Qwen Models
Usage
97.9B
4.9M
135 of 156
- qwen3.8-flash
- qwen3.8-max
- qwen3.7-flash
- qwen3-vl-plus
- qwen3.7-plus
- coding-qwen4-max-preview
- qwen3.6-35b-a3b
- qwen3.8-max-2026-09-02
- 51 more models
- qwen3-vl-plus
- qwen3.8-flash
- qwen3.7-flash
- qwen3-embedding-0.6b
- qwen3-embedding-8b
- qwen3.7-plus
- qwen3.8-max-2026-09-02
- text-embedding-v4
- 127 more models
Which models that traffic went to
- Qwen3.8 Flash28.5%27.9B
- Qwen3.8 Max23.5%23B
- Qwen3.7 Flash20.7%20.2B
- Qwen3 VL Plus3.8%3.7B
- Qwen3.7 Plus2.4%2.3B
- Coding Qwen4 Max Preview2.2%2.2B
- Qwen3.6 35B A3B2.1%2B
- Qwen3.8 Max 2026 09-022.0%1.9B
- 51 more models14.8%14.5B
- Qwen3 VL Plus29.0%1.4M
- Qwen3.8 Flash20.2%983K
- Qwen3.7 Flash11.9%576K
- Qwen3 Embedding 0.6b9.3%454K
- Qwen3 Embedding 8B4.3%209K
- Qwen3.7 Plus4.0%197K
- Qwen3.8 Max 2026 09-023.0%147K
- Text Embedding V42.7%129K
- 127 more models15.5%756K
All 156 Qwen Models
Open in model list| Modalities | ||||||||
|---|---|---|---|---|---|---|---|---|
| qwen3-coder-plus | Takes text, returns text. | 1.05M | 66K | $0.54$2.16/M | $0.108/M | — | 83 tok/s | 1.63 s |
| qwen3.6-plus-preview-free | Takes text, returns text. | 1M | 66K | FreeFree/M | — | — | — | — |
| qwen3.8-flash-free | Takes text, vision, video, returns text. | 1M | 131K | FreeFree/M | — | — | — | — |
| qwen3.8-max-free | Takes text, vision, video, returns text. | 1M | 131K | FreeFree/M | — | — | — | — |
| qwen3.5-flash | Takes text, vision, video, returns text. | 1M | 66K | $0.0282$0.282/M | $0.0028/M | $0.0352/M | 52 tok/s | 1.83 s |
| qwen3.7-flash | Takes text, vision, video, returns text. | 1M | 131K | $0.0282$0.1128/M | $0.0056/M | $0.0352/M | 32 tok/s | 20.21 s |
| qwen3.5-plus | Takes text, vision, video, returns text. | 1M | 66K | $0.1096$0.6576/M | $0.011/M | $0.137/M | 49 tok/s | 0.90 s |
| qwen3.8-flash | Takes text, vision, video, returns text. | 1M | 131K | $0.1126$0.38/M | $0.0141/M | $0.1759/M | 55 tok/s | 3.84 s |
| qwen3.8-omni-flash | Takes text, vision, audio, video, returns text. | 1M | 131K | $0.1126$0.38/M | $0.0141/M | $0.1759/M | 28 tok/s | 26.01 s |
| qwen3-coder-flash | Takes text, returns text. | 1M | 66K | $0.136$0.544/M | — | — | 110 tok/s | 1.85 s |
| qwen3.6-flash | Takes text, vision, video, returns text. | 1M | 66K | $0.169$1.014/M | $0.0169/M | $0.2112/M | 63 tok/s | 11.30 s |
| qwen3.8-27b | Takes text, vision, video, returns text. | 1M | 131K | $0.2$2.5/M | $0.05/M | — | — | — |
| qwen3.6-plus | Takes text, vision, video, returns text. | 1M | 66K | $0.282$1.692/M | $0.0282/M | $0.3525/M | 54 tok/s | 2.27 s |
| qwen3.7-plus | Takes text, vision, video, returns text. | 1M | 131K | $0.282$1.128/M | $0.0564/M | $0.3525/M | 29 tok/s | 3.94 s |
| qwen3.8-max-preview | Takes text, vision, video, returns text. | 1M | 131K | $0.338$1.014/M | $0.0676/M | $0.4225/M | 48 tok/s | 2.40 s |
| coding-qwen4-max-preview | Takes text, vision, video, returns text. | 1M | 393K | $0.353$1.059/M | $0.0441/M | $0.4412/M | 37 tok/s | 4.22 s |
| qwen4-max | Takes text, vision, video, returns text. | 1M | 262K | $1.471$4.412/M | $0.0736/M | $1.8388/M | 35 tok/s | 12.38 s |
| qwen3.7-max | Takes text, returns text. | 1M | 131K | $1.69$5.07/M | $0.169/M | $2.1125/M | 50 tok/s | 2.80 s |
