The Known Good Updated 29 Jul 2026
Providers· First-party endpoint· 46 tracked models

Alibaba — pricing & performance

Compare models All providers Data sources
Models served
46
of 947 tracked models
Mean output speed
62
tokens per second, averaged over
44 measured endpoints
Mean latency
0.9s
time to first token, averaged over
44 measured endpoints
Cheapest blended
$0.055
per 1M tokens at a 3:1
input:output blend
Output speed on Alibaba

Median output tokens per second for the 44 of 46 models on Alibaba with published throughput telemetry from OpenRouter. The full table below lists all 46, measured or not. Higher is better. We do not run these measurements ourselves.

⇩
224
132
127
117
108
106
99
87
87
74
71
67
The Known Good
46 models on Alibaba
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
DeepSeek: DeepSeek V3.2 DeepSeek $0.37 $1.11 $0.56 40 0.8s 131k
DeepSeek: DeepSeek V4 Flash DeepSeek $0.13 $0.27 $0.17 71 0.9s 1.00M
DeepSeek: DeepSeek V4 Pro DeepSeek $1.61 $3.22 $2.01 50 1.5s 1.00M
Qwen: Qwen Plus 0728 Alibaba $0.26 $0.78 $0.39 58 0.6s 1.00M
Qwen: Qwen Plus 0728 (thinking) Alibaba $0.40 $1.20 $0.60 50 0.5s 1.00M
Qwen: Qwen-Plus Alibaba $0.26 $0.78 $0.39 51 0.5s 1.00M
Qwen: Qwen3 14B Alibaba $0.23 $0.91 $0.40 45 0.3s 131k
Qwen: Qwen3 235B A22B Alibaba $0.46 $1.82 $0.80 58 0.4s 131k
Qwen: Qwen3 235B A22B Instruct 2507 Alibaba $0.15 $0.60 $0.26 45 0.4s 131k
Qwen: Qwen3 235B A22B Thinking 2507 Alibaba $0.23 $2.30 $0.75 51 0.6s 131k
Qwen: Qwen3 30B A3B Alibaba $0.13 $0.52 $0.23 99 0.3s 131k
Qwen: Qwen3 30B A3B Instruct 2507 Alibaba $0.13 $0.52 $0.23 44 0.3s 131k
Qwen: Qwen3 30B A3B Thinking 2507 Alibaba $0.20 $2.40 $0.75 106 0.4s 82k
Qwen: Qwen3 32B Alibaba $0.10 $0.42 $0.18 — — 131k
Qwen: Qwen3 8B Alibaba $0.12 $0.46 $0.20 60 0.6s 131k
Qwen: Qwen3 Coder 30B A3B Instruct Alibaba $0.29 $1.46 $0.58 52 0.9s 262k
Qwen: Qwen3 Coder 480B A35B Alibaba $0.97 $4.88 $1.95 — — 262k
Qwen: Qwen3 Coder Flash Alibaba $0.20 $0.97 $0.39 87 0.8s 1.00M
Qwen: Qwen3 Coder Next Alibaba $0.30 $1.50 $0.60 31 1.7s 262k
Qwen: Qwen3 Coder Plus Alibaba $0.65 $3.25 $1.30 36 1.3s 1.00M
Qwen: Qwen3 Max Alibaba $0.78 $3.90 $1.56 51 1.0s 262k
Qwen: Qwen3 Max Thinking Alibaba $0.78 $3.90 $1.56 37 1.1s 262k
Qwen: Qwen3 Next 80B A3B Instruct Alibaba $0.098 $0.78 $0.27 65 0.5s 131k
Qwen: Qwen3 Next 80B A3B Thinking Alibaba $0.15 $1.20 $0.41 224 0.4s 131k
Qwen: Qwen3 VL 235B A22B Instruct Alibaba $0.26 $1.04 $0.46 32 0.7s 131k
Qwen: Qwen3 VL 235B A22B Thinking Alibaba $0.40 $4.00 $1.30 58 0.6s 131k
Qwen: Qwen3 VL 30B A3B Instruct Alibaba $0.13 $0.52 $0.23 10 0.4s 131k
Qwen: Qwen3 VL 30B A3B Thinking Alibaba $0.20 $2.40 $0.75 117 0.5s 131k
Qwen: Qwen3 VL 32B Instruct Alibaba $0.10 $0.42 $0.18 28 1.1s 131k
Qwen: Qwen3 VL 8B Instruct Alibaba $0.12 $0.46 $0.20 57 0.5s 131k
Qwen: Qwen3 VL 8B Thinking Alibaba $0.18 $2.10 $0.66 132 0.7s 131k
Qwen: Qwen3.5 397B A17B Alibaba $0.39 $2.34 $0.88 63 1.2s 262k
Qwen: Qwen3.5 Plus 2026-02-15 Alibaba $0.26 $1.56 $0.58 59 1.2s 1.00M
Qwen: Qwen3.5 Plus 2026-04-20 Alibaba $0.30 $1.80 $0.68 55 0.5s 1.00M
Qwen: Qwen3.5-122B-A10B Alibaba $0.26 $2.08 $0.71 87 0.9s 262k
Qwen: Qwen3.5-27B Alibaba $0.20 $1.56 $0.54 24 0.8s 262k
Qwen: Qwen3.5-35B-A3B Alibaba $0.16 $1.30 $0.45 127 0.5s 262k
Qwen: Qwen3.5-Flash Alibaba $0.065 $0.26 $0.11 67 0.5s 1.00M
Qwen: Qwen3.6 27B Alibaba $0.45 $2.70 $1.01 12 4.5s 262k
Qwen: Qwen3.6 Flash Alibaba $0.19 $1.12 $0.42 74 0.7s 1.00M
Qwen: Qwen3.6 Max Preview Alibaba $1.04 $6.24 $2.34 38 1.3s 262k
Qwen: Qwen3.6 Plus Alibaba $0.33 $1.95 $0.73 39 1.1s 1.00M
Qwen: Qwen3.7 Flash Alibaba $0.030 $0.13 $0.055 108 1.0s 1.00M
Qwen: Qwen3.7 Max Alibaba $1.25 $3.75 $1.88 50 1.1s 1.00M
Qwen: Qwen3.7 Plus Alibaba $0.32 $1.28 $0.56 13 0.9s 1.00M
Z.ai: GLM 5.2 Z.ai $0.81 $2.53 $1.24 65 0.9s 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for Alibaba are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.