Qwen 3.8 Max Prime

qwen/qwen3.8-max-prime

Qwen (Alibaba)· 1M ctx

API onlytool callreasoningstructured quant: unknown

0 providers priced · 0 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.

No published pricing for this dimension.

Provider	Input	Output	Cache rd	Blended
Kilo Gateway router / aggregator	$4.00	$12.00	$0.50	$2.50
NanoGPT router / aggregator	$4.00	$12.00	$0.50	$2.50
OpenRouter router / aggregator	$4.00	$12.00	$0.50	$2.50
Vercel AI Gateway router / aggregator	$4.00	$12.00	$0.50	$2.91
AI/ML API unclassified	$5.50	$16.50	$0.69	$3.44

Connect

Provider (default: cheapest output among direct providers)

$12.00 /M · router / aggregator

Includes routers & resellers — resold capacity; terms, data handling and availability not verified.

opencode.json

{
  "provider": {
    "kilo": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.kilo.ai/api/gateway"
      },
      "models": {
        "qwen/qwen3.8-max-prime": {}
      }
    }
  }
}

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

Not enough history yet — the min/median/max sparkline fills in as the daily snapshot accumulates.

Data: models.dev (MIT), snapshot 2026-10-17. Prices are vendor-published; verify before purchase. Methodology.