| qwen3.8-max | Takes text, vision, video, returns text. | 1M | 131K | $1.69$5.07/M | $0.169/M | $2.1125/M | 27 tok/s | 2.32 s |
| qwen3.8-max-2026-09-02 | Takes text, vision, video, returns text. | 1M | 131K | $1.69$5.07/M | $0.169/M | $2.1125/M | 11 tok/s | 3.86 s |
| qwen3.8-2.4t-a95b | Takes text, returns text. | 1M | 131K | $2$6/M | $0.5/M | — | 48 tok/s | 1.41 s |
| qwen3-vl-flash | Takes text, vision, video, returns text. | 262K | 33K | $0.0206$0.206/M | $0.0041/M | — | 5 tok/s | 0.34 s |
| qwen3-vl-flash-2026-01-22 | Takes text, vision, video, returns text. | 262K | 33K | $0.0206$0.206/M | — | — | 2 tok/s | 1.04 s |
| qwen3.5-35b-a3b | Takes text, vision, video, returns text. | 262K | 66K | $0.0564$0.4512/M | — | — | 59 tok/s | 4.14 s |
| qwen3.5-27b | Takes text, vision, video, returns text. | 262K | 66K | $0.0846$0.6768/M | — | — | 54 tok/s | 2.03 s |
| qwen3.5-122b-a10b | Takes text, vision, video, returns text. | 262K | 66K | $0.1126$0.9008/M | — | — | 129 tok/s | 1.00 s |
| qwen3-coder-next | Takes text, returns text. | 262K | 66K | $0.137$0.548/M | — | — | 16 tok/s | 0.51 s |
| qwen3-vl-plus | Takes text, vision, video, returns text. | 262K | 33K | $0.137$1.37/M | $0.0274/M | — | 67 tok/s | 2.32 s |
| qwen3.5-397b-a17b | Takes text, vision, video, returns text. | 262K | 66K | $0.1644$0.9864/M | — | — | 55 tok/s | 1.83 s |
| qwen3-coder-30b-a3b-instruct | Takes text, returns text. | 262K | 262K | $0.2$0.8/M | — | — | 115 tok/s | 0.95 s |
| qwen3.6-35b-a3b | Takes text, vision, video, returns text. | 262K | 66K | $0.254$1.524/M | — | — | 99 tok/s | 1.14 s |
| qwen3-235b-a22b-instruct-2507 | Takes text, vision, returns text. | 262K | 16K | $0.28$1.12/M | — | — | 96 tok/s | 1.03 s |
| qwen3-235b-a22b-thinking-2507 | Takes text, vision, returns text. | 262K | 131K | $0.28$2.8/M | — | — | 87 tok/s | 0.51 s |
| qwen3-235b-a22b-2507 | Takes text, returns text. | 262K | — | $0.35$1.4/M | $0.07/M | — | — | — |
| qwen3.6-27b | Takes text, vision, video, returns text. | 262K | 66K | $0.422$2.532/M | — | — | 81 tok/s | 1.84 s |
| qwen3-max | Takes text, returns text. | 262K | 66K | $0.4508$1.8032/M | $0.0902/M | $0.5635/M | 36 tok/s | 2.41 s |
| qwen3-max-2026-01-23 | Takes text, returns text. | 262K | 66K | $0.4508$1.8032/M | $0.0902/M | $0.5635/M | — | — |
| qwen3.6-max-preview | Takes text, returns text. | 262K | 66K | $1.268$7.608/M | $0.1268/M | $1.585/M | 185 tok/s | 0.65 s |
| qwen3-coder-480b-a35b-instruct | Takes text, returns text. | 262K | 66K | $0.82$3.28/M | — | — | 1655 tok/s | 0.92 s |
| qwen3-next-80b-a3b-instruct | Takes text, vision, returns text. | 256K | 33K | $0.138$0.552/M | — | — | 150 tok/s | 0.10 s |
| qwen3-next-80b-a3b-thinking | Takes text, vision, returns text. | 256K | 33K | $0.142$1.42/M | — | — | 109 tok/s | 0.55 s |
| qwen3-vl-30b-a3b-instruct | Takes text, vision, video, returns text. | 131K | 33K | $0.1028$0.4112/M | — | — | 42 tok/s | 1.07 s |
| qwen3-vl-30b-a3b-thinking | Takes text, vision, video, returns text. | 131K | 33K | $0.1028$1.028/M | — | — | 42 tok/s | 1.49 s |
| qwen3-vl-235b-a22b-instruct | Takes text, vision, video, returns text. | 131K | 33K | $0.274$1.096/M | — | — | 57 tok/s | 1.13 s |
