Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...
- Modalities
- text → text
- In / out per 1M
- Free / Free
- Context
- 131K tokens
- Added
- Aug 16, 2024
- Tokenizer
- Llama3
- Knowledge cutoff
- Dec 31, 2023
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | Free | — | Free |
| Output | Free | — | Free |
Providers
No provider breakdown is published for Hermes 3 405B Instruct (free) in the current catalog snapshot (Jul 28, 2026). Browse all providers
Supported parameters
- frequency_penalty
- max_tokens
- presence_penalty
- stop
- temperature
- top_k
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use
model nousresearch/hermes-3-llama-3.1-405b:free.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer ***" \
-H "Content-Type: application/json" \
-d '{
"model": "nousresearch/hermes-3-llama-3.1-405b:free",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="nousresearch/hermes-3-llama-3.1-405b:free",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "nousresearch/hermes-3-llama-3.1-405b:free",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);About Hermes 3 405B Instruct (free)
Hermes 3 405B Instruct (free) is Nous Research's 405-billion-parameter build on Llama 3.1, tuned for agentic tasks, roleplay, multi-turn conversation, and long-context coherence. It runs text-in, text-out only, with a 131,072-token context window and a knowledge cutoff of December 31, 2023. It supports frequency/presence penalties, top_k, top_p, and standard sampling controls, but no vision or tool-calling parameters are exposed. This free variant is the one to reach for when you want the full 405B model's reasoning without paying per token.
The free tag is the story here: the paid version of the same model (nousresearch/hermes-3-llama-3.1-405b) costs $1.00 per 1M input and $1.00 per 1M output tokens, and this variant matches its 131,072-token context while charging $0. That context window is larger than 23% of catalog models, and Nous also sells a cheaper 70B sibling ($0.70/$0.70 per 1M) if you don't need 405B-scale weights. No benchmark scores are published for this listing, so treat capability claims as architecture-driven, not measured.
Questions
- Is Hermes 3 405B Instruct (free) free to use?
- Yes — both prompt and completion tokens are priced at $0.00 per 1M through OpenKey, and OpenKey's flat 3% fee on $0 is still $0. This is one of 25 free models in OpenKey's 329-model catalog. The paid version of the same 405B model, by contrast, runs $1.00 per 1M input and $1.00 per 1M output.
- What is Hermes 3 405B Instruct (free)'s context window?
- It supports 131,072 tokens of context, roughly enough for a few hundred pages of text in a single call. That places it in the upper range of the catalog — larger than 23% of all models tracked on OpenKey. There's no separate max_completion_tokens limit specified, so output length is bounded by the same context budget.
- Does Hermes 3 405B Instruct (free) support tool calling or vision?
- No — its input and output modalities are text-only, and its supported parameters list (frequency_penalty, max_tokens, presence_penalty, stop, temperature, top_k, top_p) doesn't include tool-calling or structured-output options. If you need function calling or image input, look at a different model in the catalog rather than this Hermes 3 build.
- What is Hermes 3 405B Instruct (free)'s knowledge cutoff?
- Its training data goes up to December 31, 2023. That's roughly a year older than models trained through 2024, so for anything requiring recent events or up-to-date facts, verify with retrieval or a newer model.
- How does Hermes 3 405B Instruct (free) compare to its paid sibling?
- It's the same 405B-parameter model and 131,072-token context as nousresearch/hermes-3-llama-3.1-405b, but free instead of $1.00 per 1M input and $1.00 per 1M output tokens. Nous also offers Hermes 3 70B at $0.70/$0.70 per 1M and the newer Hermes 4 405B at $1.00 input / $3.00 output — so this free 405B variant is the cheapest way to try Nous's largest Hermes 3 model.
More from Nous Research
All Nous Research models →
Nous ResearchHermes 4 405B
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
ctx 131K in $1.03 out $3.09
Nous ResearchHermes 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...
ctx 131K in $0.134 out $0.412
Nous ResearchHermes 3 70B Instruct
Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...
ctx 131K in $0.721 out $0.721
Nous ResearchHermes 3 405B Instruct
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...
ctx 131K in $1.03 out $1.03