Qwen3.5 Plus 2026-04-20 pricing and routing profile
Qwen3.5 Plus 2026-04-20 from Qwen (Alibaba) lists at $0.30 per million input tokens and $1.80 per million output tokens, with a 1,000,000-token context window. Prices from OpenRouter's catalogue on 2026-09-28.
Tool callingStructured outputReasoning controlLog probabilities
Cost per 1,000 requests
| Request shape | List cost |
|---|---|
| Classification or routing (600 tokens in, 10 out) | $0.198 |
| Chat reply (2,000 in, 400 out) | $1.32 |
| Retrieval-augmented answer (8,000 in, 500 out) | $3.30 |
Before prompt caching. Try your own shape in the cost calculator.
Can Gimbix route to it first?
Yes. At least one host return token log probabilities for Qwen3.5 Plus 2026-04-20, which is the confidence signal Gimbix uses to let a cheaper model answer first.
Cheaper models that can answer first
Models priced below Qwen3.5 Plus 2026-04-20 that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.
| Model | Input / output per 1M | Cheaper on a chat reply |
|---|---|---|
| Qwen3.5 Plus 2026-02-15 | $0.26 / $1.56 | 13% |
| DeepSeek V3 0324 | $0.29 / $1.14 | 22% |
| Qwen3.5-27B | $0.195 / $1.56 | 23% |
| MiniMax M2.5 | $0.27 / $1.08 | 26% |
| DeepSeek V3.1 | $0.25 / $0.95 | 33% |
| Step 3.7 Flash | $0.20 / $1.15 | 35% |
Questions
How much does Qwen3.5 Plus 2026-04-20 cost?
Qwen3.5 Plus 2026-04-20 lists at $0.30 per million input tokens and $1.80 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $1.32 per 1,000 requests.
What is the context window of Qwen3.5 Plus 2026-04-20?
1,000,000 tokens.
Can a cheaper model replace Qwen3.5 Plus 2026-04-20?
Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Qwen3.5 Plus 2026-04-20 on one half of your requests and make at most three answers worse on the other.