Gemini Generate Content

Create text, multimodal, tool, and code-execution responses with Gemini Content and Parts.

The Generate Content API uses Content and Parts for text, multimodal, function-calling, and code-execution requests. It returns generated output through Candidates, Usage Metadata, and safety information. Requests use Bearer API key authentication. Supported input modalities, tools, and advanced generation parameters depend on the selected model.

POST/v1beta/models/{model}:generateContent

Use Gemini Content and Parts structures to generate text, multimodal, function calls, or code execution responses.

Authorization

bearerAuth

AuthorizationBearer <token>

Use Bearer your-api-key in the Authorization Header.

In: header

Path Parameters

model*string

Model ID used to generate content. The path automatically forms models/{model}.

Default"MODEL_ID"

Request Body

Gemini uses Content and Parts to represent text, multimodal input, tools, and generation settings.

application/json

Text chat

Use user and model Content objects to organize single-turn or multi-turn text conversations.

contents[]: Conversation content in chronological order.
parts[].text: Text content in each message.
role: Message author; commonly user or model.

application/json

{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Hello! Please introduce yourself."
        }
      ]
    }
  ]
}

Use Content objects and text Parts to organize single-turn or multi-turn text conversations.

contents*array<>

Text Content objects in chronological order. Each message provides content through parts[].text.

Items1 <= items

tools?array<>

tools that the model can use, such as functions, code execution, search, URL Context, File Search, MCP, and more.

toolConfig?

Configuration of tool call in requests.

safetySettings?array<>

Configure content masking thresholds by security category.

systemInstruction?

System commands set by developers, currently only supporting text content.

generationConfig?

Model generation and output configuration.

cachedContent?string

Name of the cached content used for context, formatted as cachedContents/{cachedContent}.

serviceTier?ServiceTier

The service level used by the request.

Value in

"unspecified"
"standard"
"flex"
"priority"

store?boolean

Control the logging behavior of the current request; After setting, it takes precedence over project-level log configuration.

Response Body

`application/json`

curl -X POST "https://example.com/v1beta/models/MODEL_ID:generateContent" \  -H "Content-Type: application/json" \  -d '{    "contents": [      {        "role": "user",        "parts": [          {            "text": "Hello! Please introduce yourself."          }        ]      }    ]  }'

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "Hello! I am an AI assistant who can help you answer questions and complete tasks."
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP",
      "index": 0,
      "safetyRatings": [
        {
          "category": "HARM_CATEGORY_HARASSMENT",
          "probability": "NEGLIGIBLE",
          "blocked": false
        }
      ],
      "tokenCount": 24
    }
  ],
  "promptFeedback": {
    "safetyRatings": [
      {
        "category": "HARM_CATEGORY_HARASSMENT",
        "probability": "NEGLIGIBLE"
      }
    ]
  },
  "usageMetadata": {
    "promptTokenCount": 8,
    "candidatesTokenCount": 24,
    "totalTokenCount": 32,
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 8
      }
    ],
    "candidatesTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 24
      }
    ]
  },
  "modelVersion": "MODEL_ID",
  "responseId": "response-example"
}

Google Gemini Generate Content documentationReview the upstream protocol and recent field changes.

Authorization

Path Parameters

Request Body

Response Body

200application/json

400application/json

401application/json

403application/json

404application/json

413application/json

429application/json

500application/json

503application/json

504application/json

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`