Hermes 4 14B API
About
Build advanced reasoning agents with Hermes 4 14B, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.01/1M input and $0.05/1M output tokens, native tool calling support, open weights architecture. Access Hermes 4 14B via the Chutes API with up to 41K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
Yes
Tool Use
Yes
WeightsOpen
Temperature
Adjustable
Attachment
Not Supported
Limits
Context Window
41K
Tokens
Input Limit
41K
Tokens
Max Output
41K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.01
Output
$0.05
Caching (per 1M tokens)
Read
$0.0068
Frequently Asked Questions
Hermes 4 14B by Chutes costs $0.01 per 1M input tokens and $0.05 per 1M output tokens. Cached reads cost $0.0068 per 1M tokens.
Model Details
ID
NousResearch/Hermes-4-14B
Provider
ChutesFamily
nousresearch
Release Date
Dec 29, 2025
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
CHUTES_API_KEY
API Base URL
https://llm.chutes.ai/v1