Models
Recommended Models (2025)
Always prefer the latest models for the best performance and cost-efficiency.
| Capability | Model Name | Description |
|---|---|---|
| General & Multimodal | gemini-3-flash-preview |
Best for most text/multimodal tasks. High speed, low cost. |
| Reasoning & Coding | gemini-3-pro-preview |
Best for complex logic, math, and heavy coding tasks. |
| Low Latency | gemini-2.5-flash-lite |
Optimized for high-volume, low-latency tasks. |
| Image Generation | gemini-2.5-flash-image |
"Nano Banana". Fast image generation. |
| High-Quality Images | gemini-3-pro-image-preview |
"Nano Banana Pro". High-fidelity image generation. |
| Video Generation | veo-3.0-generate-001 |
High-quality video generation. |
| Fast Video | veo-3.0-fast-generate-001 |
Faster video generation. |
Deprecated Models
Do not use:
gemini-1.5-*gemini-progemini-ultra
Model Capabilities
- Gemini 3 Series: Native reasoning (
thinking_level), high-precision tool use. - Gemini 2.5 Series: Reasoning via
thinking_budget. - Veo: Video generation from text or image prompts.