Hermes 4 405B pricing
$1.00 per 1M input tokens and $3.00 per 1M output tokens. In real work that is 0.30¢ per chat answer and 1.5¢ to summarize a 20-page PDF.
What Hermes 4 405B costs per task
Token counts estimated from a measured model of the same lab (MiniMax M3), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.30¢$3.00 / 1,000 | 206 in · 451 out · 482 reasoning | 195 of 336 | estimated |
| Reply to a customer email | 0.18¢$1.77 / 1,000 | 420 in · 262 out · 187 reasoning | 215 of 336 | estimated |
| Write a 1,500-word blog post | 0.69¢$6.92 / 1,000 | 220 in · 1,790 out · 442 reasoning | 158 of 336 | estimated |
| Write 10 product descriptions | 0.53¢$5.28 / 1,000 | 444 in · 1,080 out · 531 reasoning | 157 of 336 | estimated |
| Translate 1,000 words | 1.9¢$18.74 / 1,000 | 1,486 in · 1,217 out · 4,535 reasoning | 234 of 336 | estimated |
| Proofread one page (500 words) | 0.41¢$4.10 / 1,000 | 881 in · 656 out · 416 reasoning | 214 of 336 | estimated |
| Summarize a 20-page PDF | 1.5¢$15.15 / 1,000 | 13,017 in · 466 out · 246 reasoning | 225 of 336 | estimated |
| Extract data from an invoice | 0.31¢$3.11 / 1,000 | 540 in · 568 out · 289 reasoning | 196 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥5.3¢$52.99 / 1,000 | 4,984 in · 154 out · 15,847 reasoning | 242 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.76¢$7.60 / 1,000 | 3,807 in · 829 out · 437 reasoning | 213 of 336 | estimated |
| Classify 100 support tickets | 0.72¢$7.22 / 1,000 | 1,436 in · 444 out · 1,485 reasoning | 177 of 336 | estimated |
| Review 500 lines of code | 1.3¢$12.64 / 1,000 | 4,805 in · 2,611 out | 170 of 336 | estimated |
| Write a SQL query | 0.24¢$2.40 / 1,000 | 274 in · 708 out | 175 of 336 | estimated |
| Run a 50-step coding agent | $2.32$2,315 / 1,000 | 2,241,975 in · 15,030 out · 9,350 reasoning | 298 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Hermes 4 405B through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 Nebiusfp8 | $1.00 / $3.00 | - | 131K | 100% |
Price history
First seen in our price history on Sep 4, 2025 at $0.20 input / $0.80 output. Since then the output price moved from $0.80 to $3.00 per 1M tokens (3 changes).
FAQ
How much does Hermes 4 405B cost?
Hermes 4 405B costs $1.00 per 1 million input tokens and $3.00 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.30¢ and summarizing a 20-page PDF about 1.5¢.
Where is Hermes 4 405B cheapest?
Among 1 providers we track, the lowest list price today is at Nebius: $1.00 input and $3.00 output per 1M tokens.
Is the Hermes 4 405B cost per task measured or estimated?
Estimated: Hermes 4 405B was not run directly. Tokens come from MiniMax M3 and are rescaled by the tokenizer of Nous Research. Real usage can differ.