# Nemotron 3 Ultra API prices

Nemotron 3 Ultra (nemotron) — 1.0M context, 262k max output.
5 metered per-token offers from 10 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Requesty | $0.5 | $2.5 | — | 262k |
| Vercel AI Gateway | $0.6 | $2.4 | $0.12 | 1.0M |
| DigitalOcean | $0.9 | $1.7 | — | 131k |
| Venice AI | $0.625 | $3.125 | $0.1875 | 256k |
| Weights & Biases | $0.75 | $2.75 | $0.15 | 262k |

## Summary

- Cheapest input: $0.5 per 1M tokens (Requesty)
- Cheapest output: $1.7 per 1M tokens (DigitalOcean)
- First-party: not listed separately
- Free offers: Bothub, Kilo Gateway, OpenCode Zen, OpenRouter
- Subscription plans (not per-token): none
- Released: 2026-06-04
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/nemotron-3-ultra/
Full dataset: https://llmprice.gitlab.io/data/catalog.json