Qwen (Alibaba) models, priced in toman
44 Qwen (Alibaba) models are live on uttapen. Prices are in toman per 1 million tokens, and you are charged for the tokens you actually use.
Qwen (Alibaba) on uttapen
Qwen (Alibaba) is the 3rd largest of the 65 suppliers in the uttapen catalogue, with 44 models. All of them bill against a toman wallet, for the tokens a request actually used.
The spread inside Qwen (Alibaba) alone is wide: Qwen3.7 Flash runs about 72 toman for a 1,000-word request, while Qwen3.8 Max Prime costs 7,201 toman for the same one. Picking the right model inside a brand matters as much as picking the brand.
Measured against the whole catalogue, the median Qwen (Alibaba) output price undercuts about 62% of the other paid models.
On capabilities: 25 take image input, 40 support tool calling, 27 do multi-step reasoning, 1 accepts audio. The longest context belongs to Qwen3.8 2.4T A95B, at 1,048,576 tokens.
Every Qwen (Alibaba) model answers on the same sk-up- key and the same base_url: switching between them means changing the `model` string and nothing else.
Which Qwen (Alibaba) model should I start with?
- Qwen3.7 Flash72 · per 1,000 wordsThe cheapest way in: about 72 toman for a 1,000-word request.
- Qwen3.8 2.4T A95B3,601 · per 1,000 wordsFor multi-step problems, maths and debugging: it reasons before it answers.
- Qwen2.5 VL 72B Instruct810 · per 1,000 wordsWhen the input is an image or a scanned invoice.
- Qwen3 Embedding 8B4.50 · per 1,000 wordsAn embedding model for semantic search and RAG; only input tokens are billed.
Every Qwen (Alibaba) model, priced in toman
| Model | Capabilities | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
Qwen3 Coder 480B A35Bqwen/qwen3-coder | Tool callingJSON output | 262,144 | 103,866 | 346,219 |
Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct | Tool callingJSON output | 32,768 | 124,639 | 138,488 |
Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct | Tool callingJSON output | 32,768 | 34,622 | 69,244 |
Qwen2.5 Coder 32B Instructqwen/qwen-2.5-coder-32b-instruct | JSON output | 32,768 | 228,505 | 346,219 |
Qwen-Plusqwen/qwen-plus | Tool callingJSON output | 1,000,000 | 90,017 | 270,051 |
Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instruct | Image inputJSON output | 128,000 | 276,975 | 346,219 |
Qwen3 14Bqwen/qwen3-14b | Tool callingReasoningJSON output | 40,960 | 41,546 | 83,093 |
Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507 | Tool callingJSON output | 262,144 | 48,471 | 276,975 |
Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507 | Tool callingReasoning | 128,000 | 155,799 | 1,211,768 |
Qwen3 30B A3Bqwen/qwen3-30b-a3b | Tool callingReasoningJSON output | 40,960 | 41,546 | 173,110 |
Qwen3.8 Max Primeqwen/qwen3.8-max-prime | Image inputTool callingReasoningJSON output | 1,000,000 | 1,384,877 | 4,154,632 |
Qwen3.8 Omni Flashqwen/qwen3.8-omni-flash | Image inputTool callingReasoningJSON output | 1,000,000 | 51,933 | 162,723 |
Qwen3.8 Max (0902)qwen/qwen3.8-max-0902 | Image inputTool callingReasoningJSON output | 1,000,000 | 692,439 | 2,077,316 |
Qwen3.8 Flashqwen/qwen3.8-flash | Image inputTool callingReasoningJSON output | 1,000,000 | 51,933 | 162,723 |
Qwen3.8 27Bqwen/qwen3.8-27b | Image inputTool callingReasoningJSON output | 1,024,000 | 51,933 | 649,161 |
Qwen3.8 2.4T A95Bqwen/qwen3.8-2.4t-a95b | Tool callingReasoningJSON output | 1,048,576 | 692,439 | 2,077,316 |
Qwen3.7 Flashqwen/qwen3.7-flash | Image inputTool callingReasoningJSON output | 1,000,000 | 10,387 | 45,009 |
Qwen3.7 Plusqwen/qwen3.7-plus | Image inputTool callingReasoningJSON output | 1,000,000 | 110,790 | 443,161 |
Qwen3.7 Maxqwen/qwen3.7-max | Tool callingReasoningJSON output | 1,000,000 | 510,674 | 1,532,021 |
Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420 | Image inputTool callingReasoningJSON output | 1,000,000 | 103,866 | 623,195 |
Qwen3.6 Flashqwen/qwen3.6-flash | Image inputTool callingReasoningJSON output | 1,000,000 | 64,916 | 389,497 |
Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b | Image inputTool callingReasoningJSON output | 262,144 | 34,622 | 311,597 |
Qwen3.6 27Bqwen/qwen3.6-27b | Image inputTool callingReasoningJSON output | 262,144 | 155,799 | 934,792 |
Qwen3.6 Plusqwen/qwen3.6-plus | Image inputTool callingReasoningJSON output | 1,000,000 | 112,521 | 675,128 |
Qwen3.5-9Bqwen/qwen3.5-9b | Image inputTool callingReasoningJSON output | 262,144 | 58,857 | 86,555 |
Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b | Image inputTool callingReasoningJSON output | 262,144 | 48,471 | 346,219 |
Qwen3.5-27Bqwen/qwen3.5-27b | Image inputTool callingReasoningJSON output | 262,144 | 90,017 | 900,170 |
Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b | Image inputTool callingReasoningJSON output | 262,144 | 90,017 | 720,136 |
Qwen3.5-Flashqwen/qwen3.5-flash-02-23 | Image inputTool callingReasoningJSON output | 1,000,000 | 22,504 | 90,017 |
Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15 | Image inputTool callingReasoningJSON output | 1,000,000 | 90,017 | 540,102 |
Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b | Image inputTool callingReasoningJSON output | 262,144 | 173,110 | 1,246,390 |
Qwen3 Coder Nextqwen/qwen3-coder-next | Tool callingJSON output | 262,144 | 41,546 | 276,975 |
Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct | Image inputTool callingJSON output | 262,144 | 72,706 | 657,817 |
Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507 | Tool callingJSON output | 262,144 | 34,622 | 103,866 |
Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instruct | Image inputTool callingJSON output | 262,144 | 86,555 | 259,665 |
Qwen3 VL 30B A3B Thinkingqwen/qwen3-vl-30b-a3b-thinking | Image inputTool callingReasoningJSON output | 262,144 | 100,404 | 346,219 |
Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instruct | Image inputTool callingJSON output | 262,144 | 51,933 | 207,732 |
Qwen3 Coder Flashqwen/qwen3-coder-flash | Tool callingJSON output | 1,000,000 | 67,513 | 337,564 |
Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct | Tool callingJSON output | 262,144 | 31,160 | 380,841 |
Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct | Tool callingJSON output | 262,144 | 51,933 | 207,732 |
Qwen3 32Bqwen/qwen3-32b | Tool callingReasoningJSON output | 131,072 | 27,698 | 96,941 |
Qwen3 Embedding 8Bqwen/qwen3-embedding-8b | Embeddings | 40,960 | 3,462 | — |
Qwen3 Embedding 4Bqwen/qwen3-embedding-4b | Embeddings | 32,768 | 6,924 | — |
Qwen3.7 PlusBatchqwen/qwen3.7-plus:batch | Image inputTool callingReasoningJSON output | 262,144 | 79,630 | 318,522 |
Common questions about the Qwen (Alibaba) API
- How do I reach the Qwen (Alibaba) API from Iran?
- Sign up with your mobile number, top the wallet up in toman and create an sk-up- key. Then, in the official OpenAI SDK, point base_url at https:/
/ api.uttapen.ir/ v1 and set model to the Qwen (Alibaba) model id. No international card, no VPN. - What do Qwen (Alibaba) models cost in toman?
- It depends on the model: the cheapest, Qwen3.7 Flash, is about 72 toman for a 1,000-word request, and the dearest, Qwen3.8 Max Prime, about 7,201 toman. Each model page carries its own exact price, and you are billed for what the request actually used.
- How many Qwen (Alibaba) models are on uttapen?
- 44. 40 support tool calling and 25 accept image input. 2 are embedding models for /v1/
embeddings. The catalogue re-syncs hourly, so a newly released model shows up here on its own.