| qwen3-vl-235b-a22b-thinking | Takes text, vision, video, returns text. | 131K | 33K | $0.274$2.74/M | — | — | 58 tok/s | 2.22 s |
| qwen-3.8-27b | Takes text, vision, video, returns text. | 131K | — | $1.1$1.65/M | — | — | 562 tok/s | 0.40 s |
| bai-qwen3-vl-235b-a22b-instruct | Takes , returns text. | 131K | — | $0.274$1.096/M | — | — | 5 tok/s | 0.39 s |
| kat-dev | Takes text, returns text. | 128K | — | $0.137$0.548/M | — | — | — | — |
| Qwen/Qwen2.5-VL-72B-Instruct | Takes text, vision, video, returns text. | 128K | — | $0.5$0.5/M | — | — | — | — |
| qwen3-coder-plus-2025-07-22 | Takes text, returns text. | 128K | 66K | $0.54$2.16/M | $0.108/M | — | 83 tok/s | 1.63 s |
| decision-model-preview | Takes text. Output modality not published. | 64K | — | FreeFree/M | — | — | — | — |
| qwen3-reranker-0.6b | Takes text, vision. Output modality not published. | 16K | 8K | $0.11$0.11/M | — | — | — | — |
| qwen-mt-turbo | Takes text, returns text. | 16K | 8K | $0.192$0.5349/M | — | — | 1 tok/s | 1.10 s |
| qwen-mt-plus | Takes text, returns text. | 16K | 8K | $0.492$1.476/M | — | — | 8 tok/s | 0.30 s |
| wan3.0-video-free | Takes text, vision, audio, video, PDF, returns video. | — | — | FreeFree/M | — | — | — | — |
| wan3.0-video-prime-free | Takes text, vision, audio, video, PDF, returns video. | — | — | FreeFree/M | — | — | — | — |
| qwen-flash | Takes , returns text. | — | — | $0.02$0.2/M | — | — | 34 tok/s | 0.40 s |
| qwen-flash-2025-07-28 | Takes , returns text. | — | — | $0.02$0.2/M | — | — | 2 tok/s | 0.39 s |
| qwen-turbo | Takes text, returns text. | — | — | $0.046$0.092/M | $0.0092/M | — | 23 tok/s | 0.84 s |
| qwen-turbo-2024-11-01 | Takes text, returns text. | — | — | $0.046$0.092/M | — | — | 94 tok/s | 0.66 s |
| qwen-turbo-2025-04-28 | Takes , returns text. | — | — | $0.046$0.092/M | — | — | — | — |
| qwen-turbo-latest | Takes , returns text. | — | — | $0.046$0.092/M | $0.0092/M | — | — | — |
| qwen3-0.6b | Takes , returns text. | — | — | $0.046$0.46/M | — | — | — | — |
| qwen3-1.7b | Takes , returns text. | — | — | $0.046$0.46/M | — | — | — | — |
| qwen3-4b | Takes , returns text. | — | — | $0.046$0.46/M | — | — | — | — |
| bce-reranker-base | Takes text, vision. Output modality not published. | — | — | $0.068$0.068/M | — | — | — | — |
| qwen3-embedding-0.6b | Takes text. Output modality not published. | — | — | $0.068$0.068/M | — | — | — | — |
| qwen3-embedding-4b | Takes text. Output modality not published. | — | — | $0.068$0.068/M | — | — | — | — |
| qwen3-embedding-8b | Takes text. Output modality not published. | — | — | $0.068$0.068/M | — | — | — | — |
| Qwen/Qwen2-7B-Instruct | Takes , returns text. | — | — | $0.08$0.08/M | — | — | — | — |
| qwen3-8b | Takes , returns text. | — | — | $0.08$0.8/M | — | — | 62 tok/s | 0.39 s |
| text-embedding-v4 | Takes text. Output modality not published. | — | — | $0.08$0.08/M | — | — | — | — |
| qwen-long | Takes , returns text. | — | — | $0.1$0.4/M | — | — | 45 tok/s | 2.96 s |
| qwen3-30b-a3b-instruct-2507 | Takes , returns text. | — | — | $0.1028$0.4112/M | — | — | — | — |
| gte-rerank-v2 | Takes text, vision. Output modality not published. | — | — | $0.11$0.11/M | — | — | — | — |
