Alibaba
Qwen3.6 35B-A3B
Open multimodal Qwen MoE for local agents that need vision, audio, and code
Model facts
- Context window
- 262K tokens
- Maximum output
- 66K tokens
- Cheapest paid input
- $0.07 per 1M tokens
- Cheapest paid output
- $0.42 per 1M tokens
- Open weights
- yes
- Providers
- 27
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image, audio, video.
Local hardware estimate
At 4K context: Q4_K_M 20.2 GiB, Q8_0 36.9 GiB, F16 68.3 GiB working memory.
- Parameters
- 36.0 billion
- Architecture
- qwen3_5moe
- Model license
- apache-2.0
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| Reasoning | 32.1 | 41.9 | not measured | 141.4 |
| Non-reasoning | 24.6 | 28.1 | not measured | 144.0 |
Observed price history
- 2026-08-24: $0.07 input / $0.42 output per 1M tokens
API providers
- NaN — model id qwen3.6; free input / free output per 1M tokens; provider documentation
- QVAC — model id qwen3.6-35b-a3b; free input / free output per 1M tokens; provider documentation
- Umans AI Coding Plan — model id umans-qwen3.6-35b-a3b; free input / free output per 1M tokens; provider documentation
- EmpirioLabs AI — model id qwen3-6-35b-a3b; $0.07 input / $0.42 output per 1M tokens; provider documentation
- AKI.IO — model id qwen3.6-35b; $0.15 input / $0.5 output per 1M tokens; provider documentation
- Zenifra — model id alibaba/qwen3.6-35b-a3b; $0.19 input / $0.48 output per 1M tokens; provider documentation
- SaladCloud AI Gateway — model id qwen3.6-35b-a3b; $0.09 input / $0.6 output per 1M tokens; provider documentation
- Cortecs — model id qwen3.6-35b-a3b; $0.167 input / $0.557 output per 1M tokens; provider documentation
- NanoGPT — model id qwen/Qwen3.6-35B-A3B; $0.112 input / $0.8 output per 1M tokens; provider documentation
- OpenRouter — model id qwen/qwen3.6-35b-a3b; $0.1 input / $0.9 output per 1M tokens; provider documentation
- Kilo Gateway — model id qwen/qwen3.6-35b-a3b; $0.1 input / $0.9 output per 1M tokens; provider documentation
- Deep Infra — model id Qwen/Qwen3.6-35B-A3B; $0.1 input / $0.95 output per 1M tokens; provider documentation
- Hugging Face — model id Qwen/Qwen3.6-35B-A3B; $0.15 input / $0.95 output per 1M tokens; provider documentation
- Venice AI — model id qwen3-6-35b-a3b; $0.1 input / $1 output per 1M tokens; provider documentation
- Pioneer — model id Qwen/Qwen3.6-35B-A3B; $0.14 input / $1 output per 1M tokens; provider documentation
- Weights & Biases — model id Qwen/Qwen3.6-35B-A3B; $0.25 input / $1.25 output per 1M tokens; provider documentation
- evroc — model id Qwen/Qwen3.6-35B-A3B; $0.345 input / $1.38 output per 1M tokens; provider documentation
- Alibaba — model id qwen3.6-35b-a3b; $0.248 input / $1.49 output per 1M tokens; provider documentation
- DevPass (LLM Gateway) — model id qwen3.6-35b-a3b; $0.248 input / $1.49 output per 1M tokens; provider documentation
- LLM Gateway — model id novita/qwen3.6-35b-a3b; $0.248 input / $1.49 output per 1M tokens; provider documentation
- Merge Gateway — model id qwen/qwen3.6-35b-a3b; $0.248 input / $1.49 output per 1M tokens; provider documentation
- OrcaRouter — model id qwen/qwen3.6-35b-a3b; $0.248 input / $1.49 output per 1M tokens; provider documentation
- Scaleway — model id qwen3.6-35b-a3b; $0.25 input / $1.5 output per 1M tokens; provider documentation
- SiliconFlow — model id Qwen/Qwen3.6-35B-A3B; $0.2 input / $1.6 output per 1M tokens; provider documentation
- GreenPT — model id qwen3.6-35b-a3b; $0.342 input / $2.05 output per 1M tokens; provider documentation
- LLM Gateway — model id alibaba/qwen3.6-35b-a3b; $0.375 input / $2.25 output per 1M tokens; provider documentation
- LLMTR — model id qwen3-6-35b; $5 input / $10 output per 1M tokens; provider documentation