AI model comparison
Hermes 4 405B vs Nova Pro 1.0
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Nous
Hermes 4 405B
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research.
- Input / 1M
- $1
- Output / 1M
- $3
- Context
- 131K
Amazon
Nova Pro 1.0
Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks.
- Input / 1M
- $0.80
- Output / 1M
- $3.20
- Context
- 300K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Nova Pro 1.0
1.1x cheaper for a typical chat
Higher intelligence score
Hermes 4 405B
7.5 vs 7 on Artificial Analysis
Larger context window
Nova Pro 1.0
300K vs 131K tokens
Newer release
Hermes 4 405B
Released August 26, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Hermes 4 405B7.5Nova Pro 1.07Coding index
Hermes 4 405BNot availableNova Pro 1.0Not availableAgentic index
Hermes 4 405BNot availableNova Pro 1.0Not availablePricing
Hermes 4 405B vs Nova Pro 1.0 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Hermes 4 405B | Nova Pro 1.0 |
|---|---|---|
| Input tokensPer 1M tokens | $1 | $0.80 |
| Output tokensPer 1M tokens | $3 | $3.20 |
| Cached input (read)Per 1M tokens | Not available | Not available |
| Cache writePer 1M tokens | Not available | Not available |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Hermes 4 405B$3.50Nova Pro 1.0$3.20Coding task
30K in, 4K out
Hermes 4 405B$42Nova Pro 1.0$36.80Long document summary
150K in, 2K out
Hermes 4 405B$156Nova Pro 1.0$126.40Specs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Hermes 4 405B | Nova Pro 1.0 |
|---|---|---|
| Context window | 131K tokens | 300K tokens |
| Max output | 118K tokens | 5K tokens |
| Input types | Text | Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | Not available | Not available |
| Default reasoning effort | Not available | Not available |
| Release date | August 26, 2025 | December 5, 2024 |
Features
Supported features
API features available for each model.
| Metric | Hermes 4 405B | Nova Pro 1.0 |
|---|---|---|
| Tool calling | Not supported | Supported |
| Structured outputs | Not supported | Not supported |
| JSON mode | Supported | Not supported |
| Reasoning | Supported | Not supported |
| Temperature | Supported | Supported |
| Stop sequences | Not supported | Supported |
| Deterministic seed | Not supported | Not supported |
| Verbosity control | Not supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
Hermes 4 405BView full model details- Hermes 4 405B vs GPT-4.1 Mini
- Hermes 4 405B vs Qwen3 VL 235B A22B Instruct
- Hermes 4 405B vs Mistral Medium 3.1
- Hermes 4 405B vs Mistral Medium 3
- Hermes 4 405B vs Devstral 2 2512
- Hermes 4 405B vs GLM 4.5V
- Hermes 4 405B vs Mistral Large 2407
- Hermes 4 405B vs Hermes 3 405B Instruct
- Hermes 4 405B vs Hermes 3 70B Instruct
- Hermes 4 405B vs Mistral Large
- Hermes 4 405B vs Mixtral 8x22B Instruct
Nova Pro 1.0View full model details- Nova Pro 1.0 vs GPT-4.1 Mini
- Nova Pro 1.0 vs Qwen3 VL 235B A22B Instruct
- Nova Pro 1.0 vs Mistral Medium 3.1
- Nova Pro 1.0 vs Nova Premier 1.0
- Nova Pro 1.0 vs Mistral Medium 3
- Nova Pro 1.0 vs Devstral 2 2512
- Nova Pro 1.0 vs GLM 4.5V
- Nova Pro 1.0 vs Mistral Large 2407
- Nova Pro 1.0 vs GPT-4o-mini
- Nova Pro 1.0 vs Mistral Large
- Nova Pro 1.0 vs Mixtral 8x22B Instruct
Our take
Nova Pro 1.0 is 1.1x cheaper for a typical chat. Hermes 4 405B scores higher on the Artificial Analysis Intelligence Index (7.5 vs 7). Nova Pro 1.0 has the larger context window (300K vs 131K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is Hermes 4 405B or Nova Pro 1.0 cheaper?
Nova Pro 1.0 is cheaper for a typical chat (2K input tokens and 500 output tokens). Nova Pro 1.0 costs $0.80 per 1M input tokens and $3.20 per 1M output tokens, while Hermes 4 405B costs $1 per 1M input tokens and $3 per 1M output tokens.
Which has a bigger context window, Hermes 4 405B or Nova Pro 1.0?
Nova Pro 1.0 supports up to 300K tokens of context, compared with 131K for Hermes 4 405B.
Is Hermes 4 405B smarter than Nova Pro 1.0?
On the Artificial Analysis Intelligence Index, Hermes 4 405B scores 7.5 and Nova Pro 1.0 scores 7, putting Hermes 4 405B ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Hermes 4 405B and Nova Pro 1.0 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Hermes 4 405B and Nova Pro 1.0 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Hermes 4 405B and Nova Pro 1.0 at the same time. Compare the answers side by side and keep the best one.