MODELS / NVIDIA

Nemotron 3.5 Lightning 30B

NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substantial leap in agentic capability over its predecessor Nemotron 3 Nano, with up to 4x higher throughput on a 1M-token context.

TEXTREASONINGTOOL-USEIMPLICIT-CACHINGSTRUCTURED-OUTPUTOPEN-WEIGHTS
262.1K
CONTEXT WINDOW
131.1K
MAX OUTPUT TOKENS
$0.06
INPUT PRICE / 1M TOKENS
$0.16
OUTPUT PRICE / 1M TOKENS
QUICKSTART
PROTOCOL:
OPENAI COMPATIBLE
STREAMING:
SUPPORTED

Call it in one request.

OpenAI-compatible: change the base URL, and the setup is complete.

curl https://enterprise.blackbox.ai/v1/chat/completions \
  -H "Authorization: Bearer $BLACKBOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "blackboxai/nvidia/nemotron-3.5-lightning",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
SPECIFICATIONS
CONTEXT:
262.1K
PROVIDER:
NVIDIA
TYPE:
TEXT

The full spec sheet.

Context, pricing, modalities, routing, and deployment: everything Nemotron 3.5 Lightning 30B supports, in one table.

MODEL ID
blackboxai/nvidia/nemotron-3.5-lightning
DEVELOPED BY
NVIDIA
MODEL TYPE
Text
RELEASED
Aug 11, 2026
CONTEXT WINDOW
262.1K
MAX OUTPUT TOKENS
131.1K
INPUT MODALITIES
text
OUTPUT MODALITIES
text
INPUT PRICE
$0.06 / 1M tokens
OUTPUT PRICE
$0.16 / 1M tokens
CACHE READ
$0.03 / 1M tokens
REASONING
Supported
DATA RETENTION
Standard retention
DEDICATED DEPLOYMENT
Enterprise · single-tenant
SUPPORTED PARAMETERS
max_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs