Qwen: Qwen3.6 35B A3B

Image input Video input Text input Text output
Author's Description

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...

Key Specifications
Cost
$$$$$
Context
262K
Parameters
35B
Released
Apr 26, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Include Reasoning Response Format Temperature Max Tokens Reasoning Min P Presence Penalty Logit Bias Top P Frequency Penalty Seed
Features

This model supports the following features:

Reasoning Response Format
Performance Summary

Qwen3.6-35B-A3B, an open-weight multimodal model from Alibaba Cloud, demonstrates moderate speed performance, ranking in the 25th percentile across benchmarks. Its pricing tends to be at premium levels, positioned in the 20th percentile. A standout feature is its exceptional reliability, boasting a 99% success rate, indicating minimal technical failures. The model exhibits strong performance in several key areas. It achieved perfect accuracy in both General Knowledge and Ethics, with the latter also being the most accurate and fastest among models at its price point. Its Hallucinations baseline is impressive at 96.0% accuracy, suggesting a good ability to acknowledge uncertainty. The model also performs well in Email Classification (99.0% accuracy) and Reasoning (94.0% accuracy). While its Instruction Following (72.0% accuracy) and Coding (90.0% accuracy) are solid, they are not as exceptional as its knowledge-based and ethical reasoning capabilities. Mathematics performance is also strong at 93.0% accuracy. Overall, Qwen3.6-35B-A3B's primary strengths lie in its reliability, ethical reasoning, and general knowledge, making it a robust choice for applications requiring high accuracy and dependable operation, despite its moderate speed and premium pricing.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.161
Completion $0.965
Input Cache Read $0.161

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
AtlasCloud
AtlasCloud | qwen/qwen3.6-35b-a3b-20260415 262K $0.161 / 1M tokens $0.965 / 1M tokens
Parasail
Parasail | qwen/qwen3.6-35b-a3b-20260415 262K $0.35 / 1M tokens $2 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by qwen