NVIDIA Nemotron 3.5 Lightning vs Llama 3.3 70B (Together)
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by DeepInfra
|
by Together
2 providers:
Meta $0.590/$0.790
Together $1.04/$1.04
|
|---|---|---|
| Overview | ||
| Status | Current open weights Open weights | Current open weights Open weights |
| Released | Aug 11, 2026 | Dec 6, 2024 |
| Pricing per million tokens | ||
| Input | $0.080/Mtok | $1.04/Mtok |
| Output | $0.200/Mtok | $1.04/Mtok |
| Blended avg | $0.110/Mtok | $1.04/Mtok |
| Cached input | $0.040/Mtok | — |
| Specifications | ||
| Context window | 256K tokens | 131K tokens |
| Parameters | 30B (3B active) | 70B |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
text
|
| Benchmarks sources: Artificial Analysis / Vellum LLM Leaderboard (Jun 2026), Kaggle dataset | ||
| Avg benchmark score | — | 46.6 |
| Perf / dollar | — | 44.8 |
| GPQA Diamond | — | 50.5 |
| SWE-Bench Verified | — | 22 |
| Humanity's Last Exam | — | 10 |
| ARC-AGI 2 | — | 12 |
| AIME 2025 | — | 38 |
| MMMLU | — | 72 |
| BFCL | — | 77.3 |
| HumanEval | — | 78 |
| MATH 500 | — | 60 |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 23.6 | — |
| AA Agentic Index | 13.8 | — |
| AA-Omniscience Index (−100–100) | -17.7 | — |
| Providers | ||
| Available from |
DeepInfra — $0.080/$0.200/Mtok
|
Meta — $0.590/$0.790/Mtok
Together — $1.04/$1.04/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | NVIDIA Nemotron 3.5 Lightning | Llama 3.3 70B | Savings |
|---|---|---|---|
| 1M tokens | $0.11 | $1.04 | $0.93 (89.4%) |
| 10M tokens | $1.1 | $10.4 | $9.3 (89.4%) |
| 100M tokens | $11 | $104 | $93 (89.4%) |
| 1000M tokens | $110 | $1040 | $930 (89.4%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $0.110/Mtok blended vs $1.04 — 89.4% 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 3.3 70B doesn't offer
- you need the longer context: 256K tokens vs 131K (2×)
- provider flexibility: available from 2 providers, so you can price-shop hosts or fail over
Price movement
recorded changes since we began tracking each model · last checked Aug 18, 2026| Model | Changes | Latest move | Old → new $/M |
|---|---|---|---|
| NVIDIA Nemotron 3.5 Lightning | 0 | — no move | Stable since we began tracking — no change recorded |
| Llama 3.3 70B | 1 | price rise on Jun 25, 2026 | $0.88/$0.88 → $1.04/$1.04/Mtok |
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 3.3 70B by Together costs $1.04/Mtok input and $1.04/Mtok output, with a 131K-token context window. It supports text input and is available from 2 providers.
On a blended cost basis, NVIDIA Nemotron 3.5 Lightning is 89.4% cheaper than Llama 3.3 70B.It also has a larger context window.
The two aren't directly comparable on average benchmark score: Llama 3.3 70B 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.