Hermes 4 405B
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research.
Hermes-4-405BReleased 26 Aug 2025 (Aug 2025)Pricing
List prices at Nebius AI Studio, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.00 | $3.00 | |
| Cached input 80% off input | $0.20 | 80% off input |
What it costs a month
At Nebius AI Studio list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$453
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$396
- Coding agent1,000 requests a day, 40K in / 2K out, cached$708
- Overnight batch20,000 requests a day, 4K in / 0.4K out$3,120
Where to run it
1 host serve Hermes 4 405B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Nebius AI StudioInference Hermes-4-405B | $1.00 / $3.00 | Hermes-4-405B |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Open weights
- License: Llama 3 Community LicenseRuns in about 974 GB of GPU memory
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Nebius AI Studio.
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
- 17% less
- 43% less
- 69% less
- 87% less
Open-weight picks
- 42% less
- 43% less
- 46% less
- 47% less
Model line
Newer and older versions, at each lab's own price.
- Aug 2025Hermes 4 405BLatest$1.00 / $3.00
- UndatedHermes3 405B$0.80 / $0.80
Call it
Using Nebius AI Studio's API.
from litellm import completion
response = completion(
model="nebius/Hermes-4-405B",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Hermes 4 405B cost?
On Nebius AI Studio, Hermes 4 405B costs $1.00 per million input tokens and $3.00 per million output tokens. Cached input costs $0.20 per million tokens.
Which APIs offer Hermes 4 405B?
Hermes 4 405B runs on 1 API: Nebius AI Studio.
What is Hermes 4 405B's context window?
131K tokens, with up to 131K tokens in one reply.
Is Hermes 4 405B being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Hermes 4 405B?
No. Hermes 4 405B is the newest model in its line.
What are cheaper alternatives to Hermes 4 405B?
Models that cost less and keep most of what it can do: Grok Build 0.1 on xAI (17% less), Gemini 3.5 Flash Lite on Google AI Studio (43% less) and Motif 3 on ai& (42% less). Savings are on a mix of 3 input tokens to 1 output token.
When was Hermes 4 405B released?
Independent released it on 26 Aug 2025.
What is Hermes 4 405B's API model id?
Use Hermes-4-405B with Nebius AI Studio.
Sources
Raw catalog entry for Hermes-4-405B on Nebius AI Studio
{
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 0.000001,
"output_cost_per_token": 0.000003,
"litellm_provider": "nebius",
"mode": "chat",
"supports_function_calling": true,
"supports_reasoning": true,
"source": "https://tokenfactory.nebius.com/api/public/models_info",
"cache_read_input_token_cost": 2e-7
}