Claude Sonnet 5 vs Gemini 2.5 Flash
Both are Mid-tier models, from Anthropic and Google respectively. Gemini 2.5 Flash is the cheaper choice overall at a 4:1 input:output ratio.
Which is cheaper
- Input price: Gemini 2.5 Flash is cheaper ($0.30 vs $2.00).
- Output price: Gemini 2.5 Flash is cheaper ($2.50 vs $10.00).
- Blended, 4:1 input:output ratio: Gemini 2.5 Flash is 79.4% cheaper ($0.74 vs $3.60 per weighted 1M tokens).
Side by side
| Spec | Claude Sonnet 5 | Gemini 2.5 Flash |
|---|---|---|
| Provider | Anthropic | |
| Tier | Mid | Mid |
| Context window | 1M | 1M |
| Max output | 128K | — |
| Input $/1M | $2.00 | $0.30 |
| Output $/1M | $10.00 | $2.50 |
| Cache read $/1M | $0.20 | $0.03 |
| Cache write $/1M | $2.50 | — |
| Modalities | text, image | text, image |
Claude Sonnet 5. 5-minute cache write shown; 1-hour cache write is $4/MTok. The page now states explicitly the previously-scheduled Sep 1 2026 increase to $3/$15 will NOT occur - $2/$10 is permanent.
Gemini 2.5 Flash. Standard tier, text/image/video rate; audio input $1.00/1M. Cache storage $1.00/1M tokens/hour. Page explicitly states this model supports a 1M token context window.
Sources
Claude Sonnet 5 — verified August 29, 2026
Gemini 2.5 Flash — verified August 29, 2026
Full Claude Sonnet 5 pricing page → · Full Gemini 2.5 Flash pricing page →