Mancer Weaver (alpha) vs Nous Hermes 3 70B 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
- Weaver (alpha) is 1.4× cheaper at a typical mix of 3 input tokens per output token.
- Hermes 3 70B Instruct accepts longer prompts: 131K vs 8K tokens.
- Hermes 3 70B Instruct is the newer model (released 2024-08-18).
| Weaver (alpha) | Hermes 3 70B Instruct | |
|---|---|---|
| Vendor | Mancer | Nous |
| Released | 2023-08-02 | 2024-08-18 |
| Input / 1M | $0.40 | $0.70 |
| Output / 1M | $0.75 | $0.70 |
| Cached input / 1M | — | — |
| Blended / 1M (3:1) | $0.488 | $0.70 |
| Context | 8K | 131K |
| Max output | 6K | 16K |
| Accepts | text | text |
| Reasoning | No | No |
| Providers on OpenRouter | 1 | 1 |
| Cheapest provider, output | $0.75 | $0.70 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | — | — |
Cost calculator
Weaver (alpha)
$35.25 per month$1.18 per day
Hermes 3 70B Instruct
$52.50 per month$1.75 per day
Weaver (alpha) saves $17.25 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Weaver (alpha) with
Compare Hermes 3 70B Instruct with