Vendor
Nous Research models
4 models in the reference catalogue, vendor list prices per million tokens. 0 are routable on this deployment today.
Models
4
0 routable here
Median list price
$0.85
3:1 input to output per 1M tokens
Strongest
-
no published benchmarks
Every Nous Research model
Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.
| Model | Released | Context | Input / 1M | Output / 1M | Intelligence | Capabilities |
|---|---|---|---|---|---|---|
| Hermes 4 70Bnousresearch/hermes-4-70b | Aug 26, 2025 | 131K | $0.13 | $0.40 | - | reasoning open weights |
| Hermes 4 405Bnousresearch/hermes-4-405b | Aug 26, 2025 | 131K | $1.00 | $3.00 | - | reasoning open weights |
| Hermes 3 70B Instructnousresearch/hermes-3-llama-3.1-70b | Aug 18, 2024 | 131K | $0.70 | $0.70 | - | open weights |
| Hermes 3 405B Instructnousresearch/hermes-3-llama-3.1-405b | Aug 16, 2024 | 131K | $1.00 | $1.00 | - | open weights |
Frequently asked
- What is the cheapest Nous Research model?
- Hermes 4 70B at $0.13 per 1M input tokens and $0.40 per 1M output tokens (vendor list price).
- Which Nous Research model has the largest context window?
- Hermes 4 70B accepts 131K tokens of context.
- How do I route to Nous Research models with OpenSmartRoute?
- Declare a target in targets.yaml with metadata.model set to the catalogue id (for example nousresearch/hermes-4-70b); the router scores it against every other target on cost, quality, latency and your policies for each request.
Route Nous Research with everything else
OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a Nous Research flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.