Claude Sonnet 5 vs Nemotron 3.5 Lightning
Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 5 (Anthropic) and Nemotron 3.5 Lightning (NVIDIA). Green cells mark the better value in each row.
Prices updated Sep 13, 2026, 1:15 PM UTC · refreshed hourly
| Claude Sonnet 5 Anthropic | Nemotron 3.5 Lightning NVIDIA | |
|---|---|---|
| Pricing | ||
| Input $/1M | $2.00 | $0.08 |
| Output $/1M | $10.00 | $0.20 |
| Blended $/1M (3:1) | $4.00 | $0.11 |
| RAG example (30K in / 2K out) | $0.08 | $0.0028 |
| Quality & speed | ||
| Intelligence Index | 38.4 | 13.6 |
| Coding Index | 71.5 | 26.8 |
| Agentic Index | 44.3 | 6.1 |
| Output speed (tok/s) | 88 | 292 |
| Time to first token | 122.96s | 0.55s |
| Specs | ||
| Context window | 1M | 262K |
| Input modalities | text, image, file | text |
FAQ
Which is cheaper, Claude Sonnet 5 or Nemotron 3.5 Lightning?
Nemotron 3.5 Lightning has the lower blended API price at $0.11 per 1M tokens (3:1 input:output mix), versus $4.00 for the other model. Prices are live from OpenRouter and refresh about hourly.
Which is better for RAG workloads?
For a typical RAG request (30K input / 2K output tokens), Nemotron 3.5 Lightning costs about $0.0028 per request versus $0.08. Also compare context windows: Claude Sonnet 5 offers 1M and Nemotron 3.5 Lightning offers 262K.
Which scores higher on Artificial Analysis benchmarks?
Claude Sonnet 5 leads on the Artificial Analysis Intelligence Index (38.4 vs 13.6). Check coding and agentic indices on this page for workload-specific tradeoffs.