NVIDIA Models
haimaker.ai provides API access to all 5 NVIDIA models, with context windows up to 1M tokens, priced from $0.04 to $0.50 per 1M input tokens. OpenAI-compatible endpoint, instant access.
Models
5
Max context
1M
From
$0.04
/1M input
Modes
chat
NVIDIA Nemotron 3 Ultra 550B A55B BF16
NVIDIA
nvidia/nemotron-3-ultra-550b-a55b
560.5B params1M ctxIn: $0.50/1MOut: $2.50/1M
function callingreasoning
Nemotron 3 Nano Omni 30B A3B Reasoning BF16
NVIDIA
nvidia/nemotron-3-nano-30b-a3b
33.0B params66K ctxIn: $0.05/1MOut: $0.20/1M
function callingreasoning
NVIDIA Nemotron 3 Super 120B A12B NVFP4
NVIDIA
nvidia/nemotron-3-super-120b-a12b
67.2B params1M ctxIn: $0.09/1MOut: $0.45/1M
function callingreasoning
NVIDIA Nemotron Nano 9B v2
NVIDIA
nvidia/nemotron-nano-9b-v2
8.9B params66K ctxIn: $0.04/1MOut: $0.16/1M
function callingreasoning
Llama 3.3 Nemotron Super 49B V1.5
NVIDIA
nvidia/llama-3.3-nemotron-super-49b-v1.5
131K ctxIn: $0.10/1MOut: $0.40/1M
function callingreasoning