Gemini 2.5 Pro vs Gemini 3.1 Pro: which API costs less?
Averaged across three realistic workloads, Gemini 2.5 Pro is about 24% cheaper than Gemini 3.1 Pro. Below: raw rates and side-by-side monthly costs, computed from prices verified 2026-10-17 (we track what you are billed today, promos included).
Rates per 1M tokens
| Model | Input | Output | Cached input |
|---|---|---|---|
| Gemini 2.5 ProGoogle | $1.25 | $10 | $0.125 |
| Gemini 3.1 ProGoogle | $2 | $12 | $0.200 |
Gemini 2.5 Pro: Prompts up to 200K tokens; longer prompts cost $2.50/$15. Gemini 3.1 Pro: Preview; prompts up to 200K tokens; longer prompts cost $4/$18.
Monthly cost, side by side
| Workload | Gemini 2.5 Pro | Gemini 3.1 Pro | Difference |
|---|---|---|---|
Customer-support chatbot 2M input + 0.5M output tokens/month, 60% of input served from prompt cache | $6.15 | $7.84 | Gemini 2.5 Pro −22% |
RAG / document Q&A 20M input + 1M output tokens/month, 70% cached (shared context) | $19.25 | $26.80 | Gemini 2.5 Pro −28% |
Agentic coding assistant 50M input + 5M output tokens/month, 80% cached (long sessions) | $67.50 | $88.00 | Gemini 2.5 Pro −23% |
Your traffic looks different? Run your own numbers in the calculator.
FAQ
Which is cheaper: Gemini 2.5 Pro or Gemini 3.1 Pro?
Across three realistic workloads (chatbot, RAG, agent), Gemini 2.5 Pro works out about 24% cheaper than Gemini 3.1 Pro on average. Raw rates: Gemini 2.5 Pro $1.25/$10 per 1M tokens vs Gemini 3.1 Pro $2/$12. Verified 2026-10-17.
Does prompt caching change the comparison?
Yes — cached input costs $0.125 on Gemini 2.5 Pro and $0.200 on Gemini 3.1 Pro. Our scenario numbers already include realistic cache hit rates.
Is cheaper always better?
No. Price is one axis — model capability, context window and latency differ. This page answers only the cost question; benchmark quality on your own tasks before switching.