Nous Research: Hermes 4 70B

Public pricingIntelligence 79/100Medium memoryTiefes DenkenTool-Nutzung

Nous: Hermes 4 70B ist ein Text-Modell für Schlussfolgern und Problemlösen. Es verbindet tiefes Schlussfolgern und Planen, einen Kontext von 131K tokens und ein kostengünstig-Profil für zuverlässige Arbeit über reasoning, analysis, and hard problem solving.

Input

$0.13/1M

Output

$0.40/1M

Cached

$0.01/1M

Batch

$0.07/1M

Calculate your Hermes 4 70B bill.

Set your workload — see cost at your exact volume.

What would Hermes 4 70B cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Hermes 4 70B at a glance.

Memory

131,072

tokens

Max reply

32,768

tokens

Memory tier

Medium

a long report or a codebase file

Tokenizer

llama3

Released

Aug 2025

Training cutoff

Dec 2024

Availability

Public pricing

Status

active

Benchmarks

Quality benchmarks

Independent evaluations from public leaderboards. Higher is better.

  • aa_intelligence_index

    13

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick Hermes 4 70B

  • Multi-step reasoning, research agents, or hard math.
  • Agentic workflows that call tools or APIs.
  • High-volume workloads where unit cost matters.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.

Alternatives

Similar models to compare.

FAQ

Hermes 4 70B — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, Hermes 4 70B costs roughly $26 per month. Input is $0.13 /1M tokens and output is $0.40 /1M tokens.
Hermes 4 70B has a 131,072-token context window (medium memory — a long report or a codebase file). That means you can fit about 24,576 words of input and history in a single call.
Beyond text generation, Hermes 4 70B supports deep step-by-step reasoning, calling functions / tools, strict JSON output, fine-tuning on your own data. It streams replies by default.
Hermes 4 70B was released in August 2025, with training data cut off around December 2024.
Models in a similar class include Hermes 4 405B, Qwen3 235B A22B Thinking 2507, Qwen3 VL 30B A3B Thinking. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare Hermes 4 70B against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard