Hermes 4 405B pricing and routing profile
Hermes 4 405B from Nousresearch lists at $1.00 per million input tokens and $3.00 per million output tokens, with a 131,072-token context window. Prices from OpenRouter's catalogue on 2026-09-28.
Reasoning control
Cost per 1,000 requests
| Request shape | List cost |
|---|---|
| Classification or routing (600 tokens in, 10 out) | $0.63 |
| Chat reply (2,000 in, 400 out) | $3.20 |
| Retrieval-augmented answer (8,000 in, 500 out) | $9.50 |
Before prompt caching. Try your own shape in the cost calculator.
Can Gimbix route to it first?
Not as a first-answer model through OpenRouter: no host returns token log probabilities for Hermes 4 405B. It can still be the model Gimbix falls back to when a cheaper model is unsure.
Cheaper models that can answer first
Models priced below Hermes 4 405B that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.
| Model | Input / output per 1M | Cheaper on a chat reply |
|---|---|---|
| DeepSeek V4 Pro 0423 | $0.955 / $1.91 | 16% |
| Morph V3 Large | $0.90 / $1.90 | 20% |
| Kimi K2 Thinking | $0.60 / $2.50 | 31% |
| GPT Audio Mini | $0.60 / $2.40 | 32% |
| GLM 5.2 | $0.65 / $2.04 | 34% |
| Qwen3.8 27B | $0.42 / $3.00 | 36% |
Questions
How much does Hermes 4 405B cost?
Hermes 4 405B lists at $1.00 per million input tokens and $3.00 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $3.20 per 1,000 requests.
What is the context window of Hermes 4 405B?
131,072 tokens.
Can a cheaper model replace Hermes 4 405B?
Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match Hermes 4 405B on one half of your requests and make at most three answers worse on the other.