Hermes 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…
Full description at the source- Input price
- per 1M tokens
- Output price
- per 1M tokens
- Context
- 131.1K118K max output
- Cost / request
- 8K in · 500 out
- Writing Elo
- 1419EQ-Bench creative writing
01Routes and pricing
02Capabilities
- Input
- text
- Output
- text
- Context
- 131.1K
- Max output
- 118K
ReasoningJSON mode
03Benchmarks
Creative writing
1418.5 EloEQ-Bench Creative Writing v3EQ-Bench Creative Writing v304Quick start
Call it with your RProuter key
Any OpenAI-compatible SDK works. Point it at the RProuter base URL from your API keys page and use this model ID.
Catalog source: openrouter.ai · checked 2026-09-16
const response = await client.chat.completions.create({
model: "nousresearch/hermes-4-405b",
messages: [{ role: "user", content: "A story begins…" }],
max_tokens: 500,
stream: true,
});
for await (const chunk of response) {
process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}