Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
Qwen
qwen/qwen3.5-35b-a3bCatalogue: Indexed in the reference catalogue; nothing on this deployment answers as this model yet.
Published by the vendor; the platform bills at the target's declared price.
Qwen qwen/qwen3.5-35b-a3b
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
Qwen3.5-35B-A3B earns a request when it needs step-by-step reasoning, tool calls, very long inputs; a short, general request would go to Gemma 4 26B A4B (free) instead - free per million input tokens against $0.14 here; and the hardest requests, where the quality floor rules it out, to Claude Opus 5.5 (batch). Your rules decide the floor; the trace shows the comparison for every request.
Lower input price and an intelligence index within 5 points.
Nothing on this deployment answers as this model yet. Connect your own provider under Model providers, or add a target to your catalogue - the router picks it up without retraining.
# targets.yaml - declare a target that runs Qwen3.5-35B-A3B
targets:
- id: qwen3-5-35b-a3b
kind: llm
name: Qwen3.5-35B-A3B
metadata:
model: qwen/qwen3.5-35b-a3b # links the target to this catalogue entry
capabilities:
domains: [general]
supports_tools: true
context_window: 262144
cost:
usd_per_1k_tokens: 0.000570Input list price per million tokens; Qwen3.5-35B-A3B is the 3rd cheapest of 13 listed.
Photo: RDNE Stock project
Cached input reads $0.05 per 1M · weights on Hugging Face as Qwen/Qwen3.5-35B-A3B
A higher intelligence index, best first, with the price it comes at.
Other models by the same vendor in the catalogue.
The catalogue prints input and output prices and what three typical monthly workloads cost on each.
