nvidia: llama-3.1-nemotron-70b-instruct
Listed on OpenRouter as nvidia/llama-3.1-nemotron-70b-instruct since Nov 4, 2024. 108 snapshot observations, 4 repricings.
$1.20per 1M blended · $1.20 in / $1.20 out
USD per 1M tokens · blended at 3 input : 1 output · at this price for 157 days (since Nov 19, 2025)
All-time low$0.17Jan 17, 2025
All-time high$1.20Nov 19, 2025
Change since first seen+231.0%$0.36 on Nov 4, 2024
Listed price over time
| Observed | Input | Output | Blended | Change |
|---|---|---|---|---|
| Nov 19, 2025 | $1.20 | $1.20 | $1.20 | +100.0% |
| Sep 16, 2025 | $0.60 | $0.60 | $0.60 | +263.6% |
| Jan 17, 2025 | $0.12 | $0.30 | $0.17 | -17.5% |
| Dec 11, 2024 | $0.20 | $0.20 | $0.20 | -44.8% |
| Nov 4, 2024 | $0.35 | $0.40 | $0.36 | first observation |
Evidence and scope
- Source
- OpenRouter public model listing
- Archive
- Wayback Machine snapshots of that listing (weekly-grade, from July 2023) plus LLMPI's own daily snapshots since June 2026
- Last observed
- Apr 25, 2026
- Data
- history.json (CC BY 4.0)
This is the listed standard text-token rate for one OpenRouter listing ID. It does not normalize caching, batch discounts, long-context tiers, providers behind the listing, or model quality. A price can also move because OpenRouter's default route changed provider.