llmcloud.ai
← All providers
frontier

Alibaba (Qwen)

Qwen3 family, 1M context, strong multilingual.

live
Uptime (30d)
99.8%
Median tps
128
Median TTFT
240 ms
Price index
0.35×
vs. market median
Overview
HQ
Hangzhou, CN
Founded
1999
Models
11
Modalities
text, vision, audio
Regions
asia-east, asia-southeast
Strengths
multilinguallong-contextvision
Route via llmcloud
curl https://api.llmcloud.ai/v1/chat/completions \
  -H "Authorization: Bearer $LLMCLOUD_KEY" \
  -H "X-Provider: alibaba" \
  -d '{
    "model": "auto:quality",
    "messages": [{"role":"user","content":"hi"}]
  }'
Models served
qwen3-coder-480b
q 89.4130 tps$1.2/1M
qwen3-235b-thinking
q 88.982 tps$0.9/1M
qwen3-max
q 88.4128 tps$0.9/1M
qwen3-vl-235b
q 87.076 tps$2/1M
qwen3-235b-a22b
q 86.1145 tps$0.6/1M
qwen3-coder-30b
q 82.6220 tps$0.3/1M
qwen3-vl-72b
q 82.488 tps$1.2/1M
qwq-32b
q 81.6130 tps$0.3/1M
qwen2.5-coder-32b
q 80.2210 tps$0.3/1M
qwen3-omni-30b
q 79.2180 tps$0.4/1M
qwen2.5-72b-instruct
q 78.9190 tps$0.35/1M
qwen3-32b
q 78.4200 tps$0.2/1M
qwen3-14b
q 74.6260 tps$0.15/1M
qwen3-8b
q 70.1320 tps$0.1/1M