Qwen3.6 35B A3B
by Weights & Biases · family qwen3.6 · listed Apr 2026RTVW
Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.
Current rates USD per 1M tokens
Input$0.25
Output$1.25
Cache read$0.25
Cache write—
Against the market
On the record
- Model id
Qwen/Qwen3.6-35B-A3B- Context window
- 262K tokens
- Max output
- 262K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-04-15
- Last updated
- 2026-04-15
- Provider docs
- docs.wandb.ai/guides/integrations/inference/
Back of the envelope
≈
Also listed at
- NanoGPT$0.112 in · $0.80 out
- OpenRouter$0.14 in · $1.00 out
- Hugging Face$0.15 in · $0.95 out
- Deep Infra$0.15 in · $0.95 out
- Wafer$0.15 in · $1.00 out
- Kilo Gateway$0.161 in · $0.965 out
- Zenifra$0.19 in · $0.48 out
- SiliconFlow$0.20 in · $1.60 out
- SiliconFlow (China)$0.23 in · $1.86 out
- OrcaRouter$0.248 in · $1.49 out
- LLM Gateway$0.248 in · $1.49 out
- Alibaba$0.248 in · $1.49 out
- Scaleway$0.25 in · $1.50 out
- Neuralwatt$0.29 in · $1.15 out