DeepSeek V3.5
DeepSeek · released 2025-12-01
Quality (AA Index)81
Input price$0.14
Output price$0.28
Context128K
Throughput95 tok/s
P50 latency1.5s
Side-by-side pricing, capabilities, real-world cost across common scenarios, and our editorial pick.
DeepSeek · released 2025-12-01
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 | DeepSeek V3.5 | Gemini 2.5 Pro | Verdict |
|---|---|---|---|
Input price /百万 tokens | $0.14 | $1.25 | DeepSeek V3.5 −89% |
Output price /百万 tokens | $0.28 | $10.00 | DeepSeek V3.5 −97% |
Context window max input length | 128K | 1M | Gemini 2.5 Pro +7.8× |
AA Quality AA Intelligence Index (0–100) | 81 | 87 | Gemini 2.5 Pro +6pt |
Arena Elo LMArena human-pref Elo (800–2000) | — | — | Tied |
Throughput tokens per second | 95 | 140 | Gemini 2.5 Pro +47% |
P50 latency first token | 1.5s | 0.8s | Gemini 2.5 Pro −47% |
Vision multimodal | — | ||
Function calling tool use | Tied | ||
Reasoning mode chain-of-thought | — |
| Scenario | DeepSeek V3.5 | Gemini 2.5 Pro |
|---|---|---|
customer support 1000K req · 600/180 tok | $134 | $2.5K |
chat with docs 300K req · 4000/300 tok | $193 | $2.4K |
code generation 500K req · 2000/500 tok | $210 | $3.8K |
voice assistant 600K req · 800/200 tok | $101 | $1.8K |
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, DeepSeek V3.5 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": ["deepseek/deepseek-v3-5"]
},
"messages": [{"role": "user", "content": "..."}]
}'