ZMIME
Alibaba (Qwen) · Released Apr 17, 2026

Qwen3.6 35B-A3B

Open multimodal Qwen MoE for local agents that need vision, audio, and code.

  • Open weights
  • Reasoning
  • Tool calling
  • Vision
  • Video input
Capability
144.1ECI · #95 of 158
Input
$0.375per 1M tokens
Output
$2.25per 1M tokens
Context
262K66K max output
Pricing

What it costs

Input
$0.375per million tokens
Output
$2.25per million tokens
Blended (3:1)
$0.844pricier than 52% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$1.88
Team assistant25M input + 5M output tokens$20.63
Production app250M input + 50M output tokens$206.25

Official Alibaba API price, as listed on models.dev.

Capability

Independent benchmarks

144.1Epoch Capabilities Index
#95 of 158 scored models
68Median 147174

The shaded band is Epoch AI’s confidence range (142.2–146.0); the tick marks the median scored model.

  • GPQA DiamondGraduate-level science questions84.9%
  • FrontierMath Tiers 1–3Research-level mathematics20.4%
  • OTIS Mock AIME 2024–2025Competition mathematics86.7%

Scores from Epoch AI, run independently of Alibaba (Qwen).

Specifications

The details

Lab
Alibaba (Qwen)
Released
Apr 17, 2026
Context window
262,144 tokens
Max output
65,536 tokens
Inputs
Text, Images, Video
Output
Text
Reasoning
Thinking budget
Tool calling
Yes
Structured output
Yes
API model ID
qwen3.6-35b-a3bon Alibaba
Availability
43 API providerslisted on models.dev

Alibaba model documentation

Lab-reported

What Alibaba (Qwen) claims

Published by the lab at launch. Settings vary, so compare these only with care.

BenchmarkScoreSettingSource
SWE-Bench Verified73.4 resolved—Source
Same lab

More from Alibaba (Qwen)

Questions

About Qwen3.6 35B-A3B

How much does Qwen3.6 35B-A3B cost?

Qwen3.6 35B-A3B costs $0.375 input / $2.25 output per million tokens (official Alibaba API price). At a 3:1 input-to-output mix that is $0.844 per million tokens, more expensive than 52% of the 469 priced models we track.

What is the context window of Qwen3.6 35B-A3B?

Qwen3.6 35B-A3B accepts up to 262,144 tokens per request and can write up to 65,536 tokens in one response.

How good is Qwen3.6 35B-A3B?

Epoch AI gives Qwen3.6 35B-A3B a Capabilities Index score of 144.1 (likely range 142.2–146.0), ranking it #95 of 158 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 84.9%, FrontierMath Tiers 1–3 20.4%, OTIS Mock AIME 2024–2025 86.7%.

Is Qwen3.6 35B-A3B open source?

Yes. Alibaba (Qwen) publishes the weights, so it can be downloaded and self-hosted.

What inputs does Qwen3.6 35B-A3B support?

Qwen3.6 35B-A3B accepts text, images and video and replies in text. It is a reasoning model, supports tool calling and can return structured JSON output.

When was Qwen3.6 35B-A3B released?

Alibaba (Qwen) released Qwen3.6 35B-A3B on Apr 17, 2026.

What are the best alternatives to Qwen3.6 35B-A3B?

The closest current models from other labs on capability, price and release date are Gemini 3.5 Flash Lite (Google, ECI 145.7, $0.30 / $2.50), GLM-4.7 (Z.ai (Zhipu), ECI 143.4, $0.60 / $2.20), Nemotron 3 Ultra 550B A55B (NVIDIA, ECI 147.0, $0.55 / $2.40) and Kimi K2 Thinking (Moonshot AI, ECI 145.5, $0.60 / $2.50).