- - 🧠 Mixture-of-experts model: 30.5B total, 3.3B active per token
- - 🔧 128 experts, 8 activated across 48 layers
- - 📏 256K context in Venice; 32K native, 131K via YaRN upstream
- - 🔒 Runs in a Trusted Execution Environment with hardware attestation
- - 🛠️ Supports function calling, web search, and end-to-end encryption
- - 💬 Switchable thinking and non-thinking modes, 119 languages
- - 📚 Apache-2.0 licensed open weights
- - 🏢 Built by Alibaba's Qwen team; released March 2026
Alibaba Group is a Chinese multinational technology company founded in 1999 and headquartered in Hangzhou, Zhejiang. Originally built around e-commerce and cloud computing, Alibaba has become one of the most prolific contributors to open-weight AI research, developing the Qwen…
Explore 51 more models by Alibaba Group →Qwen3 30B A3B is Alibaba's compact sparse mixture-of-experts language model, packaging 30.5B total parameters but activating only about 3.3B per token through 8 of its 128 experts across 48 layers. As deployed in this catalog, it runs inside a Trusted Execution Environment, with hardware attestation evidence available so users can independently verify the runtime — a privacy-oriented packaging layered on top of the open-weights base model.
The base Qwen3 generation natively supports a 32,768-token context, extendable to roughly 131,072 tokens with YaRN scaling; this hosted variant advertises an ultra-long 256K window. It also offers seamless switching between a deliberate "thinking" mode and a faster non-thinking mode, plus multilingual coverage spanning 119 languages. Qwen reports that the 30B-A3B MoE outcompetes the earlier QwQ-32B despite the latter using roughly ten times the activated parameters.
Relative to the older same-family entry Qwen 2.5 7B, also offered in a TEE, this model moves from a small dense architecture to a much larger MoE design with vastly more total capacity at comparable per-token compute. Within this provider's lineup it sits alongside multimodal and uncensored relatives such as Qwen3 VL 30B A3B and Qwen3.6 35B A3B Uncensored, which extend the same sparse-MoE approach to vision and to later Qwen generations.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
Daily usage · Qwen3 30B A3B · Organic sellers
Top sellers · Qwen3 30B A3B · Organic
- Relay Works93.5%
- Linkrra Synap5.4%
- Venice.ai Proxy0.6%
- ▲ Apex Ant0.5%
| Seller | Rep↓ | Sales | Tokens | Routing | Input $/M | Cached $/M | Output $/M | Save |
|---|---|---|---|---|---|---|---|---|
| Relay Works 0x3040…7139 | 54.66 | $0.02 | 146.90k | gated | $0.14 | $0.12 | $0.56 | — |
| PawFlor-SI-Gateway ⚡ 0x70bc…8261 | 0.97 | — | — | gated | $0.10 | $0.10not advertised | $0.153 | −17% |
| Linkrra Synap 0xd7cf…71da | 0.00 | $0.00 | 14.02k | gated | $0.062 | $0.062not advertised | $0.26 | −48% |
| Apex TEE Test 0xe672…7955 | 0.00 | — | — | gated | $0.0513 | $0.0513 | $0.1863 | −57% |
| Leftermute 0x388b…5389 | 0.00 | — | — | gated | $0.0173 | $0.0173not advertised | $0.0627 | −86% |
"Best price" and the seller table are live Antseed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the Antseed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on Antseed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.