Hermes 4 405B API

nousresearch/hermes-4-405b
Hermes 4 405B stands out for its seamless integration into a wide range of applications, offering advanced reasoning, structured outputs, and flexible user control.
Context
128K tokens
Input
$1.3754 / 1M tokens
Output
$4.1262 / 1M tokens
Released
Oct 2, 2025

How to use Hermes 4 405B API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to nousresearch/hermes-4-405b.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "nousresearch/hermes-4-405b",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "nousresearch/hermes-4-405b",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nousresearch/hermes-4-405b","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Hermes 4 405B API Pricing

TypePrice
Input
$1.3754 / 1M tokens
Output
$4.1262 / 1M tokens
Cached input
$1.3754 / 1M tokens

Hermes 4 405B Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
LiveCodeBench
61.3%
Contamination-free competitive programming problemsSourceJuly 8, 2026
GPQA Diamond
70.5%
Google-proof graduate science questions (hardest subset)SourceJuly 8, 2026
AIME 2025
78.1%
Competition mathematics (AIME), 2025SourceJuly 8, 2026

Hermes 4 405B vs other models

ModelInputOutputContextBest for
Hermes 4 405B
This page
$1.3754 / 1M tokens
$4.1262 / 1M tokens
128K tokens
Coding + agents
$6.5 / 1M tokens
$39 / 1M tokens
1M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1M tokens
Reasoning + agents

Frequently asked questions

Hermes 4 405B has a 131,072 tokens context window and can return up to 16,000 tokens.

Hermes 4 405B takes text as input and returns text.

Use nousresearch/hermes-4-405b as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

Hermes 4 405B became available on October 2, 2025.

Hermes 4 405B is priced at input $1.3754 / 1M tokens, output $4.1262 / 1M tokens, cached input $1.3754 / 1M tokens.

Yes, Hermes 4 405B can stream responses as they are generated.

Hermes 4 405B was built by NousResearch.

Yes. It can choose to use internal <think> traces for deliberation or respond directly, balancing speed and depth.

It is available via the endpoint https://api.aimlapi.com/v1/chat/completions.

Yes, it supports function calling, parallel tool calls, and structured outputs.

Start building with Hermes 4 405B

Get API Key
1000+ models, one API.