The Orchestrator › Models › Nous Research
Nous Research: Nous: 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...
Specifications
| Provider | Nous Research |
| Model ID | nousresearch/hermes-4-405b |
| Context window | 131K tokens (131,072) |
| Modalities | text → text |
| Tokenizer | Other |
| Router sources | OpenRouter, TrustedRouter |
| Released | 2025-08-26 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | nousresearch/hermes-4-405b | $1.00 | $3.00 | 131K |
| standard | TrustedRouter | NousResearch/Hermes-4-405B | $1.06 | $3.17 | 131K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $1.06 | $3.17 | 131K |
| 2026-11-14 | $1.00 | $3.00 | 131K |
Capabilities
Structured outputsControllable reasoningNo content storage (attested)Zero data retention
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, top_k, top_logprobs, top_p