Qwen3.5-122B-A10B pricing and routing profile
Qwen3.5-122B-A10B from Qwen (Alibaba) lists at $0.26 per million input tokens and $2.08 per million output tokens, with a 262,144-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) | $0.177 |
| Chat reply (2,000 in, 400 out) | $1.35 |
| Retrieval-augmented answer (8,000 in, 500 out) | $3.12 |
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 Qwen3.5-122B-A10B, which is the confidence signal Gimbix uses to let a cheaper model answer first.
Cheaper models that can answer first
Models priced below Qwen3.5-122B-A10B 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 VL 235B A22B Instruct | $0.21 / $1.90 | 13% |
| Qwen3.5-27B | $0.195 / $1.56 | 25% |
| DeepSeek V3.1 | $0.25 / $0.95 | 35% |
| Step 3.7 Flash | $0.20 / $1.15 | 36% |
| Qwen3.5-35B-A3B | $0.163 / $1.30 | 38% |
| Qwen3.6 Flash | $0.188 / $1.13 | 39% |
Questions
How much does Qwen3.5-122B-A10B cost?
Qwen3.5-122B-A10B lists at $0.26 per million input tokens and $2.08 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 $1.35 per 1,000 requests.
What is the context window of Qwen3.5-122B-A10B?
262,144 tokens.
Can a cheaper model replace Qwen3.5-122B-A10B?
Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Qwen3.5-122B-A10B on one half of your requests and make at most three answers worse on the other.