Nvidia Nemotron 3.5 Super VL 120B A12B

nvidia/nvidia-nemotron-3.5-super-vl-120b-a12b

NVIDIA· 1.0M ctx

open weightstool callreasoningstructured quant: unknown

spread (output, p90 ÷ p10)

— too few providers

$0.500 – $1.25 · 2 providers · max÷min 2.5×

2 providers priced · 2 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
CoreWeave inference host	$0.150	$0.500	$0.0200	$0.0991
Venice AI inference host	$0.25	$1.25	$0.13	$0.26

Connect

Provider (default: cheapest output among direct providers)

$0.500 /M · inference host

opencode.json

{
  "provider": {
    "wandb": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.inference.wandb.ai/v1"
      },
      "models": {
        "nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": {}
      }
    }
  }
}

Set WANDB_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.