Nous Research
35 models across 8 families · Latest: Hermes-4-70B (2025-09)
Human-centric AI model innovation
Nous Research's portfolio covers 35 active models across 8 current families, spanning agents, long context, and classification. Open a model detail page to compare provider routes and sourced benchmarks.
Covers 4 workload areas across 35 active tracked models; last verified 2026-05-19.
Use it for
- Teams evaluating agents, long context, and classification across this lab's releases
- Comparing model families before committing to a flagship
- Migration and pricing follow-ups across 35 tracked models
Do not use it for
- Choosing a hosting provider without opening a model page for price ladders
Active models
35
Current models from this lab, excluding deprecated ones
Active families
8
Current model families from this lab
Open catalog
35 open
22 open source / 13 open weights
Lowest output price
$0.130 /1M
Cheapest tracked output across active models, per 1M tokens
Latest dated release
2025-09-22
Hermes-4-70B
Freshness
2026-05-19
Researched 60d ago
Information
Release cadence
Showing 5 recent dated releases (full timeline below). Latest: Hermes-4-70B (2025-09-22).
Where this lab wins
- Agentic: 1 tracked model with BFCL, tau-bench, and SWE-bench tool-use coverage.
- Long-context: 9 tracked models with context-token or InfiniteBench-class signal.
- Classification: 3 tracked models with MMLU-class moderation/safety coverage.
- JSON/tool-use: 4 tracked models with BFCL / Nexus strict-JSON routing coverage.
Flagship quality / price signal
Flagship: Hermes 2 Pro Llama 3 8B (best sourced coding quality-per-dollar in this portfolio).
Quality-per-dollar unavailable for this flagship — benchmark coverage or output token pricing is still missing.
Nous Research is an American AI research organization founded in 2023. Human-centric AI model innovation. Nous Research ships 8 model families totaling 35 models, with the most recent release Hermes-4-70B in 2025-09. Notable families include Hermes 4, Hermes 3, and Capybara. Use it as a stable reference for lab background, release coverage, and follow-up model pages as they are added. View official API endpoints, benchmark performance, and coding/agent fit for every Nous Research model.
About
Nous Research, founded in 2023 and based in New York, NY, stands as a beacon of innovation within the realm of artificial intelligence. As a private applied research group, it specializes in AI and machine learning within the technology sector, emphasizing the development of human-centric simulators and models. The team at Nous Research is distinguished by their groundbreaking work in the architecture of large language models (LLMs), data synthesis, and output steering, all aimed at aligning AI systems with real-world user experiences. Committed to challenging the traditional closed-model approach, Nous Research prioritizes open-source, human-compatible models. This vision is exemplified by their Hermes series of LLMs. The Hermes 3, their latest creation, leverages the advanced framework of Llama 3.1 and comes in three sizes: 8B, 70B, and 405B parameters. Unlike many proprietary models, Hermes 3 is highly steerable, offering users superior control over its responses and behavior. This model excels in maintaining conversation context and demonstrates remarkable reasoning and creative capabilities. It is equipped for complex activities such as role-playing, nuanced understanding, and multi-step problem solving, all the while enhancing Retrieval-Augmented Generation (RAG). The open release of Hermes 3's weights and training details showcases Nous Research's dedication to transparency and community collaboration, evidenced by the over 41,000 downloads of the 8B version within a single month. Nous Research's innovation extends beyond LLMs to projects like WorldSim, which delves into the potential of world simulation within AI. This endeavor enables users to explore and interact with AI's internal model of the world more creatively and dynamically than traditional chatbots. Additionally, their advancements in decentralized AI training, highlighted by the development of the DisTrO (Distributed Training Over the Internet) optimizer, significantly reduce bandwidth demands, thereby democratizing the training of powerful AI models across wide-spanning networks. The DisTrO has been proven to deliver an 857x increase in efficiency compared to existing algorithms, promising further efficiency gains of up to 10,000 times. In January 2024, with a successful seed round that raised $5.2 million from notable investors like Distributed Global and OSS Capital, Nous Research reinforces its position as a forward-thinking entity in AI development. This funding supports the creation of Nous-Forge, a platform anticipated to integrate with WorldSim and enhance AI orchestration. Through their innovations, Nous Research is not only advancing the field of AI but also making these technologies more accessible to researchers and developers worldwide, embodying their mission to foster customizability and collaboration within the AI community.
Featured models
| Model | Released | Context | Input price ($/1M) | Output price ($/1M) | License | Openness |
|---|---|---|---|---|---|---|
| Hermes-4-70B | 2025-09-22 | 128k | $0.05 | $0.20 | Llama 3 Community | Open weights |
| Hermes-4-405B | 2025-09-22 | 128k | $0.09 | $0.37 | Llama 3 Community | Open weights |
| Hermes 3 Llama 3.1 405B | 2024-11-01 | 128k | $1 | $1 | Llama 3 Community | Open weights |
Model families
Recent releases
- Hermes-4-70B- 2025-09-22
- Hermes-4-405B- 2025-09-22
- Hermes 3 Llama 3.1 405B- 2024-11-01
- Hermes 3 Llama 3.1 70B- 2024-11-01
- Hermes 3 Llama 3.1 8B- 2024-11-01
FAQ
Who founded Nous Research and when?
Nous Research was founded in 2023 and is associated with New York, New York, United States.
What models has Nous Research released?
Nous Research ships 35 models across 8 families: Hermes 4, Hermes 3, and Capybara.
Is Nous Research's technology open source?
All tracked Nous Research models are open-weight or open-source.
Where is Nous Research headquartered?
Nous Research is headquartered in New York, New York, United States.
What is Nous Research known for?
Human-centric AI model innovation. Its most prominent tracked family is Hermes 4.
How can I access Nous Research's models?
Nous Research's models are available via Cloudflare Workers AI, Fireworks AI, Lepton AI API, Microsoft Foundry, and Nous Portal.
Explore related pages
Last reviewed: 2026-05-19. Data sourced from public lab announcements and provider documentation.