qwen Open weights Vision Reasoning

Qwen3.5-122B-A10B pricing & benchmarks

Released Feb 25, 2026 · served by 5 providers · ranked #49 by intelligence in our index

Input / 1M tokens$0.260
Output / 1M tokens$2.08
Context window262K
Cached input
Intelligence index32.3
Coding index45.7
Agentic index20.7
1M in + 300K out$0.88

What Qwen3.5-122B-A10B is

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...

Providers and prices for Qwen3.5-122B-A10B

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
SiliconFlowcheapest $0.260 $2.08 262K fp8 81.1%
Alibaba $0.260 $2.08 262K 97.2%
DeepInfra $0.290 $2.40 262K fp4 91.7%
AtlasCloud $0.300 $2.40 262K fp8 92.1%
Novita $0.400 $3.20 262K bf16 95.3%

Cheaper models in the same class

Models scoring within 4 points of Qwen3.5-122B-A10B on the Intelligence Index, but with a lower output price.

FAQ

How much does the Qwen3.5-122B-A10B API cost?

$0.260 per 1M input tokens and $2.08 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.88.

Is Qwen3.5-122B-A10B free?

No. It is a paid model starting at $0.260 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Qwen3.5-122B-A10B?

SiliconFlow at $0.260 input / $2.08 output per 1M tokens (fp8 quantization).

Can I self-host Qwen3.5-122B-A10B?

Yes — weights are published as Qwen/Qwen3.5-122B-A10B on Hugging Face, so you can run it on your own hardware.