Qwen3 235B-A22B

qwen/qwen3-235b-a22b

Qwen (Alibaba)· 262K ctx

open weightstool callstructured quant: unknown

spread (output, p90 ÷ p10)

— too few providers

$0.800 – $1.15 · 3 providers · max÷min 1.4×

3 providers priced · 4 offerings

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
NanoGPT router / aggregator	$0.300	$0.500	$0.150	$0.223
LLM Gatewayfp8 router / aggregator	$0.200	$0.800	—	$0.255no cache price published
Hugging Face inference host	$0.200	$0.800	—	$0.255no cache price published
NovitaAIfp8 inference host	$0.200	$0.800	—	$0.255no cache price published
Jiekou.AIfp8 reseller	$0.200	$0.800	—	$0.255no cache price published
Alibaba (China)CNfirst-party first-party lab	$0.29	$1.15	—	$0.37no cache price published
Merge Gateway router / aggregator	$0.29	$1.15	$0.06	$0.22
OpenRouter router / aggregator	$0.46	$1.82	—	$0.58no cache price published
Kilo Gateway router / aggregator	$0.46	$1.82	—	$0.58no cache price published
302.AI reseller	$0.29	$2.86	—	$0.52no cache price published

Subscription plans (flat fee, not per-token) · 1

Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.

DevPass (LLM Gateway) qwen3-235b-a22b-fp8subscription plan

Free tiers (rate-limited) · 1

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

iFlow qwen3-235bChina-hosted endpoint (iflow.cn)iFlow account + API keyfree tier

Connect

Provider (default: cheapest output among direct providers)

$0.800 /M · inference host

opencode.json

{
  "provider": {
    "huggingface": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://router.huggingface.co/v1"
      },
      "models": {
        "Qwen/Qwen3-235B-A22B": {}
      }
    }
  }
}

Set HF_TOKEN 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.