Qwen3.6 Max Preview pricing, context window and limits
Qwen3.6 Max Preview costs $1.32 per million input tokens and $7.9 per million output tokens at Alibaba Qwen list price. It accepts up to 245,800 tokens of context and returns up to 65,536 tokens.
- Model id
qwen3.6-max-preview - Snapshot
What does Qwen3.6 Max Preview cost?
| Input | $1.32 |
|---|---|
| Output | $7.9 |
| Cached input (read) | $0.132 |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Qwen3.6 Max Preview read and write?
| Context window | 245,800 |
|---|---|
| Max output | 65,536 |
What can Qwen3.6 Max Preview do?
| Vision (image input) | No |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | Yes |
| Input | text |
| Output | text |
What does a request to Qwen3.6 Max Preview cost?
| A typical request: 1,000 tokens in, 500 out | $0.0053 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.021 |
| 1,000 typical requests | $5.27 |
| 1 million tokens in and 1 million out | $9.22 |
Input read from the provider's prompt cache costs $0.132 per million tokens instead of $1.32, 90% less. A request that repeats a 1,000-token prompt from the cache costs $0.0041 instead of $0.0053.
Among 64 Alibaba Qwen models with a published price, Qwen3.6 Max Preview is the 60th cheapest by input price. Its context window is the 23rd largest of 64. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Qwen3.6 Max Preview through DVARA?
Configure the qwen provider in the DVARA LLM Gateway and send the model id qwen3.6-max-preview. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Alibaba Qwen models are there?
- Qwen3.6 Flash$0.1875 in · $1.125 out · 1M context
- Qwen3.6 Plus$0.5 in · $3 out · 1M context
- Qwen3.5 Plus$0.115 in · $0.688 out · 1M context
- Qwen3.7 Flash$0.0296 in · $0.1185 out · 1M context
- Qwen3.5 Flash$0.029 in · $0.287 out · 1M context
- Qwen3.7 Max$2.5 in · $7.5 out · 1M context
- Qwen3.5 397B-A17B$0.172 in · $1.032 out · 262K context
- Qwen3.7 Plus$0.5 in · $3 out · 1M context
- Qwen3-VL Plus$0.1434 in · $1.4335 out · 262K context
- Qwen3.8 Flash$0.1187 in · $0.4007 out · 1M context
- Qwen3-VL 30B-A3B$0.108 in · $0.431 out · 131K context
- Qwen3.8 Max$1.7774 in · $5.3323 out · 1M context
Which models from other providers are similar to Qwen3.6 Max Preview?
These are the closest in context window and input price, one per provider.
- Mistral Medium 3.5Mistral AI · $1.5 in · $7.5 out · 262K context
- GLM-5.1Zhipu GLM · $1.4 in · $4.4 out · 200K context
- Grok Build 0.1xAI Grok · $1 in · $2 out · 256K context
- Claude Haiku 4.5 (AU)Amazon Bedrock · $1.1 in · $5.5 out · 200K context
- o3-miniOpenAI · $1.1 in · $4.4 out · 200K context