modelgrep

Cheapest Nous Models

Match · Updated July 2026

The cheapest Nous model is Hermes 4 70B at $0.130 per million input tokens. Hermes 3 70B Instruct ($0.700) and Hermes 4 405B ($1.00) round out the top three.

$0.130Input /M
131KContext

AI models ranked by input token price. The cheapest LLM APIs and most affordable AI models, from budget open-weight models to discounted frontier models.

  1. 1nousresearch logo
    hermes-4-70b
    ReasoningJSON131K ctx
    $0.130
    Input /M
  2. 2nousresearch logo
    hermes-3-llama-3.1-70b
    JSON5.1 intel · 131K ctx
    $0.700
    Input /M
  3. 3nousresearch logo
    hermes-4-405b
    ReasoningJSON131K ctx
    $1.00
    Input /M
  4. 4nousresearch logo
    hermes-3-llama-3.1-405b
    JSON131K ctx
    $1.00
    Input /M

Frequently asked

What is the cheapest Nous model?

The cheapest Nous model is Hermes 4 70B at $0.130 per million input tokens. Hermes 3 70B Instruct ($0.700) and Hermes 4 405B ($1.00) round out the top three.

What's a good alternative to Hermes 4 70B?

Hermes 3 70B Instruct ($0.700) is the closest alternative on this metric, followed by Hermes 4 405B ($1.00). See the full ranking above for the tradeoffs.

How many Nous models are there?

modelgrep tracks 4 Nous models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Hermes 3 70B Instruct. 4 of them qualify for this ranking.

More Nous rankings

All rankings