NVIDIA Nemotron 3 Super 120B (Public Preview)

digitalocean/nvidia-nemotron-3-super-120b · family nemotron · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.21Blended $/1M (3:1)

$0.165Input $/1M

$0.3575Output $/1M

$0.521M in + 1M out

$0.06 −64%Cache read $/1M

#1390 of 5,000Cheapest rank

Provider: DigitalOcean (digitalocean)
Context: 1,000,000 tokens
Max output: 32,768 tokens
Capabilities: toolsreasoningtext

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at DigitalOcean and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"nvidia-nemotron-3-super-120b","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):