Hermes 4 405B
nous-research/hermes-4-405b- Nous Research
- Family · Hermes 4
- Open weights
- Text → Text
- JSON
Not on OSMEXO yet
Spec & list price
Context128K
Max output118K
Input / 1M$1.00
Output / 1M$3.003× input
Usage
Tokens / day141.8M▼ 4.4% 7d
Usage rank#289
Requests / day36.4K
Per request · 30 days
Avg input3.2K0.2× median
Avg output1700.2× median
Cache hit65%about median
Reasoning share0.9%0.0× median
Consumption
Peak 354.2M 25 OctLow 60.2M 7 OctRank today #289
Speed
Output speed#265/33438 tok/s1.7× slower than median
First token#160.33 s3.3× quicker than median
Technical details
- Tokenizer
- Other
- Knowledge cutoff
- 2024-08-31
- License
- llama3
- Parameters
- 406B
- Moderation
- none
- Downloads · likes
- 2.1K · 97
Request parameters 13
- response_format
- structured_outputs
- reasoning
- include_reasoning
- temperature
- top_p
- top_k
- max_tokens
- frequency_penalty
- logprobs
+3 more
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Self-hosted assistants using open weights
- Steerable chat and role-play
- Long-form writing with large outputs
- Structured JSON output from text
Think twice for
- Image input
- Agents that need native tool calling
- Latency-sensitive high-volume chat
Want Hermes 4 405B on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.