Gemini native format

Endpoint address

POST https://api.yomiapi.com/v1beta/models/{model}:generateContent

For streaming, use the :streamGenerateContent action with the alt=sse query parameter:

POST https://api.yomiapi.com/v1beta/models/{model}:streamGenerateContent?alt=sse

Authentication methods

• Request headers: x-goog-api-key: YOUR_API_KEY, in Google's native style.
• URL parameter: ?key=YOUR_API_KEY.
• Generic method: Authorization: Bearer YOUR_API_KEY.

cURL example

curl https://api.yomiapi.com/v1beta/models/{MODEL_ID}:generateContent \
  -H "x-goog-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [{"text": "Summarize the uses of vector databases in three points"}]
    }]
  }'

Python example

Use Google's official google-genai SDK and point base_url to the platform:

pip install google-genai

from google import genai

client = genai.Client(
    api_key="YOUR_API_KEY",
    http_options={"base_url": "https://api.yomiapi.com"}
)

response = client.models.generate_content(
    model="YOUR_AVAILABLE_MODEL_ID",
    contents="Summarize the uses of vector databases in three points"
)
print(response.text)

Available models

Choosing between native and OpenAI-compatible formats

• Choose native: When migrating a Google SDK project, using contents/parts multimodal structures, or needing Gemini-specific fields such as generationConfig and safety settings.
• Choose OpenAI compatible: When you want one codebase shared with other models through /v1/chat/completions. Text, image input and function calling are supported.