Claude 4.6 Sonnet
Anthropic · released 2026-04-08
Quality (AA Index)89
Input price$3.00
Output price$15.00
Context200K
Throughput85 tok/s
P50 latency1.1s
Side-by-side pricing, capabilities, real-world cost across common scenarios, and our editorial pick.
Anthropic · released 2026-04-08
DeepSeek · released 2025-12-01
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 | Claude 4.6 Sonnet | DeepSeek V3.5 | Verdict |
|---|---|---|---|
Input price /百万 tokens | $3.00 | $0.14 | DeepSeek V3.5 −95% |
Output price /百万 tokens | $15.00 | $0.28 | DeepSeek V3.5 −98% |
Context window max input length | 200K | 128K | Claude 4.6 Sonnet +1.6× |
AA Quality AA Intelligence Index (0–100) | 89 | 81 | Claude 4.6 Sonnet +8pt |
Arena Elo LMArena human-pref Elo (800–2000) | — | — | Tied |
Throughput tokens per second | 85 | 95 | DeepSeek V3.5 +12% |
P50 latency first token | 1.1s | 1.5s | Claude 4.6 Sonnet −27% |
Vision multimodal | — | ||
Function calling tool use | Tied | ||
Reasoning mode chain-of-thought | — |
| Scenario | Claude 4.6 Sonnet | DeepSeek V3.5 |
|---|---|---|
customer support 1000K req · 600/180 tok | $4.5K | $134 |
chat with docs 300K req · 4000/300 tok | $5.0K | $193 |
code generation 500K req · 2000/500 tok | $6.8K | $210 |
voice assistant 600K req · 800/200 tok | $3.2K | $101 |
Roughly GPT-4o-class quality at roughly 90% off. Tradeoff is region availability (Chinese provider) and slower output throughput than Western frontier tiers.
Set DeepSeek V3.5 as primary, Claude 4.6 Sonnet as fallback. One key, one bill, automatic failover when DeepSeek V3.5 errors.
$ curl https://api.aipricly.com/v1/chat/completions \
-H "Authorization: Bearer $AIPC_KEY" \
-d '{
"routing": {
"primary": "deepseek/deepseek-v3-5",
"fallback": ["anthropic/claude-4-6-sonnet"]
},
"messages": [{"role": "user", "content": "..."}]
}'