Provider
Qwen API pricing: every model compared
Qwen offers 53 models through its API in our data, priced from $0.03 to $4 per million input tokens. The newest is Qwen3.8 Max Prime, first listed on 2026-09-23.
- Models
- 53
- Cheapest input
- $0.03
- Priciest input
- $4
- Largest context
- 1,048,576
- With caching
- 19 of 53
- Open weights
- 35 of 53
Cheapest
Qwen3.7 FlashQwen$0.03 in · $0.13 outLargest context
Qwen3.8 2.4T A95BQwen1,048,576 tokensLine-up
Every Qwen model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Qwen3.8 Max Prime | $4 | $12 | 1,000,000 | 2026-09-23 |
| Qwen3.8 Omni Flash | $0.15 | $0.47 | 1,000,000 | 2026-09-21 |
| Qwen3.8 Max (0902) | $2 | $6 | 1,000,000 | 2026-09-03 |
| Qwen3.8 Flash | $0.15 | $0.47 | 1,000,000 | 2026-08-26 |
| Qwen3.8 27B | $0.425 | $2.55 | 1,000,000 | 2026-08-14 |
| Qwen3.8 2.4T A95B | $2 | $6 | 1,048,576 | 2026-08-12 |
| Qwen3.7 Flash | $0.03 | $0.13 | 1,000,000 | 2026-07-27 |
| Qwen3.7 Plus | $0.32 | $1.28 | 1,000,000 | 2026-06-03 |
| Qwen3.7 Max | $1.475 | $4.425 | 1,000,000 | 2026-05-21 |
| Qwen3.5 Plus 2026-04-20 | $0.30 | $1.80 | 1,000,000 | 2026-04-27 |
| Qwen3.6 27B | $0.45 | $2.70 | 262,144 | 2026-04-27 |
| Qwen3.6 35B A3B | $0.15 | $1 | 262,144 | 2026-04-27 |
| Qwen3.6 Flash | $0.1875 | $1.125 | 1,000,000 | 2026-04-27 |
| Qwen3.6 Max Preview | $1.027 | $6.162 | 262,144 | 2026-04-27 |
| Qwen3.6 Plus | $0.325 | $1.95 | 1,000,000 | 2026-04-02 |
| Qwen3.5-9B | $0.10 | $0.15 | 256,000 | 2026-03-10 |
| Qwen3.5-122B-A10B | $0.26 | $2.08 | 262,144 | 2026-02-25 |
| Qwen3.5-27B | $0.26 | $2.60 | 262,144 | 2026-02-25 |
| Qwen3.5-35B-A3B | $0.1625 | $1.30 | 262,144 | 2026-02-25 |
| Qwen3.5-Flash | $0.065 | $0.26 | 1,000,000 | 2026-02-25 |
| Qwen3.5 397B A17B | $0.55 | $3.50 | 262,144 | 2026-02-16 |
| Qwen3.5 Plus 2026-02-15 | $0.26 | $1.56 | 1,000,000 | 2026-02-16 |
| Qwen3 Max Thinking | $0.78 | $3.90 | 262,144 | 2026-02-09 |
| Qwen3 Coder Next | $0.12 | $0.80 | 262,144 | 2026-02-04 |
| Qwen3 VL 32B Instruct | $0.104 | $0.416 | 131,072 | 2025-10-23 |
| Qwen3 VL 8B Instruct | $0.117 | $0.455 | 131,072 | 2025-10-14 |
| Qwen3 VL 8B Thinking | $0.18 | $2.10 | 131,072 | 2025-10-14 |
| Qwen3 VL 30B A3B Instruct | $0.15 | $0.60 | 262,144 | 2025-10-06 |
| Qwen3 VL 30B A3B Thinking | $0.20 | $2.40 | 131,072 | 2025-10-06 |
| Qwen3 Coder Plus | $0.65 | $3.25 | 1,000,000 | 2025-09-23 |
| Qwen3 Max | $0.78 | $3.90 | 262,144 | 2025-09-23 |
| Qwen3 VL 235B A22B Instruct | $0.21 | $1.90 | 131,072 | 2025-09-23 |
| Qwen3 VL 235B A22B Thinking | $0.40 | $4 | 131,072 | 2025-09-23 |
| Qwen3 Coder Flash | $0.195 | $0.975 | 1,000,000 | 2025-09-17 |
