Qwen3.5-35B-A3B

Qwen· released 25 Feb 2026

qwen/qwen3.5-35b-a3b

Input / 1M tokens: $0.15
Output / 1M tokens: $1

Context window262K tokens

Longest answer: 236K tokens

reads textreads imagereads videoopen weightstool callingvisionreasoning

About

Qwen3.5-35B-A3B is a Qwen model released February 25, 2026, with open weights and the Hugging Face identifier Qwen/Qwen3.5-35B-A3B. Its summary describes a native vision-language design that combines linear attention with a sparse mixture-of-experts architecture for higher inference efficiency. The model accepts text, image, and video inputs and produces text. It supports tools, vision, and reasoning. The context window is 262,144 tokens, and the maximum output is 235,929 tokens. The model identifier is qwen/qwen3.5-35b-a3b. Input pricing is 0.15 USD per 1M tokens, and output pricing is 1 USD per 1M tokens. Qwen is listed as maker and lab. The official listing is on OpenRouter.

Who it is for

Teams seeking an open-weights model with text, image, and video inputs may find this fit useful. Its tool, vision, and reasoning support also suits multimodal application development.

What is good

Open weights available
Accepts text, image, and video
262,144-token context window
Tool, vision, and reasoning support
235,929-token maximum output

What to know first

Output costs 1 USD per 1M tokens
Released February 25, 2026
Text-only output modality

Verdict

Qwen3.5-35B-A3B pairs open weights with multimodal inputs and a sparse mixture-of-experts design. Its pricing separates low-cost input processing from 1 USD per 1M output tokens.

Details

Lab: Qwenopenrouter.ai · 3 Oct 2026
Context: 262Kopenrouter.ai · 3 Oct 2026
Input price: $0.15 / 1Mopenrouter.ai · 3 Oct 2026
Output price: $1 / 1Mopenrouter.ai · 3 Oct 2026
Max output: 235,929 tokensopenrouter.ai · 3 Oct 2026
Inputs: text, image, videoopenrouter.ai · 3 Oct 2026
Open weights: Yesopenrouter.ai · 3 Oct 2026

More newest models

See the list

Ling 3.1 Flash ctx262KinFreeoutFree inclusionAI Apodex 1.1 Mini (free) ctx262KinFreeoutFree Apodex Pareto 26.10 Preview ctx1,049Kin$0.8 / 1Mout$3.2 / 1M unbiased GPT-6.1 Sol ctx1,050Kin$2 / 1Mout$10 / 1M OpenAI GPT-6.1 Sol Pro ctx1,050Kin$2 / 1Mout$10 / 1M OpenAI Claude Sonnet 5.5 ctx1,000Kin$2 / 1Mout$10 / 1M Anthropic

Listed on Inferse

Newest Models in 2026466 listed
Longest-Context Models in 2026466 listed
Cheapest Language Models in 2026437 listed
Models with Tool Calling in 2026395 listed
Reasoning Models in 2026332 listed
Vision Language Models in 2026295 listed
Open-Weight Models in 2026178 listed
Qwen Models: Pricing per 1M Tokens and Context (2026)52 listed

Sources

openrouter.ai/qwen/qwen3.5-35b-a3b· checked 3 Oct 2026