Hermes 4 70B pricing & benchmarks
Released Aug 26, 2025 · served by 1 provider
What Hermes 4 70B is
Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...
- Model ID:
nousresearch/hermes-4-70b - Modality: text->text
- Knowledge cutoff: 2024-08-31
- Tool calling: not supported · Structured output: not supported
- Weights:
NousResearch/Hermes-4-70Bon Hugging Face
Providers and prices for Hermes 4 70B
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| Nebiuscheapest | $0.130 | $0.400 | 131K | fp8 | 100.0% | — |
FAQ
How much does the Hermes 4 70B API cost?
$0.130 per 1M input tokens and $0.400 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.25.
Is Hermes 4 70B free?
No. It is a paid model starting at $0.130 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for Hermes 4 70B?
Nebius at $0.130 input / $0.400 output per 1M tokens (fp8 quantization).
Can I self-host Hermes 4 70B?
Yes — weights are published as NousResearch/Hermes-4-70B on Hugging Face, so you can run it on your own hardware.