Nvidia API Pricing (Updated 2026)
Compare pricing for all 10 Nvidia models. Prices shown per 1M tokens with historical trends.
👁 The Grid | Spot Priced LLM API
Get started for free
The Grid | Spot Priced LLM APISponsored
Change 3 lines of code and let providers compete for your requests in real time.
8 Ways to Use Fewer Tokens
Last updated: June 28, 2026 at 08:35 AM
Overview
10
Total Models
$0.05
Cheapest Input (per 1M)
1000K
Max Context Length
Model Release Timeline
10 releasesOct 2024
$0.90 / $0.90
Sep 2025
$0.06 / $0.20
Sep 2025
$0.06 / $0.20
Oct 2025
$0.40 / $0.40
Oct 2025
$0.40 / $0.40
Oct 2025
$0.20 / $0.20
Oct 2025
$0.20 / $0.20
Dec 2025
$0.05 / $0.20
Dec 2025
$0.05 / $0.20
Jun 2026
$0.50 / $2.20
Spacing represents time between releases
Oct 2024→Jun 2026
All Nvidia Models
Compare pricing for all 10 Nvidia models.
Sponsored 👁 The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot pricesModel | Context | Input | Output | Cached Input | Cache Write | Coding | MMLU | GPQA | Actions |
|---|---|---|---|---|---|---|---|---|---|
128K | $0.000 | $0.000 | - | - | — | — | — | ||
Llama 3.1 Nemotron Ultra 253B v1 Thinking | 128K | $0.000 | $0.000 | - | - | 64.1 | 82.5 | 72.8 | |
262K | $0.050 | $0.200 | $0.45 | - | 36.0 | 57.9 | 39.9 | ||
Nemotron 3 Nano 30B A3B Thinking | 262K | $0.050 | $0.200 | $0.45 | - | 74.1 | 79.4 | 75.7 | |
131K | $0.060 | $0.200 | $0.1 | - | 70.1 | 73.9 | 55.7 | ||
Nemotron Nano 9B V2 Thinking | 131K | $0.060 | $0.200 | $0.1 | - | 72.4 | 74.2 | 57.0 | |
- | $0.085 | $0.400 | $0.45 | - | — | — | — | ||
- | $0.085 | $0.400 | - | - | — | — | 80.0 | ||
131K | $0.200 | $0.200 | $0.1 | - | 34.5 | 64.9 | 43.9 | ||
Nemotron Nano 12B 2 VL Thinking | 131K | $0.200 | $0.200 | $0.1 | - | 69.4 | 75.9 | 57.2 | |
128K | $0.200 | $0.200 | $0.1 | - | — | — | — | ||
131K | $0.400 | $0.400 | - | - | 28.0 | 69.8 | 51.7 | ||
Llama 3.3 Nemotron Super 49B V1.5 Thinking | 131K | $0.400 | $0.400 | - | - | 27.7 | 78.5 | 64.3 | |
1.0M | $0.500 | $2.200 | $0.1 | - | — | — | 86.7 | ||
131K | $0.900 | $0.900 | $0.45 | - | 16.9 | 69.0 | 46.5 |
* Some models use tiered pricing based on prompt length. Displayed prices are for prompts under 200k tokens.
Showing lowest price across all providers. Benchmarks from Artificial Analysis and HuggingFace Open LLM Leaderboard.
Cost vs. Quality
Compare Nvidia models by benchmark performance and cost.
X-axis:
Y-axis:
Loading chart...
Nvidia Models
Community Ratings
Rate how well Nvidia models perform across popular AI coding tools.
Historical Pricing Trends
Price Changes Over Time
No historical pricing data available for this provider.
Try Nvidia Models
Cost Calculator
Estimate your costs for any Nvidia model based on expected token usage.
Open Cost CalculatorTry in Playground
Test Nvidia models directly in your browser.
Open PlaygroundFrequently Asked Questions
Currently, Nemotron 3 Nano 30B A3B is the most affordable at $0.05 per 1M input tokens.
Count your input tokens (prompt) and expected output tokens (response). Use the formula: (input_tokens/1M × input_price) + (output_tokens/1M × output_price). Our pricing calculator can help automate this.
Nvidia pricing varies by model. Input costs range from $0.05 to $0.90 per 1M tokens. See the table above for specific model pricing.