jishie

Nemotron 3.5 Lightning 30B A3B

kilo/nvidia/nemotron-3.5-lightning · family nemotron · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$0.09
Blended $/1M (3:1)
$0.065
Input $/1M
$0.18
Output $/1M
$0.24
1M in + 1M out
—
Cache read $/1M
#900 of 7,715
Cheapest rank
Provider
Kilo Gateway (kilo)
Kind
text (outputs text)
Context
262,144 tokens
Max output
131,072 tokens
Capabilities
tools reasoning text

Same model, other providers

“Nemotron 3.5 Lightning 30B A3B” is offered by 9 providers — cheapest-effective first. Merge Gateway is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Merge Gatewayfreefree$0.001M
Nvidiafreefree$0.00262k
RunInfra$0.05$0.15$0.08262k
Fireworks AI$0.05$0.2$0.09262k
Kilo Gateway (this)$0.065$0.18$0.09262k
Nebius Token Factory$0.06$0.24$0.101M
OpenRouter$0.08$0.2$0.111M
DevPass (LLM Gateway)$0.08$0.2$0.11262k
Pioneer$0.5$0.5$0.508k

Call it

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

Most providers are OpenAI-compatible — point base_url at Kilo 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-3.5-lightning","messages":[{"role":"user","content":"hello"}]}'

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

← all Kilo Gateway models · model index · JSON