# Nemotron 3 Super 120B A12B API prices

Nemotron 3 Super 120B A12B (nemotron) — 1.0M context, 262k max output.
11 metered per-token offers from 12 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| OpenRouter | $0.085 | $0.4 | — | 262k |
| Kilo Gateway | $0.08 | $0.45 | — | 262k |
| Pioneer | $0.09 | $0.45 | $0.09 | 256k |
| Requesty | $0.1 | $0.5 | — | 262k |
| Amazon Bedrock | $0.15 | $0.65 | — | 262k |
| Vercel AI Gateway | $0.15 | $0.65 | — | 256k |
| Eden AI | $0.3 | $0.9 | $0.3 | 262k |
| Nebius Token Factory | $0.3 | $0.9 | — | 262k |
| TensorX | $0.3 | $0.9 | $0.075 | 262k |
| Synthetic | $0.3 | $1 | $0.3 | 262k |
| Crusoe | $0.3 | $2.4 | $0.15 | 262k |

## Summary

- Cheapest input: $0.08 per 1M tokens (Kilo Gateway)
- Cheapest output: $0.4 per 1M tokens (OpenRouter)
- First-party: not listed separately
- Free offers: Kenari, Kenari, Requesty
- Subscription plans (not per-token): none
- Released: 2026-03-11
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/nemotron-3-super-120b-a12b/
Full dataset: https://llmprice.gitlab.io/data/catalog.json