Home › Compare › Gemini 3.5 Flash vs Gemini 2.5 Pro
Gemini 3.5 Flash vs Gemini 2.5 Pro
A straight cost comparison of Gemini 3.5 Flash (Google Gemini) and Gemini 2.5 Pro (Google Gemini), per 1,000,000 tokens, verified October 2026.
Rate-by-rate comparison
| Metric | Gemini 3.5 Flash | Gemini 2.5 Pro | Winner |
|---|---|---|---|
| Input / 1M | $1.50 | $1.25 | Gemini 2.5 Pro |
| Cached input / 1M | $0.15 | $0.125 | Gemini 2.5 Pro |
| Cache write / 1M | — | — | Tie |
| Output / 1M | $9 | $10 | Gemini 3.5 Flash |
| Context window | 1,000,000 | 1,000,000 | Tie |
| Batch API | Yes | Yes | Tie |
| Long-context tier | None | > 200,000 | — |
For per-token metrics, the lower number wins. For context window and batch support, the higher or broader option wins. A dash means the provider does not publish that rate: a missing cache-write fee means writes are not billed per token, while a missing cached-input rate means cache hits bill at the full input rate.
Blended cost: 1M input + 250K output
| Model | Blended cost | Difference |
|---|---|---|
| Gemini 3.5 Flash | $3.75 | Tie |
| Gemini 2.5 Pro | $3.75 | Tie |
Three workloads, two bills
| Workload | Gemini 3.5 Flash | Gemini 2.5 Pro | Winner |
|---|---|---|---|
| Support chat 1,000 requests · 4K input / 600 output | $11.40 | $11 | Gemini 2.5 Pro |
| RAG with caching 1,000 requests · 50K input (45K cached) / 1K output | $23.31 | $21.93 | Gemini 2.5 Pro |
| Nightly batch job 10,000 requests · 10K input / 2K output | $165 | $163 | Gemini 2.5 Pro |
Which one should you pick?
Gemini 3.5 Flash wins on none of the three workloads above, while Gemini 2.5 Pro wins on support chat, cached RAG, nightly batch job.
Beyond price, the two differ on input rate ($1.50 vs $1.25); output rate ($9 vs $10); cached-input rate ($0.15 vs $0.125); long-context tier (none vs yes, above 200,000).
Batch mode is available on Gemini 3.5 Flash and Gemini 2.5 Pro, which halves the nightly job. Both publish cached-input discounts, so a stable system prompt is worth caching on either.
FAQ
Is Gemini 3.5 Flash cheaper than Gemini 2.5 Pro?
No — they are priced identically at $3.75 on a blended 1M-input-plus-250K-output workload, with the same per-token rates. Choose on context window, throughput or output quality instead.
Which handles longer prompts, Gemini 3.5 Flash or Gemini 2.5 Pro?
Both models share the same 1,000,000-token context window. Watch the long-context threshold on Gemini 2.5 Pro: rates rise once input passes it.
Do both models support prompt caching?
Gemini 3.5 Flash bills cached reads at $0.15 per 1M; Gemini 2.5 Pro at $0.125.