Qwen3-Next 80B-A3B Instruct

alibaba· 2025-09· 262K ctx· apache-2.0

open weightstool callstructured quant: unknown

spread (output)

3.5×

$0.574 – $2.00 · 20 providers

20 providers priced

Provider	Input	Output	Cache rd	Blended
Nvidia relay router	free/—	free/—	—	free/—
Alibaba (China) relay router	$0.144	$0.574	—	$0.183^*
Merge Gateway unknown	$0.144	$0.574	$0.029	$0.110
NanoGPT relay router	$0.150	$0.650	$0.075	$0.148
Kilo Gateway relay router	$0.098	$0.780	—	$0.160^*
IO.NET relay router	$0.100	$0.800	$0.050	$0.148
Hugging Face relay router	$0.250	$1.00	—	$0.318^*
OpenRouter unknown	$0.090	$1.10	—	$0.182^*
Deep Infra open weights host	$0.090	$1.10	—	$0.182^*
Vercel AI Gateway unknown	$0.150	$1.20	—	$0.246^*
Amazon Bedrock hyperscaler	$0.150	$1.20	—	$0.246^*
Eden AI relay router	$0.150	$1.20	—	$0.246^*
DevPass (LLM Gateway) relay router	$0.150	$1.20	—	$0.246^*
LLM Gateway relay router	$0.150	$1.20	—	$0.246^*
Neon relay router	$0.150	$1.20	—	$0.246^*
Helicone relay router	$0.140	$1.40	—	$0.255^*
Jiekou.AI relay router	$0.150	$1.50	—	$0.273^*
NovitaAI relay router	$0.150	$1.50	—	$0.273^*
Jalapeno Cloud relay router	$0.150	$1.50	—	$0.273^*
LLM Gateway relay router	$0.150	$1.50	—	$0.273^*
Alibaba first party lab	$0.500	$2.00	—	$0.636^*

Cheapest (output)

Alibaba (China)

$0.574 /M

opencode.json

{
  "provider": {
    "alibaba-cn": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://dashscope.aliyuncs.com/compatible-mode/v1"
      },
      "models": {
        "qwen3-next-80b-a3b-instruct": {}
      }
    }
  }
}

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

Output $/M over time

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.