1. Native Gemini Format
ALLLLMS
  • AI Model APIs
    • Documentation
    • Models
      • List Models
        • Native OpenAI Format
        • Native Gemini Format
    • Chat
      • Native OpenAI Format
        • Chat Completions Format
        • Responses Format
      • Native Gemini Format
        • Gemini Text Chat
          POST
        • Gemini Media Recognition
          POST
      • Native Claude Format
        POST
    • Images
      • Native OpenAI Format
        • Generate Image
        • Edit Image
      • Qwen Format
        • Generate Image
        • Edit Image
      • Nano Banana
        • Native Gemini Format
        • OpenAI Chat Format
    • Videos
      • Sora Format
        • Create Video
        • Get Video Task Status
        • Get Video Content
      • Kling Format
        • Kling Text-to-Video
        • Get Kling Text-to-Video Task Status
        • Kling Image-to-Video
        • Get Kling Image-to-Video Task Status
      • Jimeng Format
        • Jimeng Video Generation
      • Create Video Generation Task
      • Get Video Generation Task Status
    • Embeddings
      • Native OpenAI Format
      • Native Gemini Format
    • Completions
      • Native OpenAI Format
    • Audio
      • Native OpenAI Format
        • Audio Transcription
        • Audio Translation
        • Text to Speech
      • Native Gemini Format
    • Realtime
      • Native OpenAI Format
    • Rerank
      • Document Reranking
    • Moderations
      • Native OpenAI Format
    • Unimplemented
      • Fine-tuning
        • List Fine-tuning Jobs (Unimplemented)
        • Create Fine-tuning Job (Unimplemented)
        • Get Fine-tuning Job Details (Unimplemented)
        • Cancel Fine-tuning Job (Unimplemented)
        • Get Fine-tuning Job Events (Unimplemented)
      • Files
        • List Files (Unimplemented)
        • Upload File (Unimplemented)
        • Get File Information (Unimplemented)
        • Delete File (Unimplemented)
        • Get File Content (Unimplemented)
    • Schemas
      • Schemas
        • User
        • Log
        • Model
        • Token
        • Usage
        • PageInfo
        • Channel
        • Redemption
        • ApiResponse
        • ModelsResponse
        • ErrorResponse
        • Message
        • MessageContent
        • Tool
        • ToolCall
        • GeminiModelsResponse
        • ChatCompletionResponse
        • ChatCompletionRequest
        • ChatCompletionStreamResponse
        • CompletionRequest
        • CompletionResponse
        • ResponseFormat
        • ResponsesRequest
        • ResponsesResponse
        • ResponsesStreamResponse
        • ClaudeRequest
        • ClaudeMessage
        • ClaudeResponse
        • EmbeddingRequest
        • EmbeddingResponse
        • ImageGenerationRequest
        • ImageEditRequest
        • ImageResponse
        • AudioTranscriptionRequest
        • AudioTranslationRequest
        • AudioTranscriptionResponse
        • SpeechRequest
        • RerankRequest
        • RerankResponse
        • VideoRequest
        • ModerationRequest
        • VideoResponse
        • ModerationResponse
        • VideoTaskResponse
        • GeminiRequest
        • VideoTaskMetadata
        • VideoTaskError
        • GeminiResponse
        • OpenAIVideo
        • OpenAIVideoError
  1. Native Gemini Format

Gemini Media Recognition

POST
/v1beta/models/{model}:generateContent
Gemini image, PDF, audio, and video recognition request.
Note: Only Base64 uploads through inlineData are supported for images, PDFs, audio, and video. fileData.fileUri and the File API are not supported.

Request

Authorization
Bearer Token
Provide your bearer token in the
Authorization
header when making requests to protected resources.
Example:
Authorization: Bearer ********************
or
Path Params

Body Params application/json

Examples
{
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "Tell me about this instrument"
                },
                {
                    "inlineData": {
                        "mimeType": "image/jpeg",
                        "data": "Imagebase64"
                    }
                }
            ]
        }
    ]
}

Request Code Samples

Shell
JavaScript
Java
Swift
Go
PHP
Python
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
Request Request Example
Shell
JavaScript
Java
Swift
cURL
curl --location '/v1beta/models/:generateContent' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
    "contents": [
        {
            "role": "user",
            "parts": [
                {
                    "text": "Tell me about this instrument"
                },
                {
                    "inlineData": {
                        "mimeType": "image/jpeg",
                        "data": "Imagebase64"
                    }
                }
            ]
        }
    ]
}'

Responses

🟢200Success
application/json
Success
Bodyapplication/json

Example
{
    "candidates": [
        {
            "content": {
                "role": "string",
                "parts": [
                    {}
                ]
            },
            "finishReason": "string",
            "safetyRatings": [
                {}
            ]
        }
    ],
    "usageMetadata": {
        "promptTokenCount": 0,
        "candidatesTokenCount": 0,
        "totalTokenCount": 0
    }
}
Modified at 2026-05-23 05:25:16
Previous
Gemini Text Chat
Next
Native Claude Format
Built with