nousresearch Open weights Reasoning

Hermes 4 70B pricing & benchmarks

Released Aug 26, 2025 · served by 1 provider

Input / 1M tokens$0.130
Output / 1M tokens$0.400
Context window131K
Cached input
1M in + 300K out$0.25

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...

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.

ProviderInputOutputContext QuantUptime 24hThroughput
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.