Qwen3.5 397B-A17B pricing, context window and limits
Qwen3.5 397B-A17B costs $0.172 per million input tokens and $1.032 per million output tokens at Alibaba Qwen list price. It accepts up to 262,144 tokens of context and returns up to 65,536 tokens.
- Model id
qwen3.5-397b-a17b - Snapshot
What does Qwen3.5 397B-A17B cost?
| Input | $0.172 |
|---|---|
| Output | $1.032 |
| Cached input (read) | — |
| Cache write | — |
| Reasoning | $1.032 |
US dollars per million tokens. A dash means no price is published.
How much can Qwen3.5 397B-A17B read and write?
| Context window | 262,144 |
|---|---|
| Max output | 65,536 |
What can Qwen3.5 397B-A17B do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | No |
| Reasoning | Yes |
| Input | text, image, video |
| Output | text |
What does a request to Qwen3.5 397B-A17B cost?
| A typical request: 1,000 tokens in, 500 out | $0.00069 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.0028 |
| 1,000 typical requests | $0.69 |
| 1 million tokens in and 1 million out | $1.2 |
Among 64 Alibaba Qwen models with a published price, Qwen3.5 397B-A17B is the 33rd cheapest by input price. Its context window is the 18th largest of 64. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Qwen3.5 397B-A17B through DVARA?
Configure the qwen provider in the DVARA LLM Gateway and send the model id qwen3.5-397b-a17b. DVARA, the AI governance platform, 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 is counted as costing nothing. Every cost record says which price it used.
What should I check before relying on this data?
The weekly review marked this entry. A person saw each mark and kept the model listed.
- The provider charges more above 200K tokens of input; the table shows the base price.
Which other Alibaba Qwen models are there?
- Qwen3.5 Flash$0.029 in · $0.287 out · 1M context
- Qwen3.5 Plus$0.115 in · $0.688 out · 1M context
- Qwen3-VL Plus$0.1434 in · $1.4335 out · 262K context
- Qwen3-VL 30B-A3B$0.108 in · $0.431 out · 131K context
- Qwen3-VL 235B-A22B$0.2867 in · $1.1468 out · 131K context
- Qwen3.6 Flash$0.1875 in · $1.125 out · 1M context
- Qwen3-Omni Flash Realtime$0.23 in · $0.918 out · 66K context
- Qwen3.6 Max Preview$1.32 in · $7.9 out · 246K context
- Qwen3-Omni Flash$0.058 in · $0.23 out · 66K context
- Qwen3.6 Plus$0.5 in · $3 out · 1M context
- Qwen3-Next 80B-A3B (Thinking)$0.144 in · $1.434 out · 131K context
- Qwen3.7 Flash$0.0296 in · $0.1185 out · 1M context
Which models from other providers are similar to Qwen3.5 397B-A17B?
These are the closest in context window and input price, one per provider.
- NVIDIA Nemotron 3 Super 120B A12BAmazon Bedrock · $0.15 in · $0.65 out · 262K context
- Mistral Small 4Mistral AI · $0.15 in · $0.6 out · 256K context
- GPT-5.4 nanoOpenAI · $0.2 in · $1.25 out · 400K context
- GPT OSS 120BGroq · $0.15 in · $0.6 out · 131K context
- GLM-4.5-AirZhipu GLM · $0.2 in · $1.1 out · 131K context