flagship
Gemini 3 Pro Preview vs Gemini 3 Flash Preview
Side-by-side pricing, context window, features, and per-use-case verdict. Data sourced from LiteLLM, updated regularly.
Specifications
| Feature | Gemini 3 Pro Preview | Gemini 3 Flash Preview |
|---|---|---|
| Provider | vertex ai-language-models | vertex ai-language-models |
| Model ID | gemini-3-pro-preview | gemini-3-flash-preview |
| Input / 1M tokens | $2.00 | $0.50 (75% cheaper) |
| Output / 1M tokens | $12.00 | $3.00 (75% cheaper) |
| Cached input / 1M | $0.20 | $0.05 |
| Context window | 1049kk tokens | 1049kk tokens |
| Max output | 66kk tokens | 66kk tokens |
| Vision | ✅ | ✅ |
| Function calling | ✅ | ✅ |
| Prompt caching | ✅ | ✅ |
| Web search | ✅ | ✅ |
| JSON schema | ✅ | ✅ |
Monthly cost comparison
No cache discount applied — pure token costs at three usage scales.
| Scale | Gemini 3 Pro Preview | Gemini 3 Flash Preview | Winner |
|---|---|---|---|
| Small 1M in / 0.2M out | $4.40 | $1.10 | Gemini 3 Flash Preview saves 75% |
| Medium 10M in / 2M out | $44.00 | $11.00 | Gemini 3 Flash Preview saves 75% |
| Large 100M in / 20M out | $440 | $110 | Gemini 3 Flash Preview saves 75% |
Category winners
Cheapest input
Gemini 3 Flash Preview
$0.50/M
· 75% less than the other
Cheapest output
Gemini 3 Flash Preview
$3.00/M
· 75% less than the other
Larger context
Gemini 3 Pro Preview
1049kk tokens
More features
Gemini 3 Pro Preview
5 / 5 capabilities
(tied)
Better for…
High-volume RAG & repeated context
$0.05/M cached input — prompt caching makes repeated context retrieval significantly cheaper
Gemini 3 Flash Preview
Short interactions & high-throughput APIs
$3.00/M output — 75% cheaper on output at scale
Gemini 3 Flash Preview
Cost-sensitive production at scale
$110/month at 100M-token scale — 75% cheaper than the alternative
Gemini 3 Flash Preview
Deep-dive on each model
Pricing data sourced from LiteLLM and refreshed regularly. Always verify with each provider's official pricing page before making business decisions.