Alibaba
Qwen3.5 35B-A3B
Qwen vision-language model for visual reasoning, documents, and agent tasks
Model facts
- Context window
- 262K tokens
- Maximum output
- 66K tokens
- Cheapest paid input
- $0.057 per 1M tokens
- Cheapest paid output
- $0.459 per 1M tokens
- Open weights
- yes
- Providers
- 18
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 | 29.9 | not measured | not measured | not measured |
| Non-reasoning | 24.3 | 37.0 | not measured | 157.3 |
Observed price history
- 2026-08-24: $0.057 input / $0.459 output per 1M tokens
API providers
- EmpirioLabs AI — model id qwen3-5-35b-a3b; $0.057 input / $0.459 output per 1M tokens; provider documentation
- Merge Gateway — model id qwen/qwen3.5-35b-a3b; $0.057 input / $0.459 output per 1M tokens; provider documentation
- OrcaRouter — model id qwen/qwen3.5-35b-a3b; $0.057 input / $0.459 output per 1M tokens; provider documentation
- Deep Infra — model id Qwen/Qwen3.5-35B-A3B; $0.14 input / $1 output per 1M tokens; provider documentation
- Requesty — model id qwen3.5-35b-a3b; $0.14 input / $1 output per 1M tokens; provider documentation
- Kilo Gateway — model id qwen/qwen3.5-35b-a3b; $0.163 input / $1.3 output per 1M tokens; provider documentation
- OpenRouter — model id qwen/qwen3.5-35b-a3b; $0.25 input / $1.25 output per 1M tokens; provider documentation
- Weights & Biases — model id Qwen/Qwen3.5-35B-A3B; $0.25 input / $1.25 output per 1M tokens; provider documentation
- Mixlayer — model id qwen/qwen3.5-35b-a3b; $0.25 input / $1.3 output per 1M tokens; provider documentation
- Venice AI — model id qwen3-5-35b-a3b; $0.312 input / $1.25 output per 1M tokens; provider documentation
- NanoGPT — model id qwen3.5-35b-a3b; $0.225 input / $1.8 output per 1M tokens; provider documentation
- SiliconFlow — model id Qwen/Qwen3.5-35B-A3B; $0.24 input / $1.8 output per 1M tokens; provider documentation
- Ofox — model id bailian/qwen3.5-35b-a3b; $0.29 input / $1.83 output per 1M tokens; provider documentation
- Alibaba — model id qwen3.5-35b-a3b; $0.25 input / $2 output per 1M tokens; provider documentation
- Hugging Face — model id Qwen/Qwen3.5-35B-A3B; $0.25 input / $2 output per 1M tokens; provider documentation
- Jalapeno Cloud — model id Qwen3.5-35B-A3B; $0.25 input / $2 output per 1M tokens; provider documentation
- NovitaAI — model id qwen/qwen3.5-35b-a3b; $0.25 input / $2 output per 1M tokens; provider documentation
- Arena — model id qwen3.5-35b-a3b; not published input / not published output per 1M tokens; provider documentation