Nous Research: Hermes 4 Large

Nous Research: Hermes 4 Large

byNous Research

Hermes 4 Large is a language model from Nous Research released on Aug 26, 2025. It reads text and writes text, with a 128K token context window and up to 8K tokens per reply.

Show more

It costs $0.30 per million input tokens and $1.20 per million output tokens. Cached input bills at $0.15, 50% less than fresh input.

It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.

4 providers serve it, including Nebius Token Factory, NanoGPT and Cortecs.

Modalities
In / out price
$0.30 / $1.20 per 1M
Context
128K
Max output
8K
Released
Aug 26, 2025
Knowledge cutoff
Aug 2024
  • Tool calling
  • Structured output
  • Reasoning
  • Prompt caching
  • Open weights
  • Free to use

Hermes 4 Large pricing

USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.

Input$0.30 / 1M tokens
Output$1.20 / 1M tokens
Cached input (read)$0.15 / 1M tokens

Hermes 4 Large providers

4 providers serve it, including Nebius Token Factory, NanoGPT and Cortecs. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.

ProviderInput /MOutput /MCache read /MContextMax output
Nebius Token Factory$1$3$0.10131K8K
NanoGPT$0.30$1.20$0.15128K8K
Cortecs$0.996$2.99–128K128K
Kilo Gateway$1$3–131K118K

What Hermes 4 Large costs per month

Pick a workload close to yours or type your own volumes.

Hermes 4 Large per month
$28.35
Without caching
$35.10
Per request
$0.0009

Supported request parameters

What you can set when you call Hermes 4 Large through an OpenAI compatible API.

  • Toolstools
  • Structured outputsstructured_outputs
  • Temperaturetemperature

Alternatives to Hermes 4 Large

Models that take the same inputs and call tools, closest in price, cheaper ones first.

  • Index 29.2

    Reads text, images and video. Tool calling, structured output, reasoning. Served by 43 providers.

    by minimaxMay 31, 20261M context$0.30/M input tokens$1.20/M output tokens43 providers

  • Reads text, images and files. Tool calling, structured output, reasoning. Served by 41 providers.

    by openaiJul 9, 2026$0.20/M input tokens$1.20/M output tokens41 providers

  • Reads text. Tool calling, structured output. Served by 10 providers.

    by mistralaiJul 30, 2025$0.30/M input tokens$0.90/M output tokens10 providers

  • Reads text and images. Tool calling, structured output. Served by 7 providers.

    by meta-llamaJan 15, 20251.05M context$0.25/M input tokens$1/M output tokens7 providers

  • Reads text. Tool calling, structured output, reasoning. Served by 5 providers.

    by upstageAug 6, 2026$0.30/M input tokens$1.20/M output tokens5 providers

  • Reads text. Tool calling, structured output, reasoning. Served by 3 providers.

    by minimaxMay 3, 2026$0.30/M input tokens$1.20/M output tokens3 providers

More from Nous Research

  • Reads text. Tool calling, structured output. Served by 4 providers.

    by nousresearchAug 18, 2024$0.70/M input tokens$0.70/M output tokens4 providers

  • Reads text. Tool calling, structured output. Served by 4 providers.

    by nousresearchAug 16, 2024$1/M input tokens$1/M output tokens4 providers

  • Reads text. Tool calling, structured output. Served by 2 providers.

    by nousresearchApr 30, 2024$0.14/M input tokens$0.14/M output tokens2 providers

All Nous Research models

Hermes 4 Large questions

How much does the Hermes 4 Large API cost?

$0.30 per million input tokens and $1.20 per million output tokens, with cached input at $0.15. The estimator on this page turns that into a monthly bill for your own workload.

What is the context window of Hermes 4 Large?

128,000 tokens of input, and it can write up to 8,192 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.

Which providers serve Hermes 4 Large?

4 providers serve it, including Nebius Token Factory, NanoGPT and Cortecs. Prices differ by host, so the Providers table on this page lists each one with its input and output price.

Does Hermes 4 Large support tool calling?

Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.

Is Hermes 4 Large open source?

Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.

When was Hermes 4 Large released?

Aug 26, 2025, with training data up to Aug 2024.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.