Qwen · Model
Qwen3.5 397B A17B pricing, context window and specs
Qwen3.5 397B A17B costs $0.55 per million input tokens and $3.50 per million output tokens, and reads up to 262,144 tokens per request. By blended price it is number 10 of Qwen’s 13 current models here, counting from the cheapest.
- Input / 1M
- $0.55
- Output / 1M
- $3.50
- Cached / 1M
- $0.225
- Context
- 262,144
- Max output
- Not published
- Released
- 2026-02-16
Estimate your cost with Qwen3.5 397B A17BCompare all Qwen modelsCount tokens for Qwen3.5 397B A17B
Pricing
Qwen3.5 397B A17B API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.55 | $3.50 |
| Cached input (read) | $0.225 | – |
Output costs 6.4× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 41% of the normal input price.
History
Qwen3.5 397B A17B price history
Price increase, +18% blended
- Input
- from $0.45 to $0.55
- +22%
- Output
- from $3 to $3.50
- +17%
- Cached input
- from $0.22 to $0.225
- +2.3%
Qwen3.5 397B A17B has open weights, so this is the price of OpenRouter’s top-ranked host, which can move when hosts change rather than because Qwen changed its price. Every change across all models is in the AI pricing changes log.
Examples
What Qwen3.5 397B A17B costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.00198 | $60.26 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.00466 | $70.87 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.0186 | $113.15 |
| Document summariser | 8,000 / 600 | 300 | $0.0065 | $59.31 |
Change any number in the cost calculator.
Context
Context window
Qwen3.5 397B A17B accepts up to 262,144 tokens per request, roughly 196,608 English words or 393 pages. That budget is shared between your prompt and the reply, and no separate cap on the reply is published.
Filling the whole window with one prompt costs about $0.14 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
Capabilities
- Image input
- Yes
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- Yes
- Accepts
- text, image, video
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
API
Qwen3.5 397B A17B model ID
- OpenRouter
qwen/qwen3.5-397b-a17b- Open weights
- Qwen/Qwen3.5-397B-A17B
Use the OpenRouter ID when calling it through OpenRouter; Qwen’s own API may name it differently. See the model ID reference for the providers we document.
Qwen
Where Qwen3.5 397B A17B sits in Qwen’s line-up
Ranked by blended price (three parts input to one part output, $1.2875 per 1M for Qwen3.5 397B A17B), it is number 10 of Qwen’s 13 current models here, counting from the cheapest. One step down, Qwen3.6 27B costs $1.04 blended (19% less). One step up, Qwen3.8 2.4T A95B costs $3 (2.3× as much). Unlike Qwen3.5 397B A17B, it doesn’t accept images or video and reads up to 1,048,576 tokens (262,144 here). See every Qwen model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Qwen3.5-9B | $0.10 | $0.15 | 256,000 | 2026-03-10 |
| Qwen3.8 Flash | $0.15 | $0.47 | 1,000,000 | 2026-08-26 |
| Qwen3.8 Omni Flash | $0.15 | $0.47 | 1,000,000 | 2026-09-21 |
| Qwen3 Coder Next | $0.12 | $0.80 | 262,144 | 2026-02-04 |
| Qwen3.6 35B A3B | $0.10 | $0.95 | 262,144 | 2026-04-27 |
| Qwen3 VL 8B Instruct | $0.25 | $0.75 | 262,144 | 2025-10-14 |
| Qwen3.7 Plus | $0.32 | $1.28 | 1,000,000 | 2026-06-03 |
| Qwen3.5-122B-A10B | $0.26 | $2.08 | 262,144 | 2026-02-25 |
| Qwen3.6 27B | $0.32 | $3.20 | 262,144 | 2026-04-27 |
| Qwen3.5 397B A17B (this page) | $0.55 | $3.50 | 262,144 | 2026-02-16 |
| Qwen3.8 2.4T A95B | $2 | $6 | 1,048,576 | 2026-08-12 |
| Qwen3.8 Max (0902) | $2 | $6 | 1,000,000 | 2026-09-03 |
| Qwen3.8 Max Prime | $4 | $12 | 1,000,000 | 2026-09-23 |
Qwen’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.
Save
Cheaper alternatives
- Seed 1.6 FlashByteDance Seed90% cheaper
- Gemma 4 31BGoogle88% cheaper
- GPT-6 LunaOpenAI84% cheaper
- Claude Haiku 5.5Anthropic84% cheaper
- Qwen3.8 Omni FlashQwen82% cheaper
Current models from major providers, one per provider, that keep image input, tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Similarly priced models
- Grok Build 0.1xAI$1 / $2
- Kimi K2.7 CodeMoonshot AI$0.6712 / $3.35
- Seed-2.0-CodeByteDance Seed$0.50 / $3
- Gemini 3.8 FlashGoogle$0.75 / $3.75
- Nemotron 3 UltraNVIDIA$0.60 / $2.40
Current models from other major providers, closest blended price.
FAQ
Qwen3.5 397B A17B questions
How much does Qwen3.5 397B A17B cost?
Qwen3.5 397B A17B costs $0.55 per million input tokens and $3.50 per million output tokens, with cached input at $0.225. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.00223. Use the LLM cost calculator for your own workload.
What is Qwen3.5 397B A17B’s context window?
262,144 tokens, about 196,608 English words or 393 printed pages, shared between your prompt and the reply. No separate limit on the reply is published, so the window is the limit.
Does Qwen3.5 397B A17B support prompt caching and batch requests?
Yes, cached input is billed at $0.225 per million tokens (41% of the normal input price). No batch price is published for it.
What are cheaper alternatives to Qwen3.5 397B A17B?
With the same essentials (image input and tool calling), the cheapest options are Seed 1.6 Flash (90% cheaper), Gemma 4 31B (88% cheaper), GPT-6 Luna (84% cheaper). Cheaper doesn’t mean equivalent, so test them on your own prompts.
What is the API model ID for Qwen3.5 397B A17B?
On OpenRouter it is qwen/qwen3.5-397b-a17b. Qwen’s own API may use a different name, so check its model list before you deploy. Pass the ID as the model value in each request.
Is Qwen3.5 397B A17B open source?
Yes, Qwen3.5 397B A17B has open weights, so you can run it yourself or choose between several hosting providers. The prices here are a typical hosted price.