Rank #42
Nous: Hermes 4 70B
- LLM
- 131k ctx
- 1M
- $0.27
Model · Vendors
Nous
Ranked models from this vendor or team on Global rankings (same data snapshot as the main global board).
Board snapshot:
About this vendor
Nous Research fine-tunes and merges open-weight models such as Hermes lines for agentic and chat workloads on community hosts. Track Hermes ranks, open-weights counts, and snapshot pricing on this vendor hub.
Vendor snapshot
Catalog models 4
Ranked on Global board 1
Best rank #42
Price range (avg/1M) $0.27–$2.00/1M
Max context 131k ctx
Model types
Origins
Top ranked models
Models on this board · Global rankings
| Rank | Name | Type | Key metric | 1M tokens (avg) |
|---|---|---|---|---|
| 42 | Nous: Hermes 4 70B | LLM | 131k ctx | $0.27 |
Catalog models (not in ranking)
| Rank | Name | Size | Price | Notes |
|---|---|---|---|---|
| — | Nous: Hermes 3 405B Instruct | 131k ctx | $1.00/1M | nousresearch/hermes-3-llama-3.1-405b |
| — | Nous: Hermes 3 70B Instruct | 131k ctx | $0.70/1M | nousresearch/hermes-3-llama-3.1-70b |
| — | Nous: Hermes 4 405B | 131k ctx | $2.00/1M | nousresearch/hermes-4-405b |
| — | Nous: Hermes 4 70B | 131k ctx | $0.27/1M | nousresearch/hermes-4-70b |
Data sources & methodology
Counts and prices come from the OpenRouter catalog snapshot merged with AI Hippo Global rankings (same snapshot as /rankings/). Rank reflects the composite score on that board—not LMSYS Chatbot Arena ELO. Snapshot date: 2026-08-02. Methodology
FAQ
What is Nous's highest-ranked model?
Nous: Hermes 4 70B currently ranks #42 on AI Hippo's Global rankings board (snapshot 2026-08-02).
What does Nous charge per 1M tokens?
Across catalog and ranked rows, blended 1M-token prices range from $0.27 to $2.00 in the latest snapshot (2026-08-02). Check individual model pages for prompt vs completion splits.
How many Nous models are ranked vs catalog-only?
1 of 4 catalog models appear on Global rankings; the remaining 3 are listed under catalog-only on this page.
How is the Global rankings score calculated?
Global rankings uses on-site weighting (context window first, then blended 1M-token price)—not third-party ELO. Full methodology: /en/methodology/