Gemini 2.5 Pro
Google · released 2025-09-01
Quality (AA Index)87
Input price$1.25
Output price$10.00
Context1M
Throughput140 tok/s
P50 latency0.8s
Side-by-side pricing, capabilities, real-world cost across common scenarios, and our editorial pick.
Google · released 2025-09-01
Google · released 2025-09-01
链接通过我们的 OpenRouter 推荐链接在新标签页打开。 查看推广披露
| Metric | Gemini 2.5 Pro | Gemini 2.5 Flash | Verdict |
|---|---|---|---|
Input price /百万 tokens | $1.25 | $0.30 | Gemini 2.5 Flash −76% |
Output price /百万 tokens | $10.00 | $2.50 | Gemini 2.5 Flash −75% |
Context window max input length | 1M | 1M | Tied |
AA Quality AA Intelligence Index (0–100) | 87 | 78 | Gemini 2.5 Pro +9pt |
Arena Elo LMArena human-pref Elo (800–2000) | — | — | Tied |
Throughput tokens per second | 140 | 320 | Gemini 2.5 Flash +129% |
P50 latency first token | 0.8s | 0.3s | Gemini 2.5 Flash −63% |
Vision multimodal | Tied | ||
Function calling tool use | Tied | ||
Reasoning mode chain-of-thought | Tied |
| Scenario | Gemini 2.5 Pro | Gemini 2.5 Flash |
|---|---|---|
customer support 1000K req · 600/180 tok | $2.5K | $630 |
chat with docs 300K req · 4000/300 tok | $2.4K | $585 |
code generation 500K req · 2000/500 tok | $3.8K | $925 |
voice assistant 600K req · 800/200 tok | $1.8K | $444 |
The price-performance benchmark for vision tasks. Strong multimodal, weak on deep reasoning. Pair as a fast first hop ahead of a smarter fallback.
Set Gemini 2.5 Flash as primary, Gemini 2.5 Pro as fallback. One key, one bill, automatic failover when Gemini 2.5 Flash errors.
$ curl https://api.aipricly.com/v1/chat/completions \
-H "Authorization: Bearer $AIPC_KEY" \
-d '{
"routing": {
"primary": "google/gemini-2-5-flash",
"fallback": ["google/gemini-2-5-pro"]
},
"messages": [{"role": "user", "content": "..."}]
}'