Google Gemini

Configure Google Gemini via AI Studio in GoModel, choose native or OpenAI-compatible routing, and understand image_url behavior.

This page covers Gemini through Google AI Studio API keys. For Gemini on Google Cloud’s Vertex AI, see the Google Vertex AI guide.

GoModel routes Gemini chat and Responses API requests through Gemini’s native generateContent API by default. You can switch those requests back to Gemini’s OpenAI-compatible API when you need compatibility behavior that the native adapter does not implement yet.

Configure AI Studio

Use the GEMINI_* prefix for Gemini API keys from AI Studio:

export GEMINI_API_KEY="..."
export GEMINI_API_MODE="native"

Or in config.yaml:

providers:
  gemini:
    type: gemini
    api_key: "${GEMINI_API_KEY}"
    api_mode: native

Native versus OpenAI-compatible mode

Gemini native mode is enabled by default:

export GEMINI_API_MODE="native"

Set the per-provider API mode to openai_compatible to route chat and Responses API requests through the upstream OpenAI-compatible /chat/completions endpoint:

export GEMINI_API_MODE="openai_compatible"

GEMINI_BASE_URL configures the Gemini base. GoModel keeps separate internal bases for native Gemini and the OpenAI-compatible API:

• native chat/models default: https://generativelanguage.googleapis.com/v1beta
• OpenAI-compatible default: https://generativelanguage.googleapis.com/v1beta/openai

When GEMINI_BASE_URL ends in /openai, GoModel uses that value for the OpenAI-compatible client and derives the native base by stripping /openai. Gemini embeddings, files, and batches still use the OpenAI-compatible surface.

export GEMINI_BASE_URL="https://generativelanguage.googleapis.com/v1beta/openai"

USE_GOOGLE_GEMINI_NATIVE_API is still supported as a legacy global toggle when per-provider GEMINI_API_MODE is unset. Prefer GEMINI_API_MODE for new deployments.

Image URL behavior

Gemini models support image input, but the two GoModel routing modes handle OpenAI-style image_url values differently.

In native mode, GoModel converts OpenAI-compatible messages to Gemini generateContent requests. That adapter currently supports inline image data only:

{
  "type": "image_url",
  "image_url": {
    "url": "data:image/jpeg;base64,..."
  }
}

Remote image URLs such as https://example.com/image.png are rejected in native mode. Google’s native Gemini API supports inline image data and Files API references; for URL-hosted images, Google’s examples fetch the URL first and send the bytes to generateContent.

Set GEMINI_API_MODE=openai_compatible when you need GoModel to pass the OpenAI-compatible image_url request shape through to Google’s OpenAI-compatible endpoint instead. Google documents image input for that endpoint using the OpenAI image_url field.

Current support

Integrated:

• chat completions and streaming
• Responses API and streaming
• model listing through AI Studio /models
• usage metadata normalization for native responses
• tool calls and function-call results
• inline image data via data: URLs in native mode

Not integrated yet:

• fetching remote image_url values
• uploading remote images through the Gemini Files API before a chat request

References:

• Gemini image understanding
• Gemini OpenAI compatibility