| Qwen3 Next 80B A3B Instruct | $0.09 | $1.10 | 262,144 | 2025-09-11 |
| Qwen3 Next 80B A3B Thinking | $0.15 | $1.20 | 131,072 | 2025-09-11 |
| Qwen Plus 0728 | $0.26 | $0.78 | 1,000,000 | 2025-09-08 |
| Qwen3 30B A3B Thinking 2507 | $0.20 | $2.40 | 81,920 | 2025-08-28 |
| Qwen3 Coder 30B A3B Instruct | $0.07 | $0.28 | 262,144 | 2025-07-31 |
| Qwen3 30B A3B Instruct 2507 | $0.10 | $0.30 | 262,144 | 2025-07-29 |
| Qwen3 235B A22B Thinking 2507 | $0.23 | $2.30 | 131,072 | 2025-07-25 |
| Qwen3 Coder 480B A35B | $0.30 | $1 | 262,144 | 2025-07-23 |
| Qwen3 235B A22B Instruct 2507 | $0.09 | $0.55 | 262,144 | 2025-07-21 |
| Qwen3 14B | $0.12 | $0.24 | 40,960 | 2025-04-28 |
| Qwen3 235B A22B | $0.455 | $1.82 | 131,072 | 2025-04-28 |
| Qwen3 30B A3B | $0.12 | $0.50 | 40,960 | 2025-04-28 |
| Qwen3 32B | $0.08 | $0.28 | 40,960 | 2025-04-28 |
| Qwen3 8B | $0.117 | $0.455 | 131,072 | 2025-04-28 |
| Qwen-Plus | $0.26 | $0.78 | 1,000,000 | 2025-02-01 |
| Qwen2.5 VL 72B Instruct | $0.80 | $1 | 128,000 | 2025-02-01 |
| Qwen2.5 Coder 32B Instruct | $0.66 | $1 | 32,768 | 2024-11-11 |
| Qwen2.5 7B Instruct | $0.10 | $0.20 | 32,768 | 2024-10-16 |
| Qwen2.5 72B Instruct | $0.36 | $0.40 | 32,768 | 2024-09-19 |
Prices in US dollars per 1M tokens, newest first. Release dates are when our source first listed the model.
Overview
Qwen’s pricing at a glance
The spread between Qwen’s cheapest and most expensive model is large: Qwen3.8 Max Prime costs 133× more per input token than Qwen3.7 Flash. Picking the smallest model that does the job well is usually the biggest saving available, ahead of any discount.
19 of 53 of the line-up has a cached-input price, which helps chatbots and agents that resend the same instructions. No batch prices are published in our data. 27 of 53 accept images as input.
FAQ
Qwen API questions
How much does the Qwen API cost?
Qwen's 53 models range from $0.03 to $4 per million input tokens, and output costs more than input on almost every model. The exact bill depends on your token volumes, which you can estimate in the LLM cost calculator.
What is Qwen's cheapest model?
By blended price (three parts input to one part output) it is Qwen3.7 Flash, at $0.03 input and $0.13 output per million tokens. The most expensive is Qwen3.8 Max Prime.
Which Qwen model has the largest context window?
Qwen3.8 2.4T A95B, with 1,048,576 tokens per request.
Does Qwen offer prompt caching or batch discounts?
In our data, 19 of 53 of Qwen's models have a published cached-input price and none have a published batch price. Both can cut costs substantially for repeated prompts or work that can wait.