Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
Context
131K
131,072 tokens
Max output
118K
117,964 tokens
Input
$1.00
per 1M tokens
Output
$3.00
per 1M tokens
Providers
4
5 listings
Intelligence
7.5
Intelligence Index
Pricing
USD per 1M tokens · listed by Kilo Gateway
| Token type | Standard |
|---|---|
| Input | $1.00 |
| Output | $3.00 |
Lowest input price across providers: $0.30.
Capabilities
ReasoningYes
Effort: none, high
Tool callNo
Structured outputYes
TemperatureYes
AttachmentsNo
Interleaved reasoningYes
Field: reasoning_content
Open weightsYes
ModeratedNo
Input
Text
Output
Text
Benchmarks
Published scores and Design Arena Elo
- Intelligence7.5#180 of 208
- CodingNot scored—
- AgenticNot scored—
- ArenaNot scored—
Rankings
Position on each OneAtlas leaderboard
Providers · 4
5 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Cortecs | hermes-4-405b | 128K | — | 128K | $1.00 | $2.99 | — | — | — | — | — | No | Yes | Yes | No | Aug 26, 2025 |
 Kilo Gateway | nousresearch/hermes-4-405b | 131K | — | 118K | $1.00 | $3.00 | — | — | — | — | — | Yes | No | Yes | Yes | Aug 26, 2025 |
 NanoGPT | NousResearch/hermes-4-405b | 128K | 128K | 8K | $0.30 | $1.20 | — | $0.15 | — | — | — | No | No | Yes | Yes | Aug 26, 2025 |
| NanoGPT | NousResearch/hermes-4-405b:thinking | 128K | 128K | 8K | $0.30 | $1.20 | — | $0.15 | — | — | — | No | No | Yes | Yes | Aug 26, 2025 |
 Nebius Token Factory | NousResearch/Hermes-4-405B | 131K | 120K | 8K | $1.00 | $3.00 | $3.00 | $1.00 | — | — | — | Yes | Yes | Yes | Yes | Aug 26, 2025 |