Overview
Models
42
Cheapest Input
$0.04
Max Context
1.0M
Top Intelligence
57.2
Nvidia
Models
9
Cheapest Input
$0.04
Max Context
262K
Top Intelligence
36.0
Flagship Model Comparison
Gemini 3.1 Pro PreviewvsNemotron-3 Super 120B A12B
| Metric | Gemini 3.1 Pro Preview | Nemotron-3 Super 120B A12B |
|---|---|---|
| Input $/1M tokens | $2.00 | $0.10 |
| Output $/1M tokens | $12.00 | $0.50 |
| Context Window | 1.0M | N/A |
| Intelligence | 57.2 | 36.0 |
| Coding | 55.5 | 31.2 |
All Models Pricing
Google Models
Nvidia Models
| Model | Input/1M | Output/1M | Context |
|---|---|---|---|
| Nemotron-3 Super 120B A12B | $0.10 | $0.50 | N/A |
| Llama 3.3 Nemotron Super 49B V1.5 | $0.40 | $0.40 | 131K |
| Llama 3.1 Nemotron 70B Instruct | $0.90 | $0.90 | 131K |
| Nemotron Nano 9B V2 | $0.04 | $0.16 | 131K |
| Nemotron 3 Nano 30B A3B | $0.05 | $0.20 | 262K |
| Nemotron Nano 12B 2 VL | $0.20 | $0.20 | 131K |
| Nemotron 3 Super 120B A12B | $0.09 | $0.45 | N/A |
| Nemotron Nano 12B V2 | $0.20 | $0.20 | 128K |
| Llama 3.1 Nemotron Ultra 253B v1 | $0.00 | $0.00 | 128K |
Benchmark Comparison
Best Scores by Provider
| Benchmark | Nvidia | |
|---|---|---|
| Intelligence | 57.2 Gemini 3.1 Pro Preview | 36.0 Nemotron-3 Super 120B A12B |
| Coding | 55.5 Gemini 3.1 Pro Preview | 31.2 Nemotron-3 Super 120B A12B |
| Math | 87.7 Gemini 2.5 Pro | 62.3 Nemotron Nano 9B V2 |
| MMLU Pro | 89.5 Gemini 3 Pro Preview | 73.9 Nemotron Nano 9B V2 |
| GPQA | 94.1 Gemini 3.1 Pro Preview | 80.0 Nemotron-3 Super 120B A12B |
| LiveCodeBench | 85.7 Gemini 3 Pro Preview | 70.1 Nemotron Nano 9B V2 |
| Aider | 83.1 Gemini 2.5 Pro Preview 06-05 | 54.9 Llama 3.1 Nemotron 70B Instruct |
| AIME | 88.7 Gemini 2.5 Pro | 24.7 Llama 3.1 Nemotron 70B Instruct |
| BBH | 49.3 Gemma 2 27B | N/A |
Capabilities
| Capability | Nvidia | |
|---|---|---|
| Vision | ✓ (28 models) | ✓ |
| Tool Calls | ✓ (29 models) | ✓ (7 models) |
| Reasoning | ✓ (10 models) | ✓ (5 models) |
| Audio Input | ✓ (14 models) | — |
| Audio Output | — | — |
| PDF Input | ✓ (14 models) | — |
| Web Search | ✓ | — |
| Prompt Caching | ✓ (16 models) | — |
| Open Source Models | ✓ (15 models) | ✓ (5 models) |
Model-Level Comparisons
Compare specific models head-to-head: