Qwen API: models and pricing
Pick up to 3 models · pricing, context and capabilities · simulate your product cost
Data updated on November 14, 2026· 230 models
53 Qwen chat models available by API, newest first, with price per million tokens, context and capabilities. Data as of 11/14/2026.
The cheapest Qwen API model is Qwen3.7 Flash ($0.030 input and $0.130 output per million tokens). The newest is Qwen3.8 Max Prime. Prices range from $0.030 to $4.00 per million input tokens. Data as of 11/14/2026.
Input price range
$0.030 – $4.00
per million input tokens
Cheapest model
Qwen3.7 Flash
$0.030 / $0.130
≈ $0.97/month in the example
Newest model
Qwen3.8 Max Prime
$4.00 / $12.00
≈ $108.00/month in the example
Cached input
$0.500 −88 %
per million tokens on Qwen3.8 Max Prime; 23 models with cache price
Prices are input / output in USD per million tokens. Example: 10,000 requests a month of 1,500 input + 400 output tokens.
Qwen vs other AI APIs: the cheapest of each
The cheapest recent model of each provider, next to Qwen3.7 Flash.
| Provider | Model | Input $/1M | Output $/1M | |
|---|---|---|---|---|
| Qwen | Qwen3.7 Flash | $0.030 | $0.130 | |
| DeepSeek | DeepSeek V4.1 Flash 1017 | $0.038 | $0.500 | Compare |
| Gemma 4 26B A4B | $0.068 | $0.225 | Compare | |
| OpenAI | GPT-6 Luna Pro | $0.100 | $0.500 | Compare |
| Anthropic | Claude Haiku 5.5 | $0.100 | $0.500 | Compare |
| Mistral | Ministral 3 3B 2512 | $0.100 | $0.100 | Compare |
| Moonshot | Kimi K3 | $0.192 | $16.00 | Compare |
| xAI | Grok Build 0.1 | $1.00 | $2.00 | Compare |
| # | Model | Provider | Input $/1M | Output $/1M | Context | Capabilities | Released |
|---|---|---|---|---|---|---|---|
| 1 | Qwen3.8 Max Prime | Qwen | $4.00 | $12.00 | 1 M | 09/23/2026 | |
| 2 | Qwen3.8 Omni Flash | Qwen | $0.150 | $0.470 | 1 M | 09/17/2026 | |
| 3 | Qwen3.8 Max (0902) | Qwen | $2.00 | $6.00 | 1 M | 09/03/2026 | |
| 4 | Qwen3.8 Flash | Qwen | $0.150 | $0.470 | 1 M | 08/26/2026 | |
| 5 | Qwen3.8 27B | Qwen | $0.150 | $1.88 | 1 M | 08/14/2026 | |
| 6 | Qwen3.8 2.4T A95B | Qwen | $2.00 | $6.00 | 1 M | 08/12/2026 | |
| 7 | Qwen3.7 Flash | Qwen | $0.030 | $0.130 | 1 M | 07/15/2026 | |
| 8 | Qwen3.7 Plus | Qwen | $0.320 | $1.28 | 1 M | 06/02/2026 | |
| 9 | Qwen3.7 Max | Qwen | $1.48 | $4.43 | 1 M | 05/21/2026 | |
| 10 | Qwen3.6 Flash | Qwen | $0.188 | $1.13 | 1 M | 04/27/2026 | |
| 11 | Qwen3.6 27B | Qwen | $0.320 | $3.20 | 262 K | 04/22/2026 | |
| 12 | Qwen3.6 Max Preview | Qwen | $1.03 | $6.16 | 262 K | 04/20/2026 | |
| 13 | Qwen3.6 35B A3B | Qwen | $0.100 | $0.900 | 262 K | 04/17/2026 | |
| 14 | Qwen3.6 Plus | Qwen | $0.325 | $1.95 | 1 M | 04/02/2026 | |
| 15 | Qwen3.5-Flash | Qwen | $0.065 | $0.260 | 1 M | 02/25/2026 | |
| 16 | Qwen3.5-35B-A3B | Qwen | $0.140 | $1.00 | 262 K | 02/23/2026 | |
| 17 | Qwen3.5-9B | Qwen | $0.153 | $0.225 | 262 K | 02/23/2026 | |
| 18 | Qwen3.5-27B | Qwen | $0.260 | $2.60 | 262 K | 02/23/2026 | |
| 19 | Qwen3.5-122B-A10B | Qwen | $0.260 | $2.08 | 262 K | 02/23/2026 | |
| 20 | Qwen3.5 Plus 2026-04-20 | Qwen | $0.300 | $1.80 | 1 M | 02/16/2026 | |
| 21 | Qwen3.5 Plus 2026-02-15 | Qwen | $0.260 | $1.56 | 1 M | 02/16/2026 | |
| 22 | Qwen3.5 397B A17B | Qwen | $0.600 | $3.60 | 262 K | 02/16/2026 | |
| 23 | Qwen3 VL 30B A3B Thinking | Qwen | $0.290 | $1.00 | 262 K | 02/09/2026 | |
| 24 | Qwen3 Max Thinking | Qwen | $0.780 | $3.90 | 262 K | 02/09/2026 | |
| 25 | Qwen3 30B A3B Thinking 2507 | Qwen | $0.200 | $2.40 | 82 K | 02/04/2026 | |
| 26 | Qwen3 Coder Next | Qwen | $0.120 | $0.800 | 262 K | 02/03/2026 | |
| 27 | Qwen3 Max | Qwen | $0.780 | $3.90 | 262 K | 01/23/2026 | |
| 28 | Qwen3 VL 32B Instruct | Qwen | $0.104 | $0.416 | 131 K | 10/23/2025 | |
| 29 | Qwen3 VL 8B Instruct | Qwen | $0.250 | $0.750 | 262 K | 10/14/2025 | |
