Atlas / Models / Nousresearch / Nous: Hermes 4 70B

Nous: Hermes 4 70B✓ Catalog verified

nousresearch/hermes-4-70b

Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either respond directly or generate explicit <think>...</think> reasoning traces before answering. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. Learn more in our docs This 70B variant is trained with the expanded post-training corpus (~60B tokens) emphasizing verified reasoning data, leading to improvements in mathematics, coding, STEM, logic, and structured outputs while maintaining general assistant performance. It supports JSON mode, schema adherence, function calling, and tool use, and is designed for greater steerability with reduced refusal rates.

Input price
$0.13 /1M
Output price
$0.40 /1M
Context
131K
Modalities
text
Released
Aug 26, 2025
Tool calling
Atlas signal
90/100
01

Overview

Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either respond directly or generate explicit <think>...</think> reasoning traces before answering. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. Learn more in our docs This 70B variant is trained with the expanded post-training corpus (~60B tokens) emphasizing verified reasoning data, leading to improvements in mathematics, coding, STEM, logic, and structured outputs while maintaining general assistant performance. It supports JSON mode, schema adherence, function calling, and tool use, and is designed for greater steerability with reduced refusal rates.

Access: available through the official Nousresearch API. Context window: 131K.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Aug 5, 2026
02

Specifications

API identifiernousresearch/hermes-4-70b
ProviderNousresearch
Model typeText LLM
Context window131K catalog
Input modalitiestext
Output modalitiestext
ReleasedAug 26, 2025
TokenizerLlama3
ModeratedNo
Architecture modalitytext->text
Supported parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formattemperaturetop_ktop_p
Source: provider documentation + catalog feedMethodology →
03

Pricing

Live pricing components for nousresearch/hermes-4-70b as published in the catalog.

$0.13
Input /1M
$0.40
Output /1M
Per request
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$1.3e-7$0.13 / 1MPer input token
Completion tokens$4e-7$0.40 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$0.15Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual UnderstandingNot advertisedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool CallingNot advertisedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Nous: Hermes 4 70B
MMLU Signal (Reasoning)
97signal
Coding Signal (HumanEval proxy)
82signal
Math Signal (GSM8K proxy)
92signal
Science Signal (GPQA proxy)
87signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Nous: Hermes 4 70B through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="nousresearch/hermes-4-70b",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Nous: Hermes 4 70B cost?

$0.13 per 1M input tokens and $0.40 per 1M output tokens on the official Nousresearch API.

What is the context window of Nous: Hermes 4 70B?

Nous: Hermes 4 70B supports up to 131K tokens of context.

Does Nous: Hermes 4 70B support tool / function calling?

Nous: Hermes 4 70B does not advertise first-class tool/function calling. Check vendor docs for the latest capabilities.

How do I access Nous: Hermes 4 70B?

Use the official Nousresearch API with the model id `nousresearch/hermes-4-70b`. See the Quick start section above for code examples.