N

Nous Research: hermes-4-70b:free

hermes-4-70b:free
128K contextReasoningToolsStructured
Released Aug 26, 2025Knowledge cutoff 2024Updated Aug 26, 2025

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 respond directly or generate explicit ... reasoning traces before answering. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs This 70B variant is trained with the expanded post-training corpus (~60B tokens) emphasizing verified reasoning data, leading to improvements in mathematics, coding, STEM, logic, and structured outputs while maintaining general assistant performance. It supports JSON mode, schema adherence, function calling, and tool use, and is designed for greater steerability with reduced refusal rates.

Tokenizer Llama3Quantization fp8NousResearch/Hermes-4-70B

All providers for this model are busy right now

Every upstream provider has hit its rate limit. The model comes back automatically once limits lift, usually within hours. Try again in a little while or switch to another model.

Request this model on Discord

Pricing

Input price
$0.00/ 1M tokens
Output price
$0.00/ 1M tokens
Context window 128K tokensCompatible endpoints openaiVendor Nous Research

Performance

Loading performance data...

Usage & Ranking

Loading usage...

Supported parameters

All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.

ParameterProvidersDefault
frequency_penaltyAll providers-
include_reasoningAll providers-
max_tokensAll providers-
presence_penaltyAll providers-
reasoningAll providers-
repetition_penaltyAll providers-
response_formatAll providers-
temperatureAll providers-
top_kAll providers-
top_pAll providers-

Frequently asked questions

Similar models