# nousresearch/hermes-2-pro-llama-3-8b

As of 17 September 2026, nousresearch/hermes-2-pro-llama-3-8b costs $0.140 per million input tokens and $0.140 per million output tokens on Novita AI. Observed on Novita AI's own published price list on 17 September 2026. This is Novita AI's resale price, not the model vendor's list price.

Source: Novita AI (reseller)
Canonical page: https://bertrande.com/en/ai/novita/nousresearch--hermes-2-pro-llama-3-8b/
Machine formats: https://bertrande.com/en/ai/novita/nousresearch--hermes-2-pro-llama-3-8b/data.json | https://bertrande.com/en/ai/novita/nousresearch--hermes-2-pro-llama-3-8b/data.csv
License: CC-BY-4.0, reuse with attribution and a link.

## Parameters

| Parameter | Value | Unit | Observed | Source level | Proof (SHA-256) |
|---|---|---|---|---|---|
| Input price | $0.140 | USD per 1M tokens | 2026-09-17 | L1 | `c50e1f80682be56f` |
| Output price | $0.140 | USD per 1M tokens | 2026-09-17 | L1 | `c50e1f80682be56f` |
| Context length | 8 192 | tokens | 2026-09-17 | L1 | `c50e1f80682be56f` |
| Maximum output | 8 192 | tokens | 2026-09-17 | L1 | `c50e1f80682be56f` |
| Input modalities | text | list | 2026-09-17 | L1 | `c50e1f80682be56f` |
| Output modalities | text | list | 2026-09-17 | L1 | `c50e1f80682be56f` |

## How this is verified

Every value above was read from the source URL shown on the canonical page, on the date given. We store a SHA-256 fingerprint of the source content at that moment, which is what lets us show later what the source said that day.

No value here was produced, estimated or completed by a language model. Where we have no verified figure, the row is absent rather than filled in.

Method: https://bertrande.com/en/methodology/
Report an error: https://bertrande.com/en/corrections/