Qwen 3 Max
Alibaba · released 2026-03-01
Quality (AA Index)84
Input price$0.80
Output price$3.20
Context256K
Throughput130 tok/s
P50 latency0.9s
Side-by-side pricing, capabilities, real-world cost across common scenarios, and our editorial pick.
Alibaba · released 2026-03-01
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 | Qwen 3 Max | Claude 4.6 Sonnet | Verdict |
|---|---|---|---|
Input price /百万 tokens | $0.80 | $3.00 | Qwen 3 Max −73% |
Output price /百万 tokens | $3.20 | $15.00 | Qwen 3 Max −79% |
Context window max input length | 256K | 200K | Qwen 3 Max +1.3× |
AA Quality AA Intelligence Index (0–100) | 84 | 89 | Claude 4.6 Sonnet +5pt |
Arena Elo LMArena human-pref Elo (800–2000) | — | — | Tied |
Throughput tokens per second | 130 | 85 | Qwen 3 Max +53% |
P50 latency first token | 0.9s | 1.1s | Qwen 3 Max −18% |
Vision multimodal | Tied | ||
Function calling tool use | Tied | ||
Reasoning mode chain-of-thought | — |
| Scenario | Qwen 3 Max | Claude 4.6 Sonnet |
|---|---|---|
customer support 1000K req · 600/180 tok | $1.1K | $4.5K |
chat with docs 300K req · 4000/300 tok | $1.2K | $5.0K |
code generation 500K req · 2000/500 tok | $1.6K | $6.8K |
voice assistant 600K req · 800/200 tok | $768 | $3.2K |
Set Qwen 3 Max as primary, Claude 4.6 Sonnet as fallback. One key, one bill, automatic failover when Qwen 3 Max errors.
$ curl https://api.aipricly.com/v1/chat/completions \
-H "Authorization: Bearer $AIPC_KEY" \
-d '{
"routing": {
"primary": "alibaba/qwen-3-max",
"fallback": ["anthropic/claude-4-6-sonnet"]
},
"messages": [{"role": "user", "content": "..."}]
}'