Qwen3.5 122B-A10B

qwen/qwen3.5-122b-a10b

Qwen (Alibaba)· 262K ctx

open weightstool callreasoningstructured quant: unknown

spread (output, p90 ÷ p10)

1.3×

$2.08 – $3.97 · 7 providers · max÷min 1.9×

7 providers priced · 8 offerings · 2 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	$0.115	$0.917	$0.0230	$0.129
OrcaRouter router / aggregator	$0.115	$0.917	—	$0.188no cache price published
EmpirioLabs AItiered unclassified	$0.115	$0.917	$0.115	$0.188
OpenRouter router / aggregator	$0.26	$2.08	—	$0.43no cache price published
SiliconFlowoutlier inference host	$0.26	$2.08	—	$0.43no cache price published
Kilo Gateway router / aggregator	$0.26	$2.08	—	$0.43no cache price published
Neon router / aggregator	$0.22	$2.20	—	$0.40no cache price published
Ofox reseller	$0.29	$2.29	$0.29	$0.47
Deep Infra inference host	$0.29	$2.40	—	$0.48no cache price published
Hugging Face inference host	$0.40	$3.20	—	$0.65no cache price published
Alibabafirst-party first-party lab	$0.40	$3.20	—	$0.65no cache price published
NovitaAI inference host	$0.40	$3.20	—	$0.65no cache price published
Jalapeno Cloud unclassified	$0.40	$3.20	—	$0.65no cache price published
Mixlayer inference host	$0.40	$3.20	—	$0.65no cache price published
Cortecs router / aggregator	$0.49	$3.46	$0.12	$0.53
NanoGPT router / aggregator	$0.44	$3.50	$0.10	$0.50
TensorX unclassified	$0.50	$3.50	$0.13	$0.59
Infomaniakfp8 inference host	$0.50	$3.97	—	$0.82no cache price published

Stale offerings (not in the spread) · 2

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

NEAR AI Cloud Qwen/Qwen3.5-122B-A10Bpay per token
NanoGPT qwen3.5-122b-a10bpay per token

Free tiers (rate-limited) · 1

No payment required; rate limits and quotas apply (not tracked yet). Excluded from cheapest, median and spread.

Nvidia qwen/qwen3.5-122b-a10bNVIDIA developer account + API keyfree tier

Connect

Provider (default: cheapest output among direct providers)

$2.08 /M · inference host

opencode.json

{
  "provider": {
    "siliconflow": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.siliconflow.com/v1"
      },
      "models": {
        "Qwen/Qwen3.5-122B-A10B": {}
      }
    }
  }
}

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.