Qwen3-Coder 480B-A35B Instruct

alibaba· 2025-04· 262K ctx· apache-2.0

API onlytool callstructured quant: unknown

spread (output)

9.4×

$0.800 – $7.50 · 21 providers

21 providers priced

Provider	Input	Output	Cache rd	Blended
Nvidia relay router	free/—	free/—	—	free/—
submodelfp8 relay router	$0.200	$0.800	—	$0.255^*
Helicone relay router	$0.220	$0.950	—	$0.286^*
SiliconFlow (China) relay router	$0.250	$1.00	—	$0.318^*
Deep Infra open weights host	$0.300	$1.00	$0.100	$0.236
SiliconFlow relay router	$0.250	$1.00	—	$0.318^*
Jiekou.AI relay router	$0.290	$1.20	—	$0.373^*
Abacus relay router	$0.290	$1.20	—	$0.373^*
Venice AI unknown	$0.350	$1.50	$0.040	$0.257
LLM Gateway relay router	$0.380	$1.55	—	$0.486^*
DevPass (LLM Gateway) relay router	$0.380	$1.55	—	$0.486^*
NovitaAI relay router	$0.380	$1.55	—	$0.486^*
LLM Gateway relay router	$0.220	$1.80	$0.022	$0.238
Merge Gateway unknown	$0.220	$1.80	—	$0.364^*
Amazon Bedrock hyperscaler	$0.450	$1.80	—	$0.573^*
Hugging Face relay router	$2.00	$2.00	—	$2.00^*
Together AIfp8 open weights host	$2.00	$2.00	—	$2.00^*
302.AIoutlier relay router	$0.860	$3.43	—	$1.09^*
Alibaba (China)tieredoutlier relay router	$0.861	$3.44	—	$1.10^*
Eden AIoutlier relay router	$1.50	$7.50	—	$2.05^*
Alibabatieredoutlier first party lab	$1.50	$7.50	—	$2.05^*
Vercel AI Gatewayoutlier unknown	$1.50	$7.50	$0.300	$1.28

Cheapest (output)

submodel

$0.800 /M

opencode.json

{
  "provider": {
    "submodel": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://llm.submodel.ai/v1"
      },
      "models": {
        "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {}
      }
    }
  }
}

Set SUBMODEL_INSTAGEN_ACCESS_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.