Alibaba
Models on Alibaba · prices & measurements for models served by Alibaba’s APIUSD / MTOK · VERIFIED 23 MINUTES AGO
| MODEL | INPUT | OUTPUT | CONTEXT | QUANT | TTFT | TPS | SMOKE | VS BEST ELSEWHERE |
|---|---|---|---|---|---|---|---|---|
 Qwen3.7 FlashQwen | $0.03 | $0.13 | 1M | — | 1s° | 77° tok/s | — | only provider |
| Qwen3.5-FlashQwen | $0.065 | $0.26 | 1M | — | 1.1s° | 183° tok/s | — | only provider |
| Qwen3 Next 80B A3B InstructQwen | $0.098 | $0.78 | 131K | — | ✕ | ✕ | — | $0.09 elsewhere |
| Qwen3 VL 32B InstructQwen | $0.104 | $0.416 | 131K | — | 1.7s° | 92° tok/s | — | only provider |
| Qwen3 VL 8B InstructQwenBEST PRICE | $0.117 | $0.455 | 131K | — | 1.4s° | 121° tok/s | — | cheapest here |
| Qwen3 8BQwen | $0.117 | $0.455 | 131K | — | 2.9s° | 37° tok/s | — | only provider |
| Qwen3 VL 30B A3B InstructQwenBEST PRICE | $0.13 | $0.52 | 131K | — | 1.3s° | 109° tok/s | — | cheapest here |
| Qwen3 30B A3B Instruct 2507Qwen | $0.13 | $0.52 | 131K | — | ✕ | ✕ | — | $0.048 elsewhere |
| Qwen3 30B A3BQwen | $0.13 | $0.52 | 131K | — | ✕ | ✕ | — | $0.12 elsewhere |
 DeepSeek V4 Flash 0423DeepSeek | $0.134 | $0.268 | 1M | fp8 | 0.93s° | 115° tok/s | — | $0.017 elsewhere |
| Qwen3 235B A22B Instruct 2507Qwen | $0.149 | $0.598 | 131K | — | 1.4s° | 37° tok/s | 5/5 | $0.087 elsewhere |
| Qwen3.8 Omni FlashQwen | $0.15 | $0.47 | 1M | — | ✕ | ✕ | — | only provider |
| Qwen3.8 FlashQwen | $0.15 | $0.47 | 1M | — | ✕ | ✕ | — | only provider |
| Qwen3 Next 80B A3B ThinkingQwenBEST PRICE | $0.15 | $1.20 | 131K | — | 2s° | 191° tok/s | — | cheapest here |
| Qwen3.5-35B-A3BQwen | $0.163 | $1.30 | 262K | — | 1.5s° | 202° tok/s | 5/5 | $0.08 elsewhere |
| Qwen3 VL 8B ThinkingQwen | $0.18 | $2.10 | 131K | — | 1.5s° | 119° tok/s | — | only provider |
| Qwen3.6 FlashQwen | $0.188 | $1.13 | 1M | — | 0.97s° | 120° tok/s | — | only provider |
| Qwen3.5-27BQwenBEST PRICE | $0.195 | $1.56 | 262K | — | ✕ | ✕ | 5/5 | cheapest here |
| Qwen3 Coder FlashQwen | $0.195 | $0.975 | 1M | — | 2s° | 105° tok/s | — | only provider |
| Qwen3 VL 30B A3B ThinkingQwenBEST PRICE | $0.20 | $2.40 | 131K | — | ✕ | ✕ | — | cheapest here |
| Qwen3 30B A3B Thinking 2507Qwen | $0.20 | $2.40 | 82K | — | 1.3s° | 112° tok/s | — | only provider |
| Qwen3 14BQwen | $0.228 | $0.91 | 131K | — | ✕ | ✕ | — | $0.10 elsewhere |
| Qwen3 235B A22B Thinking 2507QwenBEST PRICE | $0.23 | $2.30 | 131K | — | 1.7s° | 80° tok/s | — | cheapest here |
| Qwen3.5-122B-A10BQwenBEST PRICE | $0.26 | $2.08 | 262K | — | 1.5s° | 159° tok/s | 5/5 | cheapest here |
| Qwen3.5 Plus 2026-02-15Qwen | $0.26 | $1.56 | 1M | — | ✕ | ✕ | — | only provider |
| Qwen3 VL 235B A22B InstructQwen | $0.26 | $1.04 | 131K | — | 1.9s° | 53° tok/s | — | $0.20 elsewhere |
| Qwen Plus 0728Qwen | $0.26 | $0.78 | 1M | — | 1.4s° | 53° tok/s | — | only provider |
