Hermes 3 405B Instruct
nous-research/hermes-3-llama-3.1-405b- Nous Research
- Family · Hermes 3
- Open weights
- Text → Text
- JSON
Not on OSMEXO yet
Spec & list price
Context128K
Max output16K
Input / 1M$1.00
Output / 1M$1.001× input
Usage
Tokens / day66.2M▼ 0.9% 7d
Usage rank#329
Requests / day17.6K
Per request · 30 days
Avg input3.5K0.2× median
Avg output1470.2× median
Consumption
Peak 109.8M 16 OctLow 56.5M 24 OctRank today #329
Speed
Output speed#304/33424 tok/s2.6× slower than median
First token#400.47 s2.3× quicker than median
Technical details
- Tokenizer
- Llama3
- Knowledge cutoff
- 2023-12-31
- License
- llama3
- Parameters
- 406B
- Moderation
- none
- Downloads · likes
- 1.7K · 276
Request parameters 13
- response_format
- structured_outputs
- temperature
- top_p
- top_k
- min_p
- max_tokens
- stop
- seed
- frequency_penalty
+3 more
- logit_bias
- presence_penalty
- repetition_penalty
When to use
Best for
- Self-hosted assistants using open weights
- Role-play and steerable chat personas
- Structured JSON output from text
- Long-form drafting and rewriting
Think twice for
- Image or file input
- Agents that need native tool calling
- Hardest reasoning and coding tasks
- Very long outputs
Same family
Hermes 3- N6.0
Want Hermes 3 405B Instruct on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.