DeepSeek V3 vs Nous Hermes 3 405B Instruct
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- DeepSeek V3 is 2.2× cheaper at a typical mix of 3 input tokens per output token.
- DeepSeek V3 accepts longer prompts: 164K vs 131K tokens.
- DeepSeek V3 is the newer model (released 2024-12-26).
| DeepSeek V3 | Hermes 3 405B Instruct | |
|---|---|---|
| Vendor | DeepSeek | Nous |
| Released | 2024-12-26 | 2024-08-16 |
| Input / 1M | $0.257 | $1.00 |
| Output / 1M | $1.03 | $1.00 |
| Cached input / 1M | — | — |
| Blended / 1M (3:1) | $0.45 | $1.00 |
| Context | 164K | 131K |
| Max output | 16K | 16K |
| Accepts | text | text |
| Reasoning | No | No |
| Providers on OpenRouter | 3 | 1 |
| Cheapest provider, output | $0.89 | $1.00 |
| Best provider uptime, 24 h | 99.51% | 99.56% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | — |
Cost calculator
DeepSeek V3
$30.87 per month$1.03 per day
Hermes 3 405B Instruct
$75.00 per month$2.50 per day
DeepSeek V3 saves $44.13 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare DeepSeek V3 with
Compare Hermes 3 405B Instruct with