List price
Input / 1M$0.00Output / 1M$0.00Cache read / 1M—Blended$0.000Value index—Last move—
models.dev · MIT · retrieved Oct 24, 2026
Nvidia
Llama 3.1 Nemotron 70B Instruct
Llama 3.1 Nemotron 70B Instruct is listed by Nvidia at $0 input and $0 output per million tokens. The recorded context window is 128,000 tokens. Release date on file: 2025-04-15. LMArena's text board published 2026-10-20 gives it an overall rating of 1282.7 (rank 267, 7,140 votes). Price source: models.dev (MIT).
- Context12
- Inverse price—
- Arena39
- GPQA—
- Tools100
- Modalities33
Price history
Input and output list price. A missing day stays a gap in the line. The series is not a quality history.
No ModelPriceWatch series matched this model, so there is no line to draw.
Benchmarks
LMArena is CC-BY-4.0. Epoch scores, including LiveBench where Epoch publishes it, are CC-BY-4.0. A blank cell means this snapshot has no match. Nothing here is estimated.
| Benchmark | Score | Detail | Source |
|---|---|---|---|
| LMArena overall | 1282.7 | rank 267 · 7,140 votes | LMArena leaderboard dataset · CC-BY-4.0 |
| LMArena coding | 1271.6 | rank 279 · 1,312 votes | LMArena leaderboard dataset · CC-BY-4.0 |
| LMArena math | 1271.0 | rank 264 · 1,041 votes | LMArena leaderboard dataset · CC-BY-4.0 |
| GPQA Diamond | — | — | — |
| LiveBench | — | — | — |
| SWE-bench Verified | — | — | — |
| Epoch Capability Index | — | — | — |
Provider prices
The list row is the price used for the value index. Other rows are the same model id on models.dev, plus the LiteLLM catalog price when we have one. A split quote is kept beside the list price.
| Quote | Provider | Input / 1M | Output / 1M | Blended | Source |
|---|---|---|---|---|---|
| List | Nvidia | $0.00 | $0.00 | $0.000 | models.dev · MIT |
| Also listed | Eden AI | $0.60 | $0.60 | $0.600 | models.dev · MIT |
| LiteLLM | deepinfra | $0.60 | $0.60 | $0.600 | LiteLLM model_prices_and_context_window.json · MIT |
Spec
Context128,000Max output8,192InputtextOutputtextReleased2025-04-15Open weightsYes
Spec fields are from the models.dev row for Nvidia.