Gemini Native Format

Call Gemini models using Google Native API format

POST /v1beta/models/{model}:{method}

Gemini Native Format

cURL

curl --request POST \
  --url https://api.poyo.ai:{method}/v1beta/models/{model}:62437 \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data @- <<EOF
{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Summarize the 'new night mode' requirements in 3 points and provide next steps."
        }
      ]
    }
  ]
}
EOF

200

{
  "code": 200,
  "data": {
    "candidates": [
      {
        "content": {
          "role": "model",
          "parts": [
            {
              "text": "Hello! I'm pleased to introduce myself."
            }
          ]
        },
        "finishReason": "STOP",
        "index": 0
      }
    ],
    "promptFeedback": {
      "safetyRatings": [
        {
          "category": "HARM_CATEGORY_HATE_SPEECH",
          "probability": "NEGLIGIBLE"
        },
        {
          "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
          "probability": "NEGLIGIBLE"
        },
        {
          "category": "HARM_CATEGORY_HARASSMENT",
          "probability": "NEGLIGIBLE"
        },
        {
          "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
          "probability": "NEGLIGIBLE"
        }
      ]
    }
  },
  "usageMetadata": {
    "promptTokenCount": 15,
    "candidatesTokenCount": 29,
    "totalTokenCount": 44,
    "thoughtsTokenCount": 0,
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 15
      }
    ]
  }
}

• Call Gemini models using Google Native API format
• Synchronous processing mode with real-time response
• Minimal parameters for quick start

Authorizations

Authorization · string · required

All API endpoints require Bearer Token authentication

Get your API Key:

Visit the API Key Management Page to get your API Key

Add it to the request header:

Authorization: Bearer PoYo_API_KEY

Path Parameters

model · string · required

Gemini model name. Example: gemini-3-flash-preview

method · enum<string> · required

Request method

• generateContent
• streamGenerateContent

Body

contents · array · required

Conversation contents with roles and parts

Show Content object structure

role · enum<string>

Role type

• user - User input
• model - Model output

parts · array · required

Parts list (text or inline data)

Example:

[
  {
    "role": "user",
    "parts": [{"text": "Summarize the goals of the new 'night mode' in one sentence."}]
  }
]

generationConfig · object

Generation configuration

Show Properties

temperature · number

Controls output randomness

topP · number

Nucleus sampling parameter

topK · integer

Top-k sampling parameter

maxOutputTokens · integer

Maximum output tokens

stopSequences · array

Stop sequences

safetySettings · array

Safety settings

Show Safety setting object

category · string

Safety category

threshold · string

Blocking threshold

Response

candidates · array

Generated candidates

Show Properties

content · object

Output content

finishReason · string

Reason for completion

index · integer

Candidate index

promptFeedback · object

Prompt safety feedback

usageMetadata · object

Token usage metadata

Show Properties

promptTokenCount · integer

Tokens in prompt

candidatesTokenCount · integer

Tokens in candidates

totalTokenCount · integer

Total tokens

thoughtsTokenCount · integer

Thoughts tokens

Authorizations

Authorization · string · header · required

All API endpoints require Bearer Token authentication.

Get your API Key:

Visit the API Key Management Page to get your API Key

Add it to the request header:

Authorization: Bearer YOUR_API_KEY

Path Parameters

model · string · required

Gemini model name.

Example:

"gemini-3-flash-preview"

method · enum<string> · required

Request method: generateContent or streamGenerateContent.

Available options: generateContent, streamGenerateContent

Example:

"generateContent"

Body

application/json

contents · object[] · required

Conversation contents with roles and parts.

Show child attributes

generationConfig · object

Show child attributes

safetySettings · object[]

Show child attributes

Response

200 - application/json

Content generated

code · integer

Example:

200

data · object

Show child attributes

usageMetadata · object

Show child attributes