Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for qwen

Qwen: Qwen3.6 35B A3B

qwen/qwen3.6-35b-a3b

Model weights
Compare

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 DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost. The model supports a 262K token native context window (extensible to 1M via YaRN) and accepts text, image, and video inputs. It includes integrated thinking mode with reasoning traces preserved across multi-turn conversations, function calling, and structured output. Released under the Apache 2.0 license.

Modalities

In / Out Price

$0.05 / $0.70per 1M

Context

262K

Released

Apr 27, 2026

Compare
BenchmarksProvidersPricingPerformanceUptimeAppsActivityFAQExplore

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Qwen: Qwen3.6 35B A3B (Artificial Analysis)
SourceBenchmarkScore
Artificial AnalysisQwen3.6 35B A3B (Reasoning) Intelligence Index18.2
Artificial AnalysisQwen3.6 35B A3B (Reasoning) Coding Index41.9
Artificial AnalysisQwen3.6 35B A3B (Reasoning) Agentic Index13.1
Artificial AnalysisQwen3.6 35B A3B (Reasoning) GPQA Diamond84.1%
Artificial AnalysisQwen3.6 35B A3B (Reasoning) HLE22.2%
Artificial AnalysisQwen3.6 35B A3B (Reasoning) IFBench64.4%
Artificial AnalysisQwen3.6 35B A3B (Reasoning) τ²-Bench Telecom95.3%
Artificial AnalysisQwen3.6 35B A3B (Reasoning) AA-LCR71.7%
Artificial AnalysisQwen3.6 35B A3B (Reasoning) GDPval-AA19.0%
Artificial AnalysisQwen3.6 35B A3B (Reasoning) CritPt0.3%
Artificial AnalysisQwen3.6 35B A3B (Reasoning) SciCode36.6%
Artificial AnalysisQwen3.6 35B A3B (Reasoning) Terminal-Bench Hard34.8%
Artificial AnalysisQwen3.6 35B A3B (Reasoning) AA-Omniscience Accuracy18.8%
Artificial AnalysisQwen3.6 35B A3B (Reasoning) AA-Omniscience Non-Hallucination Rate49.5%
Artificial AnalysisQwen3.6 35B A3B (Non-reasoning) Coding Index28.1
Artificial AnalysisQwen3.6 35B A3B (Non-reasoning) GPQA Diamond81.7%
Artificial AnalysisQwen3.6 35B A3B (Non-reasoning) HLE13.9%
Artificial AnalysisQwen3.6 35B A3B (Non-reasoning) IFBench36.2%
Artificial AnalysisQwen3.6 35B A3B (Non-reasoning) τ²-Bench Telecom85.1%
Artificial AnalysisQwen3.6 35B A3B (Non-reasoning) AA-LCR64.3%
Artificial AnalysisQwen3.6 35B A3B (Non-reasoning) GDPval-AA16.9%
Artificial AnalysisQwen3.6 35B A3B (Non-reasoning) CritPt0.0%
Artificial AnalysisQwen3.6 35B A3B (Non-reasoning) Terminal-Bench Hard25.8%
Artificial AnalysisQwen3.6 35B A3B (Non-reasoning) AA-Omniscience Accuracy16.7%
Artificial AnalysisQwen3.6 35B A3B (Non-reasoning) AA-Omniscience Non-Hallucination Rate7.9%

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), Floor (cheapest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
1.
Favicon for https://sekai.chat/
Sekai
new
17.9Btokens
2.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
6.38Btokens
3.
Favicon for https://sbatman.com/
Sentient
new
1.96Btokens
4.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
1.63Btokens
5.
Favicon for https://openclaw.ai/
OpenClaw
OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.
1.61Btokens

Frequently asked questions

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 DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost.

Qwen3.6 35B A3B costs $0.05/M input tokens and $0.70/M output tokens.

Qwen3.6 35B A3B has a 262,144 token context window. It supports up to 32,768 completion tokens.

Yes. Qwen3.6 35B A3B accepts tools and tool_choice for function calling on 8 of the 10 providers serving it, and requests that send tools are routed to those providers. It also supports structured outputs via a JSON schema in response_format.

Qwen3.6 35B A3B accepts text, images, and video as input and returns text.

Qwen3.6 35B A3B is served by 10 providers on OpenRouter: Darkbloom, AkashML, DeepInfra, Venice, Parasail, AtlasCloud, Phala, io.net and 2 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Qwen3.6 35B A3B was released on April 27, 2026.