Qwen3.6 35B A3B
by CoreWeave · family qwen · 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$0.10
Output$0.89
Cache read$0.035
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
- 2026-04-17
- Last updated
- 2026-04-17
- Provider docs
- docs.wandb.ai/inference
Back of the envelope
≈
Also listed at
- QVACfree in · free out
- engy$0.045 in · $0.30 out
- SaladCloud AI Gateway$0.09 in · $0.60 out
- Kilo Gateway$0.10 in · $0.90 out
- OpenRouter$0.10 in · $0.90 out
- Deep Infra$0.10 in · $0.95 out
- Mallard AI$0.107 in · $1.00 out
- NanoGPT$0.112 in · $0.80 out
- Ambient$0.15 in · $1.00 out
- Hugging Face$0.15 in · $0.95 out
- ZeroGPU$0.20 in · $1.50 out
- Phala$0.20 in · $1.27 out
- SiliconFlow$0.24 in · $1.80 out
- DevPass (LLM Gateway)$0.248 in · $1.49 out
- Novita AI$0.248 in · $1.49 out