Nous Research API Pricing
Community-driven open-source AI research and fine-tuned models
8 paid models · 24 free · Price range: $0.02 - $1.00 /1M
About Nous Research
Nous Research is a community-driven AI research organization known for high-quality fine-tuned models. Their Hermes series and other fine-tunes are popular in the open-source community for their strong instruction-following and creative capabilities.
Key Highlights
- High-quality fine-tuned models
- Strong community engagement
- Hermes series for instruction following
- Creative and roleplay capabilities
- Open-source focused
Pricing Features
- Pay-per-token billing
Models available for free through open-source. API access through hosting partners at competitive rates.
API Features
Common Use Cases
- • Creative Writing
- • Roleplay Applications
- • Research
- • Community Projects
- • Fine-Tuning Base
📊 Nous Research Model Comparison
Compare all models side by side. Sorted by total price (input + output).
| Model | Tier | Input /1M | Output /1M | Total /1M | Context | Best For |
|---|---|---|---|---|---|---|
| Hermes 2 Pro - Llama-3 8B | Budget | $0.02 | $0.08 | $0.10 | 8k | General tasks |
| Hermes 2 Pro - Llama-3 8B | Budget | $0.14 | $0.14 | $0.28 | 8k | General tasks |
| Hermes 4 70B | Budget | $0.11 | $0.38 | $0.49 | 131k | Complex reasoning, math |
| Hermes 4 70B | Budget | $0.13 | $0.40 | $0.53 | 131k | Complex reasoning, math |
| Hermes 3 70B Instruct | Budget | $0.30 | $0.30 | $0.60 | 131k | General tasks |
| Hermes 3 70B Instruct | Budget | $0.30 | $0.30 | $0.60 | 131k | General tasks |
🎯 Which Nous Research Model Should You Choose?
Quick recommendations based on your use case.
💰 Nous Research Monthly Cost Examples
Estimated monthly costs for common use cases.
| Use Case | Monthly Usage | Hermes 2 Pro - Llama-3 8B (Budget) |
Hermes 4 70B (Flagship) |
|---|---|---|---|
|
Customer Service Bot
1000 conversations/day
|
500k input 200k output |
$0.03/mo | $0.13/mo |
|
Code Assistant
200 requests/day
|
1.0M input 500k output |
$0.07/mo | $0.30/mo |
|
Data Analysis
500 analyses/day
|
2.0M input 300k output |
$0.07/mo | $0.33/mo |
⚔️ Nous Research vs Competitors
How does {brand} compare to other major AI providers?
| Brand | Model | Input /1M | Output /1M | Total /1M | Context | vs {brand} |
|---|---|---|---|---|---|---|
|
Nous Research
|
Hermes 4 70B Current | $0.11 | $0.38 | $0.49 | 131k | — |
OpenAI
|
Codex Mini | $1.50 | $6.00 | $7.50 | 200k | 1431% more |
|
OpenAI
|
GPT-5.2 Pro | $21.00 | $168.00 | $189.00 | 400k | 38471% more |
|
OpenAI
|
GPT-5.2 | $1.75 | $14.00 | $15.75 | 400k | 3114% more |
|
OpenAI
|
GPT-5.1-Codex-Max | $1.25 | $10.00 | $11.25 | 400k | 2196% more |
|
OpenAI
|
GPT-5.1 | $1.25 | $10.00 | $11.25 | 400k | 2196% more |
|
OpenAI
|
GPT-5.1-Codex | $1.25 | $10.00 | $11.25 | 400k | 2196% more |
All Models
❓ Nous Research Pricing FAQ
What is the cheapest Nous Research model?
The cheapest Nous Research model is Hermes 2 Pro - Llama-3 8B at $0.10 per 1M tokens (input + output combined).
What is the maximum context length for Nous Research models?
Nous Research models support up to 200k context length, allowing you to process large documents and maintain long conversations.
How do I choose between Nous Research models?
For budget projects, choose the cheapest model. For code generation, prioritize low output price. For complex reasoning, choose models with reasoning capability. Use our scenario guide above.