Qwen 3.5 35B A3B
Qwen 3.5 35B A3BAlternatives?
CheaperGPT-5.6 Lunamax+10%-35%$0.18BetterGPT-6 Lunamax+8%-71%$0.068Function calling only with none · Chat Completions+3OpenQwen3.6 27Bunstated+3%+96%$0.60 / $3.60
CheaperMiniMax M3unstatedOpen+9%-24%$0.30 / $1.20Memory (4-bit): 22 GB → 256 GB+2
CheaperGLM 5.3 FlashmaxOpen+8%-65%$0.28Memory (4-bit): 22 GB → 193 GB+5GPT-5.6 Lunamax+10%-35%$0.18MiniMax M3unstatedOpen+9%-24%$0.30 / $1.20Memory (4-bit): 22 GB → 256 GB+2GPT-6 Lunamax+8%-71%$0.068Function calling only with none · Chat Completions+3GLM 5.3 FlashmaxOpen+8%-65%$0.28Memory (4-bit): 22 GB → 193 GB+5
Claude Haiku 5.5max+7%-71%$0.21Remove sampling parameters+5GPT-6 Lunamax+8%-71%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Terralow+5%+555%$0.14Prompts with >272K input tokensGPT-5.6 Lunamax+10%-35%$0.18
Grok 4.3high+6%+127%$0.21Claude Haiku 5.5max+7%-71%$0.21Remove sampling parameters+5Qwen3.6 27BunstatedOpen+3%+96%$0.60 / $3.60Qwen3.6 35B A3BnoneOpen+2%-19%$0.25 / $1.49Qwen 3.5 9BunstatedOpen-5%-87%$0.08 / $0.13
Gemma 4 31BminimalOpen-9%-77%$0.10 / $0.34Context: 262K → 256KGemma 4 26B A4BminimalOpen-12%-62%$0.15 / $0.60Context: 262K → 256KQwen3.8 Max (0902)xhigh+11%—$2 / $6Qwen3.7 Maxmax+9%—$1.48 / $4.43No image inputQwen3.6 Plusunstated+6%—$0.50 / $3Qwen3.7 Plusunstated+5%—$0.32 / $1.28Qwen3.6 Max Previewunstated+5%—$1.30 / $7.80No image input+1Qwen3.5 397B A17BnoneOpen+3%—$0.60 / $3.60Memory (4-bit): 22 GB → 242 GBQwen3.6 27BunstatedOpen+3%—$0.60 / $3.60Qwen3.6 35B A3BnoneOpen+2%—$0.25 / $1.49All Alibaba (Qwen) models →Run it yourself
estimateHistory
2 versionsBenchmarks
in Chat & KnowledgeFAQ
How much does Qwen 3.5 35B A3B cost?›
$0.25 per 1M input tokens and $2 per 1M output tokens; cheapest via lab-qwen at $0.057 / $0.46.
Is Qwen 3.5 35B A3B free to use?›
There is no free API; the cheapest paid price is $0.057 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Qwen 3.5 35B A3B, and what is it best at?›
#120 of 334 in Chat & Knowledge, #90 of 97 in Coding, #115 of 175 in Agents & Tool Use, #105 of 195 in Writing & Language, #67 of 124 in Vision & Documents. Strongest at: Tool calling, Instructions.
Is Qwen 3.5 35B A3B better than Qwen 3.5 Plus?›
On GPQA Diamond · Epoch, Qwen 3.5 35B A3B scores 83.5 vs 84.8 — lower.
How can I use Qwen 3.5 35B A3B?›
Through the API of Alibaba, AtlasCloud, Darkbloom, DeepInfra, Novita and 3 more.
What is the context window of Qwen 3.5 35B A3B?›
262K tokens, with up to 66K output tokens.
When was Qwen 3.5 35B A3B released? Is there a newer version?›
Released 2026-02-23. It has been superseded by Qwen3.6 35B A3B.
Is Qwen 3.5 35B A3B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Qwen 3.5 35B A3B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Qwen 3.5 35B A3B read images?›
It accepts text and images, video as input.
What is Qwen 3.5 35B A3B?›
Qwen 3.5 35B A3B is an open-weights language model from Alibaba (Qwen), released Feb 2026, the successor to Qwen3 VL 30B A3B Instruct.
What are the best alternatives to Qwen 3.5 35B A3B?›
GPT-5.6 Luna (cheaper), GPT-6 Luna (better), Qwen3.6 27B (open weights).