| qwen3-reranker-4b | Takes text, vision. Output modality not published. | — | — | $0.11$0.11/M | — | — | — | — |
| qwen3-reranker-8b | Takes text, vision. Output modality not published. | — | — | $0.11$0.11/M | — | — | — | — |
| qwen-plus | Takes , returns text. | — | — | $0.1126$1.126/M | $0.0225/M | $0.1407/M | 44 tok/s | 0.76 s |
| qwen-plus-2025-04-28 | Takes , returns text. | — | — | $0.1126$1.126/M | $0.0225/M | $0.1407/M | 2 tok/s | 0.37 s |
| qwen-plus-2025-07-28 | Takes , returns text. | — | — | $0.1126$1.126/M | $0.0225/M | $0.1407/M | — | — |
| qwen-plus-latest | Takes , returns text. | — | — | $0.1126$1.126/M | $0.0225/M | $0.1407/M | 35 tok/s | 0.68 s |
| qwen3-30b-a3b | Takes , returns text. | — | — | $0.12$1.2/M | — | — | — | — |
| qwen3-30b-a3b-thinking-2507 | Takes , returns text. | — | — | $0.12$1.2/M | — | — | — | — |
| gme-qwen2-vl-2b-instruct | Takes text, vision, video. Output modality not published. | — | — | $0.138$0.138/M | — | — | — | — |
| Qwen/QwQ-32B | Takes , returns text. | — | — | $0.14$0.56/M | — | — | — | — |
| Qwen/Qwen2.5-Coder-32B-Instruct | Takes , returns text. | — | — | $0.16$0.16/M | — | — | — | — |
| Qwen/QwQ-32B-Preview | Takes , returns text. | — | — | $0.16$0.16/M | — | — | — | — |
| qwen3-14b | Takes , returns text. | — | — | $0.16$1.6/M | — | — | 59 tok/s | 0.31 s |
| qwen3-32b | Takes , returns text. | — | — | $0.16$0.64/M | — | — | — | — |
| Qwen/Qwen2-1.5B-Instruct | Takes , returns text. | — | — | $0.2$0.2/M | — | — | — | — |
| Qwen/Qwen3-8B | Takes , returns text. | — | — | $0.2$0.2/M | — | — | 11 tok/s | 3.31 s |
| qwen2.5-coder-1.5b-instruct | Takes , returns text. | — | — | $0.2$0.4/M | — | — | — | — |
| qwen2.5-coder-7b-instruct | Takes , returns text. | — | — | $0.2$0.4/M | — | — | — | — |
| qwen2.5-math-1.5b-instruct | Takes , returns text. | — | — | $0.2$0.2/M | — | — | — | — |
| qwen2.5-math-7b-instruct | Takes , returns text. | — | — | $0.2$0.4/M | — | — | — | — |
| Qwen/Qwen2-57B-A14B-Instruct | Takes , returns text. | — | — | $0.24$0.24/M | — | — | — | — |
| Qwen/Qwen2.5-VL-32B-Instruct | Takes text, vision, video, returns text. | — | — | $0.24$0.24/M | — | — | — | — |
| qwen-3-235b-a22b-instruct-2507 | Takes , returns text. | — | — | $0.28$1.4/M | — | — | — | — |
| qwen-3-235b-a22b-thinking-2507 | Takes , returns text. | — | — | $0.28$2.8/M | — | — | 2 tok/s | 34.08 s |
| Qwen2-VL-7B-Instruct | Takes text, vision, video, returns text. | — | — | $0.28$0.7/M | — | — | — | — |
| Qwen3-235B-A22B-Thinking-2507 | Takes , returns text. | — | — | $0.28$2.8/M | — | — | 87 tok/s | 0.51 s |
| qwen-max | Takes , returns text. | — | — | $0.38$1.52/M | — | — | 9 tok/s | 1.71 s |
| qwen-max-0125 | Takes , returns text. | — | — | $0.38$1.52/M | — | — | — | — |
| qwen-3-32b | Takes , returns text. | — | — | $0.4$1.6/M | — | — | — | — |
| qwen-qwq-32b | Takes , returns text. | — | — | $0.4$0.8/M | — | — | — | — |
| Qwen/Qwen2.5-7B-Instruct | Takes , returns text. | — | — | $0.4$0.4/M | — | — | — | — |
| Qwen/Qwen3-32B | Takes , returns text. | — | — | $0.4$0.8/M | — | — | — | — |
| qwen2.5-14b-instruct | Takes , returns text. | — | — | $0.4$1.2/M | — | — | — | — |
