token.app › Alibaba › Qwen3.5-122B-A10B

Qwen3.5-122B-A10B pricing & benchmarks

Qwen3.5-122B-A10B is available from Alibaba at $0.290 per million input tokens and $2.40 per million output tokens ($0.817 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$0.290
Output$2.40
Blended (3:1)$0.817
Specification
qwen/qwen3.5-122b-a10b
Context window262K
Max output82K
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
5 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.
HostBlended $/1MIn / OutContextWeightsUptime 24h
SiliconFlow $0.715 $0.260 / $2.08 262K fp8 88.3%
Alibaba $0.715 $0.260 / $2.08 262K fp8 99.9%
DeepInfra $0.817 $0.290 / $2.40 262K fp4 99.0%
AtlasCloud $0.825 $0.300 / $2.40 262K fp8 98.2%
Novita $1.10 $0.400 / $3.20 262K bf16 99.2%
Host prices and uptime from OpenRouter, synced 2026-08-08. 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
Qwen3.5-122B-A10B vs DeepSeek V4 Flash 0731 Qwen3.5-122B-A10B vs Claude Opus 5 Qwen3.5-122B-A10B vs Gemini 3.6 Flash Qwen3.5-122B-A10B vs Kimi K3 Qwen3.5-122B-A10B vs GPT-5.6 Luna Qwen3.5-122B-A10B vs GPT-5.6 Terra Qwen3.5-122B-A10B vs GPT-5.6 Sol Qwen3.5-122B-A10B vs Grok 4.5
FAQ
How much does Qwen3.5-122B-A10B cost?
Qwen3.5-122B-A10B costs $0.290 per million input tokens and $2.40 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.817 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 81,920 output tokens.