nvidia/llama-3.1-nemotron-70b-instruct| Provider | Input, $ per 1M | Output, $ per 1M | In our data since |
|---|---|---|---|
| DeepInfra | $0.6 | $0.6 | 31 Jul 2026 |
Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.
The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.
| Task set | Result | Run conditions | Measured by |
|---|---|---|---|
| Arena Score in English | 1,315.06 1,305–1,325 | — | — |
| Arena Score, overall | 1,282.81 1,275–1,291 | — | — |
| Arena Score, multi-turn dialogue | 1,275.4 1,259–1,292 | — | — |
| Arena Score, programming | 1,272.26 1,257–1,288 | — | — |
| Arena Score, mathematics | 1,271.06 1,254–1,288 | — | — |
| Arena Score, creative writing | 1,268.95 1,250–1,288 | — | — |
| Arena Score, hard prompts | 1,266.64 1,254–1,279 | — | — |
| Arena Score, instruction following | 1,252.3 1,241–1,263 | — | — |
| Arena Score, expert questions | 1,241.87 1,215–1,269 | — | — |
| Arena Score, long queries | 1,238.7 1,221–1,256 | — | — |
| Arena Score in Russian | 1,225.92 1,209–1,243 | — | — |