google/gemini-3-pro-preview
Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts
This model's cache
This model page returns the exact headers below. The page and /api/models/google--gemini-3-pro-preview share the model:google--gemini-3-pro-preview tag, so invalidation stays scoped to this model.
/models/google--gemini-3-pro-previewpublic, max-age=300, stale-while-revalidate=3600catalogmodel:google--gemini-3-pro-previewWorkers Cache derives the key from this path/query, plus the Worker entrypoint and current Worker version.
export const Route = createFileRoute('/models/$modelSlug')({
headers: () => ({
'Cache-Control': 'public, max-age=300, stale-while-revalidate=3600',
'Cache-Tag': 'catalog,model:google--gemini-3-pro-preview',
}),
})Invalidate this cache tag
await ctx.cache.purge({ tags: ['model:google--gemini-3-pro-preview'] })Use this when one model changes and you do not want to evict the whole catalog.
- Released
- Nov 18, 2025
- Last updated
- Nov 18, 2025
- Context window
- 1.0M tokens
- Max output
- 65.5K tokens
- Open weights
- No
- Family
- Gemini Pro
Starts at
$2
per 1M input tokens
Output
$12
Sellers
6
No cart or checkout in this MVP — pick a provider below and open their docs when you're ready to use it.
Sorted by lowest input price
| Provider | Input / 1M | Output / 1M | Context | |
|---|---|---|---|---|
Requesty google/gemini-3-pro-preview | $2 | $12 | 1.0M | Docs |
Vercel AI Gateway google/gemini-3-pro-preview | $2 | $12 | 1M | Docs |
gemini-3-pro-preview | $2 | $12 | 1.0M | Docs |
Merge Gateway google/gemini-3-pro-preview | $2 | $12 | 1.0M | Docs |
OrcaRouter google/gemini-3-pro-preview | $4 | $18 | 1.0M | Docs |
AnyAPI google/gemini-3-pro-preview | Quote | Quote | 1.0M | Docs |
google/gemini-3.5-flash
Gemini 3.5 Flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
google/gemini-3.1-flash-lite
Gemini 3.1 Flash Lite
Low-latency Gemini model for high-volume multimodal and agent workloads
google/gemma-4-26b-a4b-it
Gemma 4 26B A4B IT
Open Gemma instruction model for efficient chat and self-hosted deployments