jishie

Nemotron 3 Nano Omni 30B A3B Reasoning

crusoe/nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B · family nemotron · in: text, image, video, audio → out: text · price provider-declared (via models.dev). Capabilities: toolsreasoningtextimagevideoaudio.

$0.68Blended $/1M (3:1)
$0.3Input $/1M
$1.83Output $/1M
$2.131M in + 1M out
$0.3Cache read $/1M
#2591 of 5,860Cheapest rank
Provider
Crusoe (crusoe)
Kind
text (outputs text)
Context
256,000 tokens
Max output
65,536 tokens
Capabilities
toolsreasoningtextimagevideoaudio

Same model, other providers

“Nemotron 3 Nano Omni 30B A3B Reasoning” is offered by 2 providers — cheapest-effective first. Deep Infra is the cheapest at $0.35 blended.

ProviderInputOutputBlendedContext
Deep Infra$0.2$0.8$0.35262k
Crusoe (this)$0.3$1.83$0.68256k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Crusoe 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-Nano-Omni-Reasoning-30B-A3B","messages":[{"role":"user","content":"hello"}]}'

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