Qwen

Qwen3.6 35B A3B

Launched 2026-04-17 · Listed on OpenRouter 2026-04-27

Prices updated . Benchmarks updated .

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...

You send / 1M

$0.100

tokens in

It replies / 1M

$0.900

tokens out

Context

262K

tokens it can read at once

Typical request

$0.0006

1,000 words in, 400 out

Benchmarks

BenchmarkScoreKindDateSource
Epoch Capabilities Index143.8Independent2026-04-14Epoch AI
GPQA Diamond84.8%Independent2026-08-07Epoch AI
OTIS Mock AIME86.7%Independent2026-08-07Epoch AI
Terminal-Benchagent little-coder24.6%Independent2026-04-16Terminal-Bench, republished by Epoch AI
CritPt0.3%Independent2026-04-14CritPt, republished by Epoch AI

Rankings on this site use the Epoch Capabilities Index, an independent composite. Lab-reported rows are the lab's own figures and are kept separate.

Data privacy

No training or retention: Yes. At least one provider serves it with zero data retention.

ProviderYou send / 1MIt replies / 1MUptimePrivacy policy
PrimeIntellect · fp8$0.037$0.338100%Read
DeepInfra · fp8$0.080$0.76091%Read
CoreWeave · fp8$0.100$0.890100%Read
AkashML · fp8$0.100$0.900100%Read
Parasail · fp8$0.100$0.900100%Read
DeepInfra · fp8$0.100$0.950100%Read
Venice · fp8$0.100$1.00100%Read
DeepInfra · fp8$0.150$1.4399%Read
SiliconFlow · fp8$0.240$1.8081%Read

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

  • Reads: text, image, video
  • Writes: text
  • Weights: Open weights
  • Reasoning: Yes
  • Tool calling: Yes
  • Longest reply: 262K tokens
  • Repeated text is billed at $0.025 per 1M (prompt caching)

Compare with

Appears in

Estimate your monthly cost with Qwen3.6 35B A3B

Sources and licenses

  • OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
  • Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
  • models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
  • Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
  • LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
  • Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
  • What a score measures: the benchmark guide.