All Nous Research models
N

Hermes 4 70B

Nous Research · released August 2025

Hermes 4 70B is a Nous Research model with a 131K token context window — about 190 pages of text. It reads Text and replies in Text. It can show its reasoning before it answers.

$0.149

input / 1M tokens

$0.460

output / 1M tokens

131K

context — about 190 pages

0.11¢

a client proposal

Pricing

Input
$0.149 per million tokens
Output
$0.460 per million tokens

Billed from your Alyph wallet. Prices can change when the provider changes theirs — last checked August 9, 2026.

The numbers

Released
August 2025 (2025-08-26)
Context window
131K tokens — about 190 pages
Max output
Not specified
Input
Text
Output
Text
Reasoning
Shows its thinking before answering
Knowledge cutoff
2024-08-31

Cost vs Token Amount

Drag the slider to adjust the split between input and output workload.

80% Input20% Output
free$0.11$0.210 tokens250k500k750k1000k
Hermes 4 70B

Adjust the ratio slider to change how output tokens influence the final price for equivalent workloads.

What a task costs

2K tokens in · 500 tokens out.

Hermes 4 70B

Nous Research

0.05¢

for this task

57% input · 43% output

Full pricing →

Your $5 welcome credit covers about 9,451 of these.

Compare Hermes 4 70B

Closest in price on a typical task:

Questions, answered

How much does Hermes 4 70B cost on Alyph?

Hermes 4 70B costs $0.149 per million input tokens and $0.460 per million output tokens on Alyph. A typical task — 5K tokens in, 800 out — works out to about 0.11¢. Billed from your Alyph wallet, with hard spending limits. Prices can change when the provider changes theirs; this page was last checked on August 9, 2026.

What is Hermes 4 70B's context window?

131K tokens — about 190 pages.

Can Hermes 4 70B read images and files?

Hermes 4 70B is text-only. The canvas still serializes uploads into plain text, so you can work with files — but it cannot see images.

Does Hermes 4 70B show its reasoning?

Yes. Hermes 4 70B can expose its thinking before the final answer, so you can watch how it got there.

Test Hermes 4 70B against GPT-5.6 Luna

One prompt, both models at the same time, the better answer wins. Free to start, with $5 of credit.