nousresearch/hermes-3-llama-3.1-70b vs nousresearch/hermes-4-405b
For 100,000 calls of 2,000 in and 500 out, nousresearch/hermes-3-llama-3.1-70b is cheaper: $175.00 a month at OpenRouter, against $350.00 for nousresearch/hermes-4-405b at OpenRouter — 2.0× the cost.
Cheapest on each
nousresearch/hermes-3-llama-3.1-70b
$175.00/mo
cheapest, at OpenRouter — $0.7 in, $0.7 out per million
nousresearch/hermes-4-405b
$350.00/mo
cheapest, at OpenRouter — $1 in, $3 out per million
Aligned facts
Same rows on both sides, including the ones we cannot fill.
| Attribute | nousresearch/hermes-3-llama-3.1-70b | nousresearch/hermes-4-405b |
|---|---|---|
| Context window | 131K | 131K |
| Accepts | Aa | Aa |
| Sellers | 1 | 1 |
| Cheapest input rate | $0.7 / M | $1 / M |
| Cached input rate | ○ no answer | ○ no answer |
No quality or benchmark row appears here. We hold no throughput or accuracy measurement for either model, and a cost-per-quality figure built from a lab’s own claim would look authoritative and mean nothing.
Cost for this workload — both models, every seller
100,000 calls a month · 2,000 input and 500 output tokens each. Sellers of both models lead, cheapest combined cost first.
| Seller | nousresearch/hermes-3-llama-3.1-70b /mo | nousresearch/hermes-4-405b /mo |
|---|---|---|
| OpenRouter | $175.002026-10-27 | $350.002026-10-27 |
Cheapest tier per seller, this workload only. In and output rates, and a cached prefix, are broken out in the cost calculator.