Qwen3.5-122B-A10B pricing & benchmarks
Qwen3.5-122B-A10B is available from Alibaba at $0.400 per million input tokens and $3.20 per million output tokens ($1.10 blended at 3:1). It accepts up to 262,144 tokens of context. The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...
Pricing
Per million tokens · OpenRouter
Input$0.400
Output$3.20
Blended (3:1)$1.10
Specification
qwen/qwen3.5-122b-a10b
Context window262K
Max output66K
ReleasedFeb 2026
LicenceOpen weights
Modalitiesin:text, in:image, in:video, out:text
No independently-run benchmark scores are published for Qwen3.5-122B-A10B yet. We show nothing rather than reprinting an unverified figure.
Where to run Qwen3.5-122B-A10B
4 hosts · 1.5× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| SiliconFlow | $0.715 | $0.260 / $2.08 | 262K | fp8 | 98.2% |
| Alibaba | $0.715 | $0.260 / $2.08 | 262K | — | 100.0% |
| AtlasCloud | $0.825 | $0.300 / $2.40 | 262K | fp8 | 99.6% |
| Novita | $1.10 | $0.400 / $3.20 | 262K | bf16 | 100.0% |
Host prices and uptime from OpenRouter, synced 2026-10-22. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Qwen3.5-122B-A10B
FAQ
How much does Qwen3.5-122B-A10B cost?
Qwen3.5-122B-A10B costs $0.400 per million input tokens and $3.20 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $1.10 per million tokens.
What is Qwen3.5-122B-A10B's context window?
Qwen3.5-122B-A10B accepts up to 262,144 tokens of context, and can generate up to 65,536 output tokens.