Qwen3 30B A3B
Qwen3 30B A3BAlternatives?
CheaperClaude Haiku 5.5max×9.7-7%$0.21Remove sampling parameters+5
BetterGPT-6 Lunalow×4.4-7%$0.005Function calling only with none · Chat Completions+3OpenQwen3.8 27Bxhigh×7.4+345%$1.01max_tokens range · QwenCloud+4
CheaperAgnes 2.5 Pro Beta×8.2-30%$0.10 / $0.30
CheaperMiMo v2.6 FlashthinkingOpen×7.6-19%$0.062Memory (4-bit): 18 GB → 186 GB+4Claude Haiku 5.5max×9.7-7%$0.21Remove sampling parameters+5GPT-6 Lunamax×8.4-7%$0.068Function calling only with none · Chat Completions+3Agnes 2.5 Pro Beta×8.2-30%$0.10 / $0.30MiMo v2.6 FlashthinkingOpen×7.6-19%$0.062Memory (4-bit): 18 GB → 186 GB+4
Nemotron 3.5 Super VLOpen×6.7-19%$0.19Memory (4-bit): 18 GB → 75 GBGPT-6 Lunalow×4.4-7%$0.005Function calling only with none · Chat Completions+3
Granite 4.2 3BthinkingOpen+44%-76%$0.006GPT-5.6 Lunalow×4.3+109%$0.01GPT OSS 20BhighOpen×2.4-83%$0.011
Mistral Small 4thinkingOpen×2.1+22%$0.015Memory (4-bit): 18 GB → 72 GBQwen3.8 27BxhighOpen×7.4+345%$1.01max_tokens range · QwenCloud+4Nemotron 3.5 Bolt 74B-A9BOpen×5.4——Memory (4-bit): 18 GB → 45 GBQwen 3.5 27BthinkingOpen×5.2+284%$0.30 / $2.40
Gemma 4 31BthinkingOpen×5.1-26%$0.10 / $0.34Memory (4-bit): 18 GB → 19 GBIK2 Horizon MoVA 36B A4BthinkingOpen×5.1+714%$1 / $4Memory (4-bit): 18 GB → 22 GBQwen3.8 Max (0902)thinking×9.4—$5.41Qwen3.8 2.4T A95BthinkingOpen×9.2—$2.16Memory (4-bit): 18 GB → 1,468 GB+5Qwen3.7 Maxthinking×8.8—$1.15Qwen3.8 FlashthinkingOpen×8.3—$0.37Memory (4-bit): 18 GB → 108 GB+6Qwen3.7 Plusthinking×7.7—$0.22Qwen3.6 Max Previewthinking×6.7—$1.30 / $7.80Include the word JSON · QwenCloudQwen3.5 397B A17BthinkingOpen×6.3—$0.47Memory (4-bit): 18 GB → 242 GBQwen3 Max Thinkingthinking×6.1—$1.20 / $6All Alibaba (Qwen) models →Run it yourself
estimateHistory
2 versionsBenchmarks
in Chat & KnowledgeFAQ
How much does Qwen3 30B A3B cost?›
$0.12 per 1M input tokens and $0.50 per 1M output tokens (cheapest host: DeepInfra).
Is Qwen3 30B A3B 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 Qwen3 30B A3B, and what is it best at?›
#288 of 334 in Chat & Knowledge, #142 of 239 in Coding, #182 of 242 in Agents & Tool Use, #141 of 195 in Writing & Language.
Is Qwen3 30B A3B better than Qwen3 4B 2507 (Reasoning)?›
On Humanity's Last Exam, Qwen3 30B A3B scores 6.2 vs 6.2 — about the same.
How can I use Qwen3 30B A3B?›
Through the API of DeepInfra.
What is the context window of Qwen3 30B A3B?›
33K tokens, with up to 16K output tokens.
When was Qwen3 30B A3B released? Is there a newer version?›
Released 2025-04-28. It has been superseded by Qwen3 30B A3B 2507 (Reasoning).
Is Qwen3 30B A3B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Qwen3 30B A3B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Qwen3 30B A3B read images?›
No, it accepts text only.
What is Qwen3 30B A3B?›
Qwen3 30B A3B is an open-weights language model from Alibaba (Qwen), released Apr 2025.
What are the best alternatives to Qwen3 30B A3B?›
Claude Haiku 5.5 (cheaper), GPT-6 Luna (better), Qwen3.8 27B (open weights).