| 30 | Qwen3 VL 8B Thinking | Qwen | $0.180 | $2.10 | 131 K | 10/14/2025 | |
| 31 | Qwen3 VL 30B A3B Instruct | Qwen | $0.150 | $0.600 | 262 K | 10/04/2025 | |
| 32 | Qwen3 VL 235B A22B Instruct | Qwen | $0.210 | $1.90 | 262 K | 09/23/2025 | |
| 33 | Qwen3 VL 235B A22B Thinking | Qwen | $0.400 | $4.00 | 131 K | 09/15/2025 | |
| 34 | Qwen Plus 0728 | Qwen | $0.260 | $0.780 | 1 M | 09/08/2025 | |
| 35 | Qwen3 Next 80B A3B Instruct | Qwen | $0.090 | $1.10 | 262 K | 09/01/2025 | |
| 36 | Qwen3 Next 80B A3B Thinking | Qwen | $0.150 | $1.20 | 262 K | 09/01/2025 | |
| 37 | Qwen3 30B A3B Instruct 2507 | Qwen | $0.100 | $0.300 | 262 K | 07/28/2025 | |
| 38 | Qwen3 Coder Flash | Qwen | $0.195 | $0.975 | 1 M | 07/28/2025 | |
| 39 | Qwen3 235B A22B Thinking 2507 | Qwen | $0.450 | $3.50 | 128 K | 07/25/2025 | |
| 40 | Qwen3 Coder Plus | Qwen | $0.650 | $3.25 | 1 M | 07/23/2025 | |
| 41 | Qwen3 Coder 480B A35B | Qwen | $0.300 | $1.00 | 262 K | 07/22/2025 | |
| 42 | Qwen3 235B A22B Instruct 2507 | Qwen | $0.140 | $0.800 | 262 K | 07/21/2025 | |
| 43 | Qwen3 30B A3B | Qwen | $0.120 | $0.500 | 41 K | 04/28/2025 | |
| 44 | Qwen3 32B | Qwen | $0.080 | $0.280 | 131 K | 04/01/2025 | |
| 45 | Qwen3 235B A22B | Qwen | $0.455 | $1.82 | 131 K | 04/01/2025 | |
| 46 | Qwen3 Coder 30B A3B Instruct | Qwen | $0.150 | $0.600 | 262 K | 04/01/2025 | |
| 47 | Qwen3 14B | Qwen | $0.120 | $0.240 | 41 K | 04/01/2025 | |
| 48 | Qwen3 8B | Qwen | $0.117 | $0.455 | 131 K | 04/01/2025 | |
| 49 | Qwen2.5 VL 72B Instruct | Qwen | $0.800 | $1.00 | 128 K | 01/26/2025 | |
| 50 | Qwen2.5 Coder 32B Instruct | Qwen | $0.660 | $1.00 | 33 K | 11/11/2024 | |
| 51 | Qwen2.5 7B Instruct | Qwen | $0.100 | $0.200 | 33 K | 10/16/2024 | |
| 52 | Qwen2.5 72B Instruct | Qwen | $0.360 | $0.400 | 33 K | 09/19/2024 | |
| 53 | Qwen-Plus | Qwen | $0.260 | $0.780 | 1 M | 01/25/2024 |
More free tools
See allFrequently asked questions
How much does the Qwen API cost?
It depends on the model: from $0.030 to $4.00 per million input tokens. The cheapest is Qwen3.7 Flash ($0.030 / $0.130); the newest is Qwen3.8 Max Prime ($4.00 / $12.00). Data as of 11/14/2026.
Is the Qwen API free?
No: the Qwen API is pay-as-you-go, billed per million tokens. The cheapest model, Qwen3.7 Flash, costs $0.030 per million input tokens and $0.130 per million output tokens, so light use costs cents. Any free credits depend on Qwen's own offer.
Does the Qwen API charge less for cached input?
Yes, on 23 of its 53 models. For example, Qwen3.8 Max Prime charges $0.500 per million cached input tokens instead of $4.00: 88% less. The cache applies when you resend the same beginning of a prompt, like a long system prompt or a document.
How much does the Qwen API cost per month?
For 10,000 requests a month of 1,500 input tokens and 400 output tokens: Qwen3.7 Flash costs about $0.97 and Qwen3.8 Max Prime about $108.00. Each model's page has a calculator for your own numbers.
How many Qwen models are available by API?
53 chat models in the catalog, as of 11/14/2026. Each one has its own sheet with pricing, context and capabilities.
Where do the prices come from and how often are they updated?
From the public catalogs of OpenRouter, models.dev and LiteLLM, which publish each provider's list prices. They sync once a day and the last update date is shown above the comparison.
What does price per million tokens mean?
It is what the provider charges per million tokens you send (input) or the model generates (output). A token is roughly 4 characters. Output almost always costs more than input.
Sources: OpenRouter, models.dev and LiteLLM. Prices in USD per million tokens, list price, no volume discounts. Prompt tokens are an estimate; each provider's tokenizer may differ.