llmreference
Together AI

Using OpenHermes 2 Mistral 7B on Together AI

Implementation guide · OpenHermes 2 · Teknium

Serverless

Quick Start

  1. 1
    Create an account at Together AI and generate an API key.
  2. 2
    Use the Together AI SDK or REST API to call openhermes-2-mistral-7b — see the documentation for request format.
  3. 3
    You'll be billed $0.20/1M input, $0.20/1M output tokens. See full pricing.

Code Examples

Install
pip install together
API key
TOGETHER_API_KEY
Model ID
openhermes-2-mistral-7b

Together uses "organization/model-name" format, e.g. "meta-llama/Llama-4-Scout-17B-16E-Instruct" or "Qwen/QwQ-32B". See the Together model catalog for the exact ID.

from together import Together

client = Together()  # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
    model="openhermes-2-mistral-7b",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

About Together AI

Platform for running open-source and proprietary LLMs

Together AI is a platform for running open-source and proprietary LLMs with fast serverless and dedicated endpoints at competitive inference pricing.

Pricing on Together AI

TypePrice (per 1M)
Input tokens$0.20
Output tokens$0.20

Capabilities

No model capability flags are currently sourced.

About OpenHermes 2 Mistral 7B

OpenHermes 2 Mistral 7B is a cutting-edge large language model developed by Teknium. It builds on the Mistral architecture, known for its performance and efficiency, and is fine-tuned to offer significant improvements over prior models. Trained on a diverse dataset of over 900,000 entries, primarily produced by GPT-4, it showcases advanced capabilities in natural language understanding and generation. The model excels in generating high-quality text, engaging in multi-turn conversations, and producing structured outputs. It supports various prompt formats through ChatML, facilitating nuanced interactions. Furthermore, OpenHermes 2 Mistral 7B is available in several quantized formats for optimized performance on different hