NVIDIA API pricing
All 13 NVIDIA models with a live API price, cheapest input from $0.04 per 1M tokens. Sort by price, context window or benchmark, filter by capability, and copy the exact model ID for any serving provider. Verified against LiteLLM and OpenRouter daily.
Models
13
with a live API
Cheapest input
$0.04
per 1M tokens
Cheapest output
$0.10
per 1M tokens
Max context
262K
tokens
Capability
| Nvidia Nemotron Nano 9B | NVIDIA | 131K | $0.04 from | $0.16 from | 7.4 | n/a | 56% | 3 providers |
| Nvidia Nemotron Nano 12B | NVIDIA | 131K | $0.20 from | $0.20 from | n/a | n/a | n/a | 2 providers |
| Nvidia Nemotron Nano 3 30B | NVIDIA | 262K | $0.06 | $0.24 | 7.4 | n/a | 40% | Amazon Bedrock cheapest nvidia.nemotron-nano-3-30b |
| Llama 3.3 Nemotron Super 49B | NVIDIA | 131K | $0.10 | $0.40 | 8.5 | n/a | 52% | Nebius cheapest nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1 |
| Nemotron Nano V2 12B VL | NVIDIA | 4K | $0.10 | $0.10 | 4.6 | n/a | 44% | Fireworks AI cheapest fireworks_ai/accounts/fireworks/models/nemotron-nano-v2-12b-vl |
| Llama 3.3 Nemotron Super 49B V1.5 | NVIDIA | 131K | $0.10 | $0.40 | n/a | n/a | n/a | DeepInfra cheapest deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 |
| Llama3 1 Nemotron 70B Instruct FP8 | NVIDIA | 131K | $0.12 | $0.30 | n/a | n/a | n/a | Lambda AI cheapest lambda_ai/llama3.1-nemotron-70b-instruct-fp8 |
| Nvidia Nemotron Super 3 120B | NVIDIA | 256K | $0.15 | $0.65 | n/a | n/a | n/a | Amazon Bedrock cheapest nvidia.nemotron-super-3-120b |
| Nemotron 120B A12b | NVIDIA | n/a | $0.30 | $0.75 | n/a | n/a | n/a | Baseten cheapest baseten/nvidia/Nemotron-120B-A12B |
| Nemotron 3 120B A12b | NVIDIA | 256K | $0.50 | $1.50 | 25.4 | 37.7 | 80% | Cloudflare cheapest cloudflare/@cf/nvidia/nemotron-3-120b-a12b |
| Llama 3.1 Nemotron 70B Instruct | NVIDIA | 131K | $0.60 | $0.60 | 7.6 | n/a | 46% | DeepInfra cheapest deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct |
| Llama 3.1 Nemotron Ultra 253B | NVIDIA | 128K | $0.60 | $1.80 | n/a | n/a | n/a | Nebius cheapest nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1 |
| Llama V3p1 Nemotron 70B Instruct | NVIDIA | 131K | $0.90 | $0.90 | n/a | n/a | n/a | Fireworks AI cheapest fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct |
Nvidia Nemotron Nano 9B
NVIDIA · 131K CTX
Input $/1M
$0.04from
Output $/1M
$0.16from
Intelligence7.43 providers
Nvidia Nemotron Nano 12B
NVIDIA · 131K CTX
Input $/1M
$0.20from
Output $/1M
$0.20from
Intelligencen/a2 providers
Nvidia Nemotron Nano 3 30B
NVIDIA · 262K CTX
Input $/1M
$0.06
Output $/1M
$0.24
Intelligence7.4Amazon Bedrock
Llama 3.3 Nemotron Super 49B V1.5
NVIDIA · 131K CTX
Input $/1M
$0.10
Output $/1M
$0.40
Intelligencen/aDeepInfra
Llama3 1 Nemotron 70B Instruct FP8
NVIDIA · 131K CTX
Input $/1M
$0.12
Output $/1M
$0.30
Intelligencen/aLambda AI
Reasoning modelNvidia Nemotron Super 3 120B
NVIDIA · 256K CTX
Input $/1M
$0.15
Output $/1M
$0.65
Intelligencen/aAmazon Bedrock
Reasoning modelNemotron 3 120B A12b
NVIDIA · 256K CTX
Input $/1M
$0.50
Output $/1M
$1.50
Intelligence25.4Cloudflare
Llama 3.1 Nemotron 70B Instruct
NVIDIA · 131K CTX
Input $/1M
$0.60
Output $/1M
$0.60
Intelligence7.6DeepInfra
Llama V3p1 Nemotron 70B Instruct
NVIDIA · 131K CTX
Input $/1M
$0.90
Output $/1M
$0.90
Intelligencen/aFireworks AI
1–13 of 13 models
Page 1 of 1
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI