Qwen3.5 27B

qwen/qwen3.5-27b

Qwen (Alibaba)· 262K ctx

open weightstool callreasoningstructured quant: unknown

spread (output, p90 ÷ p10)

1.0×

$2.00 – $2.60 · 6 providers · max÷min 1.3×

6 providers priced · 7 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	$0.0860	$0.688	$0.0172	$0.0969
EmpirioLabs AItiered unclassified	$0.0860	$0.688	$0.0860	$0.141
OrcaRouter router / aggregator	$0.0860	$0.688	—	$0.141no cache price published
OpenRouter router / aggregator	$0.20	$1.56	—	$0.32no cache price published
Kilo Gateway router / aggregator	$0.20	$1.56	—	$0.32no cache price published
SiliconFlowoutlier inference host	$0.25	$2.00	—	$0.41no cache price published
Ofox reseller	$0.29	$2.05	$0.29	$0.45
NanoGPT router / aggregator	$0.27	$2.16	$0.14	$0.36
NovitaAI inference host	$0.30	$2.40	—	$0.49no cache price published
Alibabafirst-party first-party lab	$0.30	$2.40	—	$0.49no cache price published
Mixlayer inference host	$0.30	$2.40	—	$0.49no cache price published
Jalapeno Cloud unclassified	$0.30	$2.40	—	$0.49no cache price published
Hugging Face inference host	$0.30	$2.40	—	$0.49no cache price published
Deep Infraoutlier inference host	$0.26	$2.60	—	$0.47no cache price published
Requesty router / aggregator	$0.26	$2.60	—	$0.47no 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 qwen3.5-27bpay per token

Connect

Provider (default: cheapest output among direct providers)

$2.00 /M · inference host

opencode.json

{
  "provider": {
    "siliconflow": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.siliconflow.com/v1"
      },
      "models": {
        "Qwen/Qwen3.5-27B": {}
      }
    }
  }
}

Set SILICONFLOW_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.