Llama 3.3 Nemotron Super 49B V1

Llama 3.3 Nemotron Super 49B V1 is a text model from Nebius with a context window of 131K tokens and max output of 131K tokens. Pricing starts at 0.10 per million input tokens and 0.40 per million output tokens.

Capabilities

Vision Function Calling Reasoning JSON Schema System Messages Web Search Prompt Caching Audio Input Audio Output

Specifications

Model Keynebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1
ProviderNebius
Provider IDnebius
ModeText
Canonical Namellama-nemotron-super-3.3-49b-1
Context Window131K tokens
Max Output131K tokens

Pricing

TypePer 1K TokensPer 1M Tokens
Input Tokens0.0001000.100
Output Tokens0.0004000.400

Benchmarks

Intelligence Index14.3#139
Coding Index7.6#144
Math Index7.7#120
MMLU-Pro0.7#110
GPQA0.5#125
HLE0.0#202
LiveCodeBench0.3#118
AIME0.2#66
IFBench0.4#82
Time to First Token0.00s#1
SciCode0.2#146
MATH-5000.8#73
AIME 20250.1#120
LCR0.1#128
TerminalBench Hard0.0#148