| qwen2.5-3b-instruct | Takes , returns text. | — | — | $0.4$0.8/M | — | — | — | — |
| qwen2.5-7b-instruct | Takes , returns text. | — | — | $0.4$0.8/M | — | — | — | — |
| Qwen/Qwen3-14B | Takes , returns text. | — | — | $0.5$0.5/M | — | — | — | — |
| Qwen/Qwen2.5-32B-Instruct | Takes , returns text. | — | — | $0.6$0.6/M | — | — | 24 tok/s | 1.62 s |
| qwen2.5-32b-instruct | Takes , returns text. | — | — | $0.6$1.2/M | — | — | — | — |
| Qwen/Qwen2-72B-Instruct | Takes , returns text. | — | — | $0.8$0.8/M | — | — | — | — |
| Qwen/Qwen2.5-72B-Instruct | Takes , returns text. | — | — | $0.8$0.8/M | — | — | — | — |
| Qwen/Qwen2.5-72B-Instruct-128K | Takes , returns text. | — | — | $0.8$0.8/M | — | — | — | — |
| qwen2.5-72b-instruct | Takes , returns text. | — | — | $0.8$2.4/M | — | — | — | — |
| qwen2.5-math-72b-instruct | Takes , returns text. | — | — | $0.8$2.4/M | — | — | — | — |
| qwen3-max-preview | Takes text, vision, returns text. | — | — | $0.846$3.384/M | $0.1692/M | — | 2 tok/s | 0.58 s |
| Qwen/Qwen3-30B-A3B | Takes , returns text. | — | — | $1$1/M | — | — | — | — |
| Qwen/QVQ-72B-Preview | Takes , returns text. | — | — | $1.2$1.2/M | — | — | — | — |
| Qwen2-VL-72B-Instruct | Takes text, vision, video, returns text. | — | — | $2.18$6.54/M | — | — | — | — |
| qwen2.5-vl-72b-instruct | Takes text, vision, returns text. | — | — | $2.4$7.2/M | — | — | — | — |
| qwen-max-longcontext | Takes , returns text. | — | — | $7$21/M | — | — | 2 tok/s | 0.48 s |
| happyhorse-1.0-i2v | Takes text, vision, returns video. | — | — | from $0.1395 / s | — | — | — | — |
| happyhorse-1.0-r2v | Takes text, vision, returns video. | — | — | from $0.1395 / s | — | — | — | — |
| happyhorse-1.0-t2v | Takes text, returns video. | — | — | from $0.1395 / s | — | — | — | — |
| happyhorse-1.0-video-edit | Takes text, vision, video, returns video. | — | — | from $0.1395 / s | — | — | — | — |
| happyhorse-1.1-i2v | Takes text, vision, returns video. | — | — | from $0.1395 / s | — | — | — | — |
| happyhorse-1.1-r2v | Takes text, vision, returns video. | — | — | from $0.1395 / s | — | — | — | — |
| happyhorse-1.1-t2v | Takes text, returns video. | — | — | from $0.1395 / s | — | — | — | — |
| qwen-audio-3.0-tts-flash | Takes text, returns audio. | — | — | $0.0142 / 1K chars | — | — | — | — |
| qwen-audio-3.0-tts-plus | Takes text, returns audio. | — | — | $0.0197 / 1K chars | — | — | — | — |
| qwen-image | Takes text, vision, returns vision. | — | — | $0.036 / img | — | — | — | — |
| qwen-image-2.0 | Takes text, vision, returns vision. | — | — | $0.0282 / img | — | — | — | — |
| qwen-image-2.0-pro | Takes text, vision, returns vision. | — | — | $0.0704 / img | — | — | — | — |
| qwen-image-2.1-pro | Takes text, vision, returns vision. | — | — | $0.0352 / img | — | — | — | — |
| qwen-image-2.1-turbo | Takes text, vision, returns vision. | — | — | $0.0141 / img | — | — | — | — |
| qwen-image-3.0 | Takes text, vision, returns vision. | — | — | $0.0254 / img | — | — | — | — |
| qwen-image-3.0-pro | Takes text, vision, returns vision. | — | — | from $0.0357 / img | — | — | — | — |
| qwen-image-edit | Takes text, vision, returns vision. | — | — | $0.042 / img | — | — | — | — |
| qwen-image-max | Takes text, vision, returns vision. | — | — | $0.0704 / img | — | — | — | — |
| wan2.2-i2v-plus | Takes text, vision, returns video. | — | — | from $0.0192 / s | — | — | — | — |
| wan2.5-i2v-preview | Takes text, vision, returns video. | — | — | from $0.0411 / s | — | — | — | — |
| wan2.5-t2v-preview | Takes text, returns video. | — | — | from $0.0411 / s | — | — | — | — |
| wan2.6-i2v | Takes text, vision, returns video. | — | — | from $0.0904 / s | — | — | — | — |
| wan2.6-t2i | Takes text, vision, returns vision. | — | — | $0.0282 / img | — | — | — | — |
| wan2.6-t2v | Takes text, returns video. | — | — | from $0.0904 / s | — | — | — | — |
| wan2.7-i2v | Takes text, vision, audio, returns video. | — | — | from $0.0846 / s | — | — | — | — |
| wan2.7-image | Takes text, vision, returns vision. | — | — | $0.0282 / img | — | — | — | — |
| wan2.7-image-pro | Takes text, vision, returns vision. | — | — | $0.0704 / img | — | — | — | — |
| wan2.7-r2v | Takes text, vision, audio, video, returns video. | — | — | from $0.0846 / s | — | — | — | — |
| wan2.7-t2v | Takes text, audio, returns video. | — | — | from $0.0846 / s | — | — | — | — |
| wan2.7-videoedit | Takes text, vision, video, returns video. | — | — | from $0.0846 / s | — | — | — | — |
| wan3.0-video | Takes text, vision, audio, video, returns video. | — | — | from $0.0423 / s | — | — | — | — |
| wan3.0-video-prime | Takes text, vision, audio, video, returns video. | — | — | from $0.0634 / s | — | — | — | — |
Qwen on AIHubMix
Which Qwen model should I start with?
qwen3-vl-flash at $0.0206/M input — the cheapest entry here that declares tool calling, and it carries a 262K context. Move up to qwen-max-longcontext when answer quality matters more than cost, or to qwen3.6-plus-preview-free for long-form reasoning.
Which of these models reason before answering?
25 of the 156 models here declare a reasoning phase — they work through the problem before producing an answer, which helps on multi-step problems at the cost of extra output tokens. Use the Reasoning filter above the table to see them. The catalog does not record anything further about how they differ, so this page does not sort them into families.
Why are there several entries for the same model?
Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), some are the open-weight repository form (Qwen/…), and some differ only in capitalisation, kept so older integrations keep working.
The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.
How is cached input billed?
The Cache read column is the rate for input tokens served from the prompt cache — for example qwen4-max bills cache hits at 5% of the input rate and qwen3.5-flash bills cache hits at 10% of the input rate. Cache write is the surcharge for putting a prompt into the cache in the first place, and only a few upstreams bill it separately. A dash in either column means the catalog carries no cache rate for that model, so plan on paying the full input rate.
Do I need a separate Qwen account?
No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.
Start calling Qwen in one line
One key, one endpoint, 984 models across 49 model authors.
