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
Anthropic · released 2026-04-08
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 | Claude 4.6 Sonnet | Verdict |
|---|---|---|---|
Input price /百万 tokens | $1.25 | $3.00 | Gemini 2.5 Pro −58% |
Output price /百万 tokens | $10.00 | $15.00 | Gemini 2.5 Pro −33% |
Context window max input length | 1M | 200K | Gemini 2.5 Pro +5.0× |
AA Quality AA Intelligence Index (0–100) | 87 | 89 | Claude 4.6 Sonnet +2pt |
Arena Elo LMArena human-pref Elo (800–2000) | — | — | Tied |
Throughput tokens per second | 140 | 85 | Gemini 2.5 Pro +65% |
P50 latency first token | 0.8s | 1.1s | Gemini 2.5 Pro −27% |
Vision multimodal | Tied | ||
Function calling tool use | Tied | ||
Reasoning mode chain-of-thought | Tied |
| Scenario | Gemini 2.5 Pro | Claude 4.6 Sonnet |
|---|---|---|
customer support 1000K req · 600/180 tok | $2.5K | $4.5K |
chat with docs 300K req · 4000/300 tok | $2.4K | $5.0K |
code generation 500K req · 2000/500 tok | $3.8K | $6.8K |
voice assistant 600K req · 800/200 tok | $1.8K | $3.2K |
Largest context window in the top tier (1M tokens). Tradeoff: pricier than DeepSeek and slower TTFT than GPT-5 — pick when whole-codebase or whole-PDF tasks matter.
Set Gemini 2.5 Pro as primary, Claude 4.6 Sonnet as fallback. One key, one bill, automatic failover when Gemini 2.5 Pro errors.
$ curl https://api.aipricly.com/v1/chat/completions \
-H "Authorization: Bearer $AIPC_KEY" \
-d '{
"routing": {
"primary": "google/gemini-2-5-pro",
"fallback": ["anthropic/claude-4-6-sonnet"]
},
"messages": [{"role": "user", "content": "..."}]
}'