NVIDIA Nemotron 3.5 Lightning vs Llama 4 Scout
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by DeepInfra
|
by Meta
3 providers:
Groq $0.110/$0.340
Meta $0.110/$0.340
DeepInfra $0.100/$0.300
|
|---|---|---|
| Overview | ||
| Status | Current open weights Open weights | Current open weights Open weights |
| Released | Aug 11, 2026 | Apr 6, 2025 |
| Pricing per million tokens | ||
| Input | $0.080/Mtok | $0.110/Mtok |
| Output | $0.200/Mtok | $0.340/Mtok |
| Blended avg | $0.110/Mtok | $0.168/Mtok |
| Cached input | $0.040/Mtok | — |
| Specifications | ||
| Context window | 256K tokens | 10M tokens |
| Parameters | 30B (3B active) | 17B (16 experts) |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
textimage
|
| Benchmarks sources: Artificial Analysis / Vellum LLM Leaderboard | ||
| Independent composite scores measured for both models — each on its own scale | ||
| AA Intelligence Index | 23.6 | 10.3 |
| AA Agentic Index | 13.8 | 1.1 |
| AA-Omniscience Index (−100–100) | -17.7 | -52.1 |
| Per-benchmark results published for Llama 4 Scout only — no independent per-benchmark scores exist for NVIDIA Nemotron 3.5 Lightning yet | ||
| Avg benchmark score | — | 46.8 |
| Perf / dollar | — | 279.4 |
| GPQA Diamond | — | 57.2 |
| SWE-Bench Verified | — | 28 |
| LiveCodeBench | — | 32.8 |
| Humanity's Last Exam | — | 12 |
| ARC-AGI 2 | — | 15 |
| AIME 2025 | — | 45 |
| MMMLU | — | 75 |
| BFCL | — | 58 |
| HumanEval | — | 80 |
| MATH 500 | — | 65 |
| Providers | ||
| Available from |
DeepInfra — $0.080/$0.200/Mtok
|
Groq — $0.110/$0.340/Mtok
Meta — $0.110/$0.340/Mtok
DeepInfra — $0.100/$0.300/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | NVIDIA Nemotron 3.5 Lightning | Llama 4 Scout | Savings |
|---|---|---|---|
| 1M tokens | $0.11 | $0.17 | $0.06 (35.8%) |
| 10M tokens | $1.1 | $1.68 | $0.57 (34%) |
| 100M tokens | $11 | $16.75 | $5.75 (34.3%) |
| 1000M tokens | $110 | $167.5 | $57.5 (34.3%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.110/Mtok blended vs $0.168 — 34.3% less on the same 50/50 token mix
- your workload re-reads context (agents, RAG, long chats): cached input costs $0.040/Mtok — 50% off its list input price, a discount Llama 4 Scout doesn't offer
- you need the longer context: 10M tokens vs 256K (39.1×)
- provider flexibility: available from 3 providers, so you can price-shop hosts or fail over
Summary
NVIDIA Nemotron 3.5 Lightning by DeepInfra costs $0.080/Mtok input and $0.200/Mtok output, with a 256K-token context window. It supports text input.
Llama 4 Scout by Meta costs $0.110/Mtok input and $0.340/Mtok output, with a 10M-token context window. It supports text, image input and is available from 3 providers.
On a blended cost basis, NVIDIA Nemotron 3.5 Lightning is 34.3% cheaper than Llama 4 Scout.
The two aren't directly comparable on average benchmark score: Llama 4 Scout has published per-benchmark results, while NVIDIA Nemotron 3.5 Lightning does not yet — it is measured today on independent composites (see the table above).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.