Qwen3-Next 80B-A3B (Thinking)

alibaba· 2025-09· 256K ctx· apache-2.0

open weights quant: unknown

spread (output)

9.2×

$0.650 – $6.00 · 14 providers

14 providers priced

Provider	Input	Output	Cache rd	Blended
NanoGPT relay router	$0.150	$0.650	$0.075	$0.148
Eden AI relay router	$0.150	$1.20	—	$0.246^*
Vercel AI Gateway unknown	$0.150	$1.20	—	$0.246^*
Kilo Gateway 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^*
Merge Gateway unknown	$0.150	$1.20	—	$0.246^*
OpenRouter unknown	$0.150	$1.20	—	$0.246^*
Alibaba (China) relay router	$0.144	$1.43	—	$0.261^*
NovitaAI relay router	$0.150	$1.50	—	$0.273^*
Jalapeno Cloud relay router	$0.150	$1.50	—	$0.273^*
Jiekou.AI relay router	$0.150	$1.50	—	$0.273^*
Hugging Faceoutlier relay router	$0.300	$2.00	—	$0.455^*
Alibabaoutlier first party lab	$0.500	$6.00	—	$1.00^*

Cheapest (output)

NanoGPT

$0.650 /M

opencode.json

{
  "provider": {
    "nano-gpt": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://nano-gpt.com/api/v1"
      },
      "models": {
        "qwen/qwen3-next-80b-a3b-thinking": {}
      }
    }
  }
}

Set NANO_GPT_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.