jishie

Nemotron 3 Nano 30B A3B

merge-gateway/nvidia/nemotron-3-nano-30b-a3b · family nemotron · in: text → out: text · price provider-declared (via models.dev). Capabilities: reasoning text.

$0.09
Blended $/1M (3:1)
$0.05
Input $/1M
$0.2
Output $/1M
$0.25
1M in + 1M out
—
Cache read $/1M
#858 of 9,470
Cheapest rank
Provider
Merge Gateway (merge-gateway)
Kind
text (outputs text)
Context
256,000 tokens
Max output
32,000 tokens
Capabilities
reasoning text

Same model, other providers

“Nemotron 3 Nano 30B A3B” is offered by 7 providers — cheapest-effective first. This one (Merge Gateway) is the cheapest.

ProviderInputOutputBlendedContext
Merge Gateway (this)$0.05$0.2$0.09256k
Novita AI$0.05$0.2$0.09262k
Deep Infra$0.05$0.2$0.09262k
Crusoe$0.05$0.2$0.09262k
Kilo Gateway$0.06$0.24$0.10262k
OpenRouter$0.06$0.24$0.10262k
Thinking Machines$0.195$0.495$0.2766k

Call it

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

Most providers are OpenAI-compatible — point base_url at Merge Gateway 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-30b-a3b","messages":[{"role":"user","content":"hello"}]}'

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

← all Merge Gateway models · model index · JSON