Nvidia
Nvidia is an AI model provider.Tokenando tracks 17 Nvidia models, with input pricing from $0.040/M and an average blended cost of $0.843/M. Its flagship model is Llama-3.1-Nemotron-Ultra-253B.
NIM endpoints expose Nemotron and partner models behind a uniform API. Tight integration with NVIDIA enterprise stack.
MODELS TRACKED
17
3 categories
FLAGSHIP
Llama-3.1-Nemotron-Ultra-253B
Live API
MIN INPUT
$0.040/M
cheapest model in family
AVG BLENDED
$0.843/M
across 17 priced models
MAX CONTEXT
1,000,000
largest window in family
Frontier
4 models
Llama-3.1-Nemotron-Ultra-253Bprofile
Live API · 128,000 ctx
in $1.600/Mout $1.600/M
253B Nemotron · manual-seed
Mistral-Large-2 (NIM)profile
Live API · 128,000 ctx
in $2.000/Mout $6.000/M
Mistral via NIM · manual-seed
Nemotron 3 Ultra
text->text · 1,000,000 ctx
in $0.500/Mout $2.500/M
tokenizer: Other · cron:openrouter
Nemotron 3 Ultra (batch)
text->text · 512,288 ctx
in $0.600/Mout $3.600/M
Multimodal
3 models
Nemotron Nano 12B 2 VL
text+image+video->text · 131,072 ctx
in $0.200/Mout $0.600/M
tokenizer: Other · cron:openrouter
Nemotron 3.5 Content Safety (free)
text+image->text · 128,000 ctx
in $0.000/Mout $0.000/M
tokenizer: Other · cron:openrouter
Nemotron 3 Nano Omni (free)
text+image+audio+video->text · 256,000 ctx
in $0.000/Mout $0.000/M
tokenizer: Other · cron:openrouter
Efficient
10 models
Llama-3.1-Nemotron-70Bprofile
Live API · 128,000 ctx
in $0.350/Mout $0.400/M
RLHF-tuned 70B · manual-seed
Nemotron-4-340Bprofile
Live API · 4,000 ctx
in $4.200/Mout $4.200/M
340B NVIDIA · manual-seed
Mistral-NeMo-12B (NIM)profile
Live API · 128,000 ctx
in $0.150/Mout $0.150/M
NIM deployment · manual-seed
Phi-3-Mini-4K (NIM)profile
Live API · 4,000 ctx
in $0.040/Mout $0.040/M
Tiny NIM · manual-seed
Nemotron 3 Super
text->text · 262,144 ctx
in $0.085/Mout $0.400/M
tokenizer: Other · cron:openrouter
Nemotron 3 Nano 30B A3B
text->text · 262,144 ctx
in $0.050/Mout $0.200/M
tokenizer: Other · cron:openrouter
Nemotron Nano 9B V2
text->text · 131,072 ctx
in $0.040/Mout $0.160/M
tokenizer: Other · cron:openrouter
Llama 3.1 Nemotron 70B Instructprofile
text->text · 131,072 ctx
in $1.200/Mout $1.200/M
tokenizer: Llama3 · cron:openrouter
Nemotron 3.5 Lightning
text->text · 262,144 ctx
in $0.080/Mout $0.200/M
tokenizer: Other · cron:openrouter
Llama 3.3 Nemotron Super 49B V1.5
text->text · 131,072 ctx
in $0.100/Mout $0.400/M
tokenizer: Llama3 · cron:openrouter
Frequently Asked Questions
How many models does Nvidia offer?
Tokenando tracks 17 Nvidia models.
How much do Nvidia models cost?
Nvidia model input pricing starts at $0.040 per million tokens, with an average blended cost of $0.843 per million across the 17 priced models we track.
What is Nvidia's flagship model?
Nvidia's flagship model is Llama-3.1-Nemotron-Ultra-253B. It is the highest-tier Nvidia model we track, with input pricing of $1.600 per million tokens.
What model categories does Nvidia cover?
Nvidia covers 3 categories: frontier, multimodal and efficient.