Google Gemini
Google's Gemini series. Natively multimodal, with text, image, audio and video input and long context. There are also image generation, text-to-speech, speech-to-text and embedding models.
Choosing a group
| Group | Price |
|---|---|
gemini | Pay 20% of official price |
gemini_image | Pay 30% of official price |
gemini_vertex | Pay 41.53% of official price |
gemini: the most complete set of models, including image, speech and preview models.gemini_vertex: sourced from Vertex AI.gemini_image: image models only.
Recommended API
Prefer the native Gemini API, which gives full access to thinkingConfig, multimodal input, and image and speech output. Text models can also be called through Chat Completions.
bash
curl "https://api.codingrouter.ai/v1beta/models/gemini-3.5-flash:generateContent" \
-H "x-goog-api-key: $CODINGROUTER_KEY" \
-H "Content-Type: application/json" \
-d '{
"contents": [{"role": "user", "parts": [{"text": "Summarize the key points of this article: ..."}]}],
"generationConfig": {"thinkingConfig": {"thinkingBudget": 1024}}
}'Choosing a model
| Type | Example models | Description |
|---|---|---|
| Pro | gemini-3.1-pro-preview | Complex reasoning and coding |
| Flash | gemini-3.5-flash, gemini-3.7-flash, gemini-3.8-flash | Balance of speed, cost and capability |
| Flash Lite | gemini-3.5-flash-lite, gemini-3.1-flash-lite | Cheapest, for large batch tasks |
| Image | gemini-3-pro-image, gemini-3.1-flash-image | Generate and edit images, see Image generation |
| Speech | *-tts, gemini-3.5-transcribe | Text-to-speech, speech-to-text |
| Embedding | gemini-embedding-001 | Can also use the Embeddings API |
Usage tips
- Image models need
IMAGEingenerationConfig.responseModalities. - The request format of speech models matches Google's official speech generation documentation. Call them through the native API.
- Models with
previewin the name are previews; their behavior and price may change.
Representative models
| Model | Group | Good for |
|---|---|---|
gemini-3.1-pro-preview | gemini, gemini_vertex | Complex reasoning and coding |
gemini-3.7-flash | gemini, gemini_vertex | Coding and agents |
gemini-3.5-flash | gemini, gemini_vertex | Balance of speed and cost |
gemini-3.5-flash-lite | gemini | Large batches at low cost |
gemini-3-pro-image | gemini_image, gemini | Image generation and editing |
gemini-3.8-flash-tts | gemini | Text-to-speech |
gemini-3.5-transcribe | gemini | Speech-to-text |
gemini-embedding-001 | gemini | Embeddings |
For the full list and prices see the model square.
