Qwen API models ranked by price (Nov 2026)
Every current Alibaba Qwen text model on OpenRouter, from the cheapest up.
Cheapest today: Qwen3.7 Flash from Alibaba (Qwen) at $0.03 per million input tokens and $0.13 per million output tokens. The spread to #22 (Qwen3.8 Max Prime) is 109x on a blended basis.
Data updated 2026-11-11 - 22 models - source: public OpenRouter model list, refreshed daily. Prices in USD per million tokens.
| # | Model | Input | Output | Blended | Batch | Cached in | Context | Max out | Features | 30-day range (out) |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Qwen3.7 Flash | $0.03 | $0.13 | $0.055 | - | $0.006 | 1M | 66K | reasoning, tools, vision, video | stable |
| 2 | Qwen3.5-Flash | $0.065 | $0.26 | $0.114 | - | - | 1M | 66K | reasoning, tools, vision, video | stable |
| 3 | Qwen3.5-9B | $0.17 | $0.25 | $0.19 | - | - | 262K | 236K | reasoning, tools, vision, video | $0.13 - $0.25 * |
| 4 | Qwen3.8 Omni Flash | $0.15 | $0.47 | $0.23 | - | $0.016 | 1M | 131K | reasoning, tools, vision, audio, video | stable |
| 5 | Qwen3.8 Flash | $0.15 | $0.47 | $0.23 | - | $0.016 | 1M | 131K | reasoning, tools, vision, video | stable |
| 6 | Qwen3 Coder Next | $0.12 | $0.8 | $0.29 | - | $0.07 | 262K | 236K | tools | stable |
| 7 | Qwen3.6 35B A3B | $0.1 | $0.9 | $0.3 | - | $0.025 | 262K | 236K | reasoning, tools, vision, video | $0.9 - $1 * |
| 8 | Qwen3.5-35B-A3B | $0.14 | $1 | $0.355 | - | $0.05 | 262K | 82K | reasoning, tools, vision, video | $0.75 - $1 * |
| 9 | Qwen3.6 Flash | $0.188 | $1.13 | $0.422 | - | - | 1M | 66K | reasoning, tools, vision, video | stable |
| 10 | Qwen3.7 Plus | $0.32 | $1.28 | $0.56 | $0.23 / $0.92 | $0.064 | 1M | 131K | reasoning, tools, vision | stable |
| 11 | Qwen3.8 27B | $0.15 | $1.88 | $0.581 | $0.16 / $2 | $0.0375 | 1.05M | 236K | reasoning, tools, vision, video | $1.25 - $2.5 * |
| 12 | Qwen3.5 Plus 2026-02-15 | $0.26 | $1.56 | $0.585 | - | - | 1M | 66K | reasoning, tools, vision, video | stable |
| 13 | Qwen3.5 Plus 2026-04-20 | $0.3 | $1.8 | $0.675 | - | - | 1M | 66K | reasoning, tools, vision, video | stable |
| 14 | Qwen3.5-122B-A10B | $0.26 | $2.08 | $0.715 | - | - | 262K | 66K | reasoning, tools, vision, video | $2.08 - $3.2 * |
| 15 | Qwen3.6 Plus | $0.325 | $1.95 | $0.731 | - | - | 1M | 66K | reasoning, tools, vision, video | stable |
| 16 | Qwen3.5-27B | $0.26 | $2.6 | $0.845 | - | - | 262K | 82K | reasoning, tools, vision, video | $1.56 - $2.6 * |
| 17 | Qwen3.6 27B | $0.32 | $3.2 | $1.04 | - | - | 262K | 82K | reasoning, tools, vision, video | $2 - $3.2 * |
| 18 | Qwen3.5 397B A17B | $0.6 | $3.6 | $1.35 | - | $0.12 | 262K | 64K | reasoning, tools, vision, video | $2.34 - $3.6 * |
| 19 | Qwen3.7 Max | $1.48 | $4.43 | $2.21 | - | $0.295 | 1M | 131K | reasoning, tools | stable |
| 20 | Qwen3.8 2.4T A95B | $2 | $6 | $3 | - | $0.25 | 1.05M | 131K | reasoning, tools | stable |
| 21 | Qwen3.8 Max (0902) | $2 | $6 | $3 | $1.15 / $3.45 | $0.25 | 1M | 131K | reasoning, tools, vision, video | stable |
| 22 | Qwen3.8 Max Prime | $4 | $12 | $6 | - | $0.5 | 1M | 131K | reasoning, tools, vision, video | stable |
Blended = (3 x input + output) / 4. Context and max output in tokens (K = thousand, M = million). * Volatile: the output price moved by 30% or more in the last 30 days, usually because OpenRouter routes the model to a different provider.
Head-to-head comparisons for models in this list
Other lists
- Cheapest LLM APIs
- Cheapest 1M-context models
- Cheapest reasoning models
- Cheapest vision models
- Largest context windows
- Free LLM APIs
- OpenAI models by price
- Claude models by price
- Gemini models by price
- DeepSeek models by price
- Grok models by price
How we rank
The list includes text models from established vendors that OpenRouter added in the last 12 months, with at least a 32,000-token window. Batch, preview, experimental and image or audio generation variants are left out; batch prices appear in their own column on vendor pages. Prices are the current per-token list rates; for open-weight models served by several hosts, OpenRouter shows the price of the provider it currently routes to, which is why some of them move often. Need a full cost estimate? Use the AI cost calculator or browse the full model atlas.
Frequently asked questions
What is the cheapest Qwen model?
As of 11 Nov 2026, Qwen3.7 Flash from Alibaba (Qwen) is the cheapest in this list at $0.03 per million input tokens and $0.13 per million output tokens (a blended $0.055). Next is Qwen3.5-Flash at $0.065 / $0.26.
What is the most expensive Alibaba (Qwen) model in this list?
Qwen3.8 Max Prime at $4 per million input tokens and $12 per million output tokens.
How is the ranking calculated?
Models are sorted by a blended price that assumes three input tokens for every output token, the same convention Artificial Analysis uses. If your workload writes more than it reads, look at the output column instead.
How often is this list updated?
Every day. Prices, context windows and features come from the public OpenRouter model list, refreshed each morning; the date at the top of the page shows the last update.
// follow
New tests and price changes, straight to your feed reader
Free RSS, no account and no email needed.
Follow Quantslant →