The best model in the world for multimodal understanding, and our most powerful agentic and vibe-coding model yet, delivering richer visuals and deeper interactivity, all built on a foundation of state-of-the-art reasoning.
function_callinghttps://generativelanguage.googleapis.com/v1beta/v1beta/models/{model}:generateContenthttps://generativelanguage.googleapis.com/v1beta/v1beta/models/{model}:streamGenerateContent| Input | Cached input | Output | |
|---|---|---|---|
| Standard | $0.5 | $0.05 | $3 |
| Batch | $0.25 | — | $1.5 |
| Model | Context | Max out | Pricing |
|---|---|---|---|
| gemini-3-pro-preview | 1.0M | 66K | — |
| gemini-3-flash-preview | 1.0M | 66K | $0.5$3 |
| gemini-3-pro-image-preview | 66K | 33K | $2$12 |
| gemini-3-pro-image | 66K | 33K | $2$12 |
/v1/models/google/gemini-3-flash-previewThe best model in the world for multimodal understanding, and our most powerful agentic and vibe-coding model yet, delivering richer visuals and deeper interactivity, all built on a foundation of state-of-the-art reasoning.