| Qwen-PlusQwen | $0.26 | $0.78 | 1M | — | ✕ | ✕ | — | only provider |
| Qwen3 Coder 30B A3B InstructQwen | $0.292 | $1.46 | 262K | — | ✕ | ✕ | — | $0.07 elsewhere |
| DeepSeek V4.1 FlashDeepSeek | $0.30 | $1.20 | 1M | — | 0.93s° | 116° tok/s | — | $0.018 elsewhere |
| Qwen3.5 Plus 2026-04-20Qwen | $0.30 | $1.80 | 1M | — | ✕ | ✕ | — | only provider |
| Qwen3 Coder NextQwen | $0.30 | $1.50 | 262K | — | ✕ | ✕ | — | $0.12 elsewhere |
| Qwen3.7 PlusQwen | $0.32 | $1.28 | 1M | — | 1.2s° | 69° tok/s | — | only provider |
| Qwen3.6 PlusQwen | $0.325 | $1.95 | 1M | — | ✕ | ✕ | — | only provider |
| DeepSeek V4 Flash 0731DeepSeek | $0.352 | $1.06 | 1M | — | ✕ | ✕ | — | $0.01 elsewhere |
| DeepSeek V3.2DeepSeek | $0.37 | $1.11 | 131K | fp8 | 1.6s° | 43° tok/s | — | $0.209 elsewhere |
| Qwen3.5 397B A17BQwenBEST PRICE | $0.39 | $2.34 | 262K | — | 1.6s° | 111° tok/s | 5/5 | cheapest here |
| Qwen3 VL 235B A22B ThinkingQwenBEST PRICE | $0.40 | $4.00 | 131K | — | 38.8s° | 61° tok/s | — | cheapest here |
| Qwen3.8 27BQwen | $0.425 | $2.55 | 1M | — | 4.4s° | 55° tok/s | — | $0.024 elsewhere |
| Qwen3.6 27BQwen | $0.45 | $2.70 | 262K | — | ✕ | ✕ | 5/5 | $0.30 elsewhere |
| Qwen3 235B A22BQwen | $0.455 | $1.82 | 131K | — | 1.7s° | 47° tok/s | — | only provider |
| Qwen3 Coder PlusQwen | $0.65 | $3.25 | 1M | — | ✕ | ✕ | — | only provider |
| Qwen3 Max ThinkingQwen | $0.78 | $3.90 | 262K | — | ✕ | ✕ | — | only provider |
| Qwen3 MaxQwen | $0.78 | $3.90 | 262K | — | 1s° | 49° tok/s | — | only provider |
 Kimi K2.7 CodeMoonshot AI | $0.95 | $4.00 | 262K | fp8 | 5.7s° | 59° tok/s | — | $0.671 elsewhere |
 GLM 5.2Z.ai | $0.966 | $3.04 | 1M | fp8 | ✕ | ✕ | — | $0.03 elsewhere |
| Qwen3 Coder 480B A35BQwen | $0.975 | $4.88 | 262K | — | 1.7s° | 44° tok/s | — | $0.22 elsewhere |
| Qwen3.6 Max PreviewQwen | $1.03 | $6.16 | 262K | — | ✕ | ✕ | — | only provider |
| DeepSeek V4 Pro 0813DeepSeek | $1.12 | $3.37 | 1M | — | ✕ | ✕ | 4/5 | $0.158 elsewhere |
| GLM 5.3Z.ai | $1.19 | $3.74 | 1M | — | 0.69s° | 80° tok/s | — | $0.039 elsewhere |
| GLM 5.1Z.ai | $1.33 | $4.18 | 203K | fp8 | 2.1s° | 63° tok/s | — | $0.966 elsewhere |
| DeepSeek V4 Pro 0423DeepSeek | $1.42 | $2.83 | 1M | fp8 | 1.6s° | 71° tok/s | — | $0.30 elsewhere |
| Qwen3.7 MaxQwen | $1.48 | $4.42 | 1M | — | 1.2s° | 83° tok/s | — | only provider |
| Qwen3.8 Max (0902)Qwen | $2.00 | $6.00 | 1M | — | ✕ | ✕ | — | only provider |
| Qwen3.8 2.4T A95BQwenBEST PRICE | $2.00 | $6.00 | 1M | — | 1.9s° | 50° tok/s | 5/5 | cheapest here |
| GLM 5.3 PrimeZ.ai | $2.80 | $8.80 | 1M | — | ✕ | ✕ | — | only provider |
| Kimi K3Moonshot AI | $3.45 | $17.25 | 1.05M | — | 1.6s° | 36° tok/s | — | $0.68 elsewhere |
| Qwen3.8 Max PrimeQwen | $4.00 | $12.00 | 1M | — | 1.6s° | 81° tok/s | — | only provider |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) for Alibaba’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page