Qwen3 235B A22B
Qwen3 235B A22BRankingin thinking mode?
Alternatives?
CheaperMiMo v2.6 ProthinkingOpen×4.5-56%$0.13Memory (4-bit): 141 GB → 615 GB+4
BetterGPT-6 Lunalow+84%-84%$0.005Function calling only with none · Chat Completions+3
OpenGLM 5.3 Flashmax×3.6-81%$0.28Memory (4-bit): 141 GB → 193 GB+5
CheaperMiniMax M3.1 Flashthinking×4.4-79%$0.22Complete model response must be appended
CheaperClaude Haiku 5.5max×4-84%$0.21Remove sampling parameters+5MiMo v2.6 ProthinkingOpen×4.5-56%$0.13Memory (4-bit): 141 GB → 615 GB+4MiniMax M3.1 Flashthinking×4.4-79%$0.22Complete model response must be appendedClaude Haiku 5.5max×4-84%$0.21Remove sampling parameters+5
DeepSeek V4.1 Flash 1017maxOpen×3.9-57%$0.26Memory (4-bit): 141 GB → 458 GB+5GLM 5.3 FlashmaxOpen×3.6-81%$0.28Memory (4-bit): 141 GB → 193 GB+5GPT-6 Lunalow+84%-84%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow+81%-63%$0.01MiMo v2.5thinkingOpen×2.5-86%$0.019Memory (4-bit): 141 GB → 186 GBClaude Haiku 5.5low×2.5-84%$0.024Remove sampling parameters+5
Mercury 2high+56%-69%$0.039GLM 5.3 FlashmaxOpen×3.6-81%$0.28Memory (4-bit): 141 GB → 193 GB+5
Ling 3.1 FlashOpen×3.6-63%$1.00Memory (4-bit): 141 GB → 343 GBMiniMax M3thinkingOpen×3.5-57%$0.51Memory (4-bit): 141 GB → 256 GB+2Qwen3.8 FlashthinkingOpen×3.5-81%$0.37max_tokens range · QwenCloud+5MMotif 3Open×3.4-29%$0.50 / $2Memory (4-bit): 141 GB → 189 GBQwen3.8 Max (0902)thinking×3.9—$5.41Qwen3.8 2.4T A95BthinkingOpen×3.9—$2.16Memory (4-bit): 141 GB → 1,468 GB+5Qwen3.7 Maxthinking×3.7—$1.15Qwen3.8 FlashthinkingOpen×3.5—$0.37max_tokens range · QwenCloud+5Qwen3.7 Plusthinking×3.2—$0.22Qwen3.6 Max Previewthinking×2.8—$1.30 / $7.80Include the word JSON · QwenCloudQwen3.5 397B A17BthinkingOpen×2.6—$0.47Memory (4-bit): 141 GB → 242 GBQwen3 Max Thinkingthinking×2.5—$1.20 / $6All Alibaba (Qwen) models →Run it yourself
estimateBenchmarks
all categoriesFAQ
How much does Qwen3 235B A22B cost?›
$0.70 per 1M input tokens and $2.80 per 1M output tokens; cheapest via DeepInfra at $0.18 / $0.54.
Is Qwen3 235B A22B free to use?›
There is no free API; the cheapest paid price is $0.18 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Qwen3 235B A22B, and what is it best at?›
#176 of 334 in Chat & Knowledge, #15 of 19 in Coding, #174 of 242 in Agents & Tool Use, #91 of 195 in Writing & Language.
Is Qwen3 235B A22B better than Qwen2.5 72B Instruct?›
On Humanity's Last Exam, Qwen3 235B A22B scores 11 vs 3.6 — higher.
How can I use Qwen3 235B A22B?›
Through the API of Alibaba, DeepInfra, Featherless.
What is the context window of Qwen3 235B A22B?›
33K tokens, with up to 16K output tokens.
When was Qwen3 235B A22B released? Is there a newer version?›
Released 2025-04-27. It is the current version in its line.
Is Qwen3 235B A22B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Qwen3 235B A22B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Qwen3 235B A22B read images?›
No, it accepts text only.
What is Qwen3 235B A22B?›
Qwen3 235B A22B is an open-weights language model from Alibaba (Qwen), released Apr 2025, the successor to Qwen2.5 72B Instruct.
What are the best alternatives to Qwen3 235B A22B?›
MiMo v2.6 Pro (cheaper), GPT-6 Luna (better), GLM 5.3 Flash (open weights).