Sulat.com
AI models
$10 off the fastest DeepSeek V4.1 Flash, Kimi K3 and GLM 5.3 from Synthetic
Merge Gateway logo

Model details

Qwen3.6 Plus

Qwen3.6 Plus is Alibaba's flagship Plus-tier model in the Qwen 3.6 generation, built on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing to balance scalability with high-throughput inference. Compared to the prior Qwen 3.5 series, it delivers major gains in agentic coding, front-end development, and overall reasoning, with particular strength in repository-level problem solving and complex creative tasks such as 3D scenes and games. On the SWE-bench Verified coding evaluation it reaches a score of 78.8, positioning it at the level of leading state-of-the-art systems for software engineering work.

The model is positioned as a foundation for real-world agents, with sharper multimodal perception that lets it reason more accurately over images and video alongside text. It runs as a proprietary hosted service through the Qwen and Alibaba Cloud Model Studio APIs, retaining the family's long-context design while emphasizing reliability and stability improvements gathered from earlier Qwen Plus deployments. This focus on consistent multi-step execution makes Qwen3.6 Plus a practical fit for production coding agents, long-horizon research assistants, and multimodal applications where reasoning depth and agentic behavior matter more than raw chat performance.

Merge Gatewayqwen/qwen3.6-plusqwen

Quick Info

Powered by
Provider
Merge Gateway
Model key
qwen/qwen3.6-plus
Release date
Apr 2, 2026
Last updated
Apr 2, 2026
Knowledge cutoff
2025-04
Input modalities
Output modalities
Capabilities

Cost

Input token cost
$0.276
Output token cost
$1.651

Limits

Output tokens
250,000 tokens
Context window
1,000,000 tokens

Transparent token rates

Compare Qwen3.6 Plus pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Qwen3.6 Plus

Merge Gateway

CoverageBenchmark

OpenRouter's listing for Qwen3.6 Plus independently corroborates the model's identity and core specs: hybrid linear-attention + sparse mixture-of-experts architecture, 1M-token context, multimodal I/O, and an April 2, 2026 release. The model scored 78.8 on SWE-bench Verified and Alibaba Cloud Int. is listed as the sole Qwen3.6 Plus is described as a substantial leap from the 3.5 series for agentic coding, front-end development, reasoning, and "vibe coding," with strengths on 3D scenes, games, and repository-level tasks. OpenRouter reports 100% uptime for the Alibaba Cloud Int. endpoint over the displayed window, and the listing's P50

Videos about Qwen3.6 Plus

More models around Qwen3.6 Plus