Qwen 3.6 Plus Uncensored
qwen-3-6-plusqwen-3-6-plus-uncensoredqwen-3.6-plusqwen-3.6-plus-uncensoredqwen3.6-plusqwen3.6-plus-uncensored- - 🏢 Alibaba's flagship Qwen3.6 Plus reasoning model, packaged uncensored by Venice.
- - 📏 1 million token context window enabled by default.
- - 👁️ Natively multimodal: processes text and images for reasoning.
- - 🔧 Native function calling and agentic coding workflows.
- - 🌐 Supports web search and tool use as exposed through the Venice catalog.
- - 🆕 Released April 2026, succeeding the Qwen3.5-Plus series.
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 34 more models by Alibaba Group →Qwen 3.6 Plus Uncensored is Venice's content-unrestricted deployment of Alibaba's Qwen3.6-Plus, a hosted Plus-tier model positioned in the "Plus" tier of the Qwen3 lineup — a balance of reasoning and cost between the lighter and Max-tier offerings. Alibaba describes it as built "towards real-world agents," integrating deep logical reasoning, extensive contextual memory, and precise tool execution into a single multi-step workflow.
Against its same-family predecessor, the Qwen3.5-Plus series, Alibaba calls this a "massive capability upgrade" with three headline improvements: a 1M-token context window by default, substantially enhanced agentic coding, and sharper multimodal perception and reasoning.
On Alibaba's reported benchmarks, the model scores 48.2% on MCPMark for tool-calling reliability. Treat these as vendor-reported figures evaluated within tool-augmented agent scaffolds.
Within the broader family, it sits alongside the open-weight Qwen 3.6 27B and Qwen 3.6 35B A3B FP8, and is itself superseded by the later Qwen 3.7 Plus and Max-tier Qwen 3.7 Max. Note that the standard Qwen3.6-Plus is a proprietary, API-hosted model; this catalog entry reflects an uncensored variant.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
| Seller | Reputation↓ | Routing | Input $/M | Cached $/M | Output $/M | Categories | API |
|---|---|---|---|---|---|---|---|
| ▲ Apex Ant 0x73b4…e736 | 71.90 | #3 | $1.25 | $0.03 | $3.75 | chat,agents,coding,reasoning,vision,multimodal,long-context,uncensored,premium | openai-chat-completions |
| Venice.ai Proxy 0x1f22…18c9 | 70.55 | #1 | $0.3125 | $0.0313 | $1.875 | chat,reasoning,coding,vision,video,multimodal,web-search,uncensored | openai-chat-completions |
| D5V1N2 0xd5e7…7be0 | 67.45 | #2 | $0.48 | $0.323 | $2.90 | chat,coding,reasoning,vision,large-context,router,fallback,qwen | openai-chat-completions |
| Fire Ant 🔥🐜 0xbe05…bc5d | 50.00 | gated | $0.4993 | $0.0499 | $2.9956 | — | — |
| antseed-cosmic-heron-08f1 0x5cd4…08f1 | 50.00 | gated | $0.48 | $0.03 | $1.70 | chat,chinese,coding,math,reasoning,general | openai-chat-completions |
| Open Bird 0xc0f1…8183 | 50.00 | gated | $0.0966 | $0.0097 | $0.5779 | chat | openai-chat-completions |
| antseed-neon-puma-944e 0x6650…944e | 35.09 | gated | $0.2131 | $0.0625 | $1.2788 | chat,coding,math | openai-chat-completions |
| incharge-austin 0x5938…ac97 | 30.79 | gated | $0.475 | $0.0475 | $2.85 | chat,coding | openai-chat-completions |
| Leftermute 0x388b…5389 | 28.39 | gated | $0.1263 | $0.1263 | $0.7575 | chat,coding,json | openai-chat-completions |
| Apex TEE Test 0xe672…7955 | 15.22 | gated | $0.3468 | $0.3468 | $2.0796 | chat,coding,open-source,vision,multimodal,reasoning,long-context,agents | openai-chat-completions |
"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.