Qwen3.5 35B-A3B

qwen/qwen3.5-35b-a3b

Qwen (Alibaba)· 262K ctx

open weightstool callreasoningstructured quant: unknown

spread (output, p90 ÷ p10)

1.6×

$1.00 – $2.00 · 8 providers · max÷min 2.0×

8 providers priced · 9 offerings · 1 omitted (stale)

Including routers & resellers

Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.

Provider classes in the stats:

Blended $/M assumptionsInput : output: 1Cache-hit share of input%

blended = 90.9% input × [(1 − 70% cache) × input + 70% cache × cache-read] + 9.1% × output + cache writes (30% of uncached input) where a write price is published

A provider that publishes no cache price is blended with cache share 0 (all input at the input price) and labelled “no cache price published” — never penalised against identical in/out prices.

Provider	Input	Output	Cache rd	Blended
Merge Gateway router / aggregator	$0.0570	$0.459	$0.0204	$0.0702
EmpirioLabs AItiered unclassified	$0.0570	$0.459	$0.0570	$0.0935
OrcaRouter router / aggregator	$0.0570	$0.459	—	$0.0935no cache price published
302.AI reseller	$0.0600	$0.460	—	$0.0964no cache price published
Deep Infra inference host	$0.14	$1.00	$0.05	$0.16
Requesty router / aggregator	$0.14	$1.00	$0.05	$0.16
CoreWeave inference host	$0.25	$1.25	$0.25	$0.34
OpenRouter router / aggregator	$0.31	$1.25	$0.16	$0.30
Venice AI inference host	$0.31	$1.25	$0.16	$0.30
Kilo Gateway router / aggregator	$0.16	$1.30	—	$0.27no cache price published
Mixlayer inference host	$0.25	$1.30	—	$0.35no cache price published
NanoGPT router / aggregator	$0.23	$1.80	$0.11	$0.30
SiliconFlow inference host	$0.24	$1.80	—	$0.38no cache price published
Ofox reseller	$0.29	$1.83	$0.29	$0.43
Alibabafirst-party first-party lab	$0.25	$2.00	—	$0.41no cache price published
NovitaAI inference host	$0.25	$2.00	—	$0.41no cache price published
Jalapeno Cloud unclassified	$0.25	$2.00	—	$0.41no cache price published
Hugging Face inference host	$0.25	$2.00	—	$0.41no cache price published

Stale offerings (not in the spread) · 1

Last priced more than 3 days before the latest snapshot — shown for reference, never mixed into cheapest, median or spread.

NanoGPT qwen3.5-35b-a3bpay per token

Connect

Provider (default: cheapest output among direct providers)

$1.00 /M · inference host

opencode.json

{
  "provider": {
    "deepinfra": {
      "npm": "@ai-sdk/deepinfra",
      "models": {
        "Qwen/Qwen3.5-35B-A3B": {}
      }
    }
  }
}

Set DEEPINFRA_API_KEY in your environment. Generated — verify against the OpenCode docs.

Output $/M over time7-day preview

Median line, min–max band. Pre-2026-09 points are catalog-recorded dates from models.dev git history, not provider effective dates.

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.