Qwen3.5-35B-A3B
by CoreWeave · family qwen3.5 · listed Feb 2026RTVW
Qwen3.5-35B-A3B is an open-weights multimodal MoE model built for efficient, high-throughput inference across chat, reasoning, and agentic tasks.
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/Qwen3.5-35B-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
- 2026-02-24
- Last updated
- 2026-02-24
- Provider docs
- docs.wandb.ai/inference
Back of the envelope
≈
Also listed at
- AIHubMix$0.0564 in · $0.451 out
- OrcaRouter$0.057 in · $0.459 out
- Merge Gateway$0.057 in · $0.459 out
- 302.AI$0.06 in · $0.46 out
- Deep Infra$0.14 in · $1.00 out
- Requesty$0.14 in · $1.00 out
- Kilo Gateway$0.163 in · $1.30 out
- OpenRouter$0.163 in · $1.30 out
- NanoGPT$0.225 in · $1.80 out
- SiliconFlow (China)$0.23 in · $1.86 out
- SiliconFlow$0.24 in · $1.80 out
- LLM Gateway$0.25 in · $2.00 out
- NovitaAI$0.25 in · $2.00 out
- Alibaba$0.25 in · $2.00 out
- Hugging Face$0.25 in · $2.00 out