Provider

Nous Research

Every Nous Research model UltraGPT can reach, kept in sync with the live catalog — pricing, context window and capabilities for each one.

3 models from Nous Research Up to 131.1K tokens of context
Open the appBrowse every provider

3

Models tracked

1

Providers

1

Reasoning models

0

See images (vision)

131K

Largest context window

0

Free to run

Directory

All Nous Research models.

Search and filter this provider's lineup — pricing per million tokens, context window, modalities, reasoning effort and independent benchmark scores where available.

3 of 3 models

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...

StreamingJSON mode
Context window131.1K tok
Max output16.4K tok
ReleasedAug 16, 2024
Knowledge cutoffDec 31, 2023
TextText
Input$1 / 1M tok
Output$1 / 1M tok

Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...

StreamingJSON mode
Context window131.1K tok
Max output16.4K tok
ReleasedAug 18, 2024
Knowledge cutoffDec 31, 2023
TextText
Input$0.7 / 1M tok
Output$0.7 / 1M tok

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...

ReasoningStreamingJSON mode
Context window131.1K tok
Max output118.0K tok
ReleasedAug 26, 2025
Knowledge cutoffAug 31, 2024
TextText
Input$1 / 1M tok
Output$3 / 1M tok

Every Nous Research model above, one subscription away.

UltraGPT puts this whole directory behind a single login and one flat monthly price — no separate bill per provider.