Qwen 3.5 122B A10B
Qwen 3.5 122B A10BRankingin thinking mode?
Alternatives?
CheaperGPT-6.1 Solmedium×3.1-34%$0.21Remove unsupported parameters+5BetterGPT-6 Lunalow+38%-99%$0.005Function calling only with none · Chat Completions+3OpenQwen3.8 Flashthinking×2.6+15%$0.37Memory (4-bit): 75 GB → 108 GB+6
CheaperMiMo v2.6 ProthinkingOpen×3-59%$0.13Memory (4-bit): 75 GB → 615 GB+4
CheaperDeepSeek V4.1 Flash 1017maxOpen×2.9-19%$0.26Memory (4-bit): 75 GB → 458 GB+5GPT-6.1 Solmedium×3.1-34%$0.21Remove unsupported parameters+5MiMo v2.6 ProthinkingOpen×3-59%$0.13Memory (4-bit): 75 GB → 615 GB+4DeepSeek V4.1 Flash 1017maxOpen×2.9-19%$0.26Memory (4-bit): 75 GB → 458 GB+5
Claude Haiku 5.5max×2.8-34%$0.21Remove sampling parameters+5
MiniMax M3.1 Flashthinking×2.7-32%$0.22Complete model response must be appendedGPT-6 Lunalow+38%-99%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow+35%-97%$0.01MiMo v2.5thinkingOpen+40%-94%$0.019Memory (4-bit): 75 GB → 186 GBClaude Haiku 5.5low+89%-92%$0.024Remove sampling parameters+5MiMo v2.5 ProthinkingOpen+67%-83%$0.054Memory (4-bit): 75 GB → 614 GB+1Qwen3.8 FlashthinkingOpen×2.6+15%$0.37Memory (4-bit): 75 GB → 108 GB+6MiMo v2.6 FlashthinkingOpen×2.4-81%$0.062Memory (4-bit): 75 GB → 186 GB+4Qwen3.8 27BxhighOpen×2.2+210%$1.01max_tokens range · QwenCloud+4
Nemotron 3.5 Super VLOpen+70%-42%$0.19TInkling SmallthinkingOpen+65%-72%$0.089Context: 262K → 256K+2Qwen3.8 Max (0902)thinking×2.9+1,565%$5.41Qwen3.8 2.4T A95BthinkingOpen×2.6+564%$2.16Memory (4-bit): 75 GB → 1,468 GB+6Qwen3.8 FlashthinkingOpen×2.6+15%$0.37Memory (4-bit): 75 GB → 108 GB+6Qwen3.7 Maxthinking+89%+253%$1.15No image inputQwen3.6 Max Previewthinking+82%—$1.30 / $7.80No image input+1Qwen3.8 27BmediumOpen+77%+249%$1.13max_tokens range · QwenCloud+4Qwen3.6 Plusthinking+73%—$0.50 / $3Qwen3.7 Plusthinking+62%-33%$0.22All Alibaba (Qwen) models →Run it yourself
estimateBenchmarks
all categoriesFAQ
How much does Qwen 3.5 122B A10B cost?›
$0.40 per 1M input tokens and $3.20 per 1M output tokens; cheapest via lab-qwen at $0.12 / $0.92. A typical benchmark task costs about $0.32 at default effort.
Is Qwen 3.5 122B A10B free to use?›
There is no free API; the cheapest paid price is $0.12 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Qwen 3.5 122B A10B, and what is it best at?›
#100 of 334 in Chat & Knowledge, #75 of 132 in Coding, #82 of 133 in Agents & Tool Use, #93 of 195 in Writing & Language, #51 of 124 in Vision & Documents. Strongest at: Tool calling, Science, Instructions.
Is Qwen 3.5 122B A10B better than Qwen3.6 35B A3B?›
On AA Intelligence Index 4.3.2, Qwen 3.5 122B A10B scores 17.7 vs 18.2 — about the same. It is 32% cheaper per task.
How can I use Qwen 3.5 122B A10B?›
Through the API of Alibaba, AtlasCloud, DeepInfra, Novita, SiliconFlow.
What is the context window of Qwen 3.5 122B A10B?›
262K tokens, with up to 66K output tokens.
When was Qwen 3.5 122B A10B released? Is there a newer version?›
Released 2026-02-23. It is the current version in its line.
Is Qwen 3.5 122B A10B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Qwen 3.5 122B A10B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Qwen 3.5 122B A10B read images?›
It accepts text and images, video as input.
What is Qwen 3.5 122B A10B?›
Qwen 3.5 122B A10B is an open-weights language model from Alibaba (Qwen), released Feb 2026.
What are the best alternatives to Qwen 3.5 122B A10B?›
GPT-6.1 Sol (cheaper), GPT-6 Luna (better), Qwen3.8 Flash (open weights).