

Unique identifier for this response.

from google import genai

client = genai.Client(
    api_key="<COMETAPI_KEY>",
    http_options={"api_version": "v1beta", "base_url": "https://api.cometapi.com"},
)

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Explain how AI works in a few words",
)

print(response.text)

{
  "candidates": [
    {
      "content": {
        "role": "<string>",
        "parts": [
          {
            "text": "<string>",
            "functionCall": {
              "name": "<string>",
              "args": {}
            },
            "inlineData": {
              "mimeType": "<string>",
              "data": "<string>"
            },
            "thought": true
          }
        ]
      },
      "finishReason": "STOP",
      "safetyRatings": [
        {
          "category": "<string>",
          "probability": "<string>",
          "blocked": true
        }
      ],
      "citationMetadata": {
        "citationSources": [
          {
            "startIndex": 123,
            "endIndex": 123,
            "uri": "<string>",
            "license": "<string>"
          }
        ]
      },
      "tokenCount": 123,
      "avgLogprobs": 123,
      "groundingMetadata": {
        "groundingChunks": [
          {
            "web": {
              "uri": "<string>",
              "title": "<string>"
            }
          }
        ],
        "groundingSupports": [
          {
            "groundingChunkIndices": [
              123
            ],
            "confidenceScores": [
              123
            ],
            "segment": {
              "startIndex": 123,
              "endIndex": 123,
              "text": "<string>"
            }
          }
        ],
        "webSearchQueries": [
          "<string>"
        ]
      },
      "index": 123
    }
  ],
  "promptFeedback": {
    "blockReason": "SAFETY",
    "safetyRatings": [
      {
        "category": "<string>",
        "probability": "<string>",
        "blocked": true
      }
    ]
  },
  "usageMetadata": {
    "promptTokenCount": 123,
    "candidatesTokenCount": 123,
    "totalTokenCount": 123,
    "trafficType": "<string>",
    "thoughtsTokenCount": 123,
    "promptTokensDetails": [
      {
        "modality": "<string>",
        "tokenCount": 123
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "<string>",
        "tokenCount": 123
      }
    ]
  },
  "modelVersion": "<string>",
  "createTime": "<string>",
  "responseId": "<string>"
}

Oversikt

API-referanse

Integrasjonsveiledninger

Feil

Priser og fakturering

Support

Oversikt

Hurtigstart

Thinking (resonnering)

Streaming

Systeminstruksjoner

JSON Mode

Google Search Grounding

Response Example

Viktige forskjeller fra OpenAI-kompatibelt endepunkt

Autorisasjoner

Stien-parametere

Kropp

Svar

Oversikt

API-referanse

Integrasjonsveiledninger

Feil

Priser og fakturering

Support

​Oversikt

​Hurtigstart

​Thinking (resonnering)

​Streaming

​Systeminstruksjoner

​JSON Mode

​Google Search Grounding

​Response Example

​Viktige forskjeller fra OpenAI-kompatibelt endepunkt

Autorisasjoner

Stien-parametere

Kropp

Svar

Oversikt

Hurtigstart

Thinking (resonnering)

Streaming

Systeminstruksjoner

JSON Mode

Google Search Grounding

Response Example

Viktige forskjeller fra OpenAI-kompatibelt endepunkt