NVIDIA models through one API
19 NVIDIA models on an OpenAI-compatible endpoint: no separate vendor contract, one bill for the whole catalogue.
Llama 3.1 Nemotron Nano VL 8B v1
Text modelcontext 131K
No charge
Llama Nemotron Embed 1B v2
Embeddings
No charge
Llama Nemotron Embed VL 1B v2
Embeddings
No charge
Mistral Nemotron
Text modelcontext 131K
No charge
Nemotron 3 Embed 1B
Embeddings
No charge
Nemotron 3 Nano 30B A3B
Text modelcontext 262K
No charge
Nemotron 3 Nano Omni 30B A3B Reasoning
Text modelcontext 262K
No charge
Nemotron 3 Nano Omni 30B A3B Reasoning (Speech to Text)
Speech to text
No charge
Nemotron 3 Super 120B A12B
Text modelcontext 262K
No charge
Nemotron 3 Ultra
NVIDIA's open reasoning flagship, available free through AnyModel.
Text modelcontext 262K
No charge
Nemotron 3.5 Content Safety
Text modelcontext 33K
No charge
Nemotron 3.5 Lightning 30B A3B
Text modelcontext 262K
No charge
Nemotron Nano 12B v2 VL
Text modelcontext 131K
No charge
NV Embed v1
Embeddings
No charge
NV EmbedCode 7B v1
Embeddings
No charge
NV EmbedQA E5 v5
Embeddings
No charge
NVIDIA Nemotron Nano 9B v2
Text modelcontext 131K
No charge
Llama Nemotron Embed VL 1b V2
Embeddings
$0.005/ 1M
Riva Translate 4B Instruct v2
Text modelcontext 33K
No charge