nousresearch
Nous: Hermes 4 70B
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...
Quality Score
81/100
composite of price, context, capability
Input Price
$0.13
per 1M tokens
Output Price
$0.40
per 1M tokens
Context Window
131,072
tokens
- Model ID
- nousresearch/hermes-4-70b
- Vendor
- nousresearch
- Tokenizer
- Llama3
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- default
- Tool Calling
- not supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no
Similar models
nousresearch
Nous: Hermes 4 405B
$1.00 in / $3.00 out
131,072 ctx
79
nousresearch
Nous: Hermes 3 70B Instruct
$0.30 in / $0.30 out
131,072 ctx
76
nousresearch
Nous: Hermes 3 405B Instruct
$1.00 in / $1.00 out
131,072 ctx
75
nousresearch
Nous: Hermes 3 405B Instruct (free)
Free
131,072 ctx
64
nousresearch
NousResearch: Hermes 2 Pro - Llama-3 8B
$0.14 in / $0.14 out
8,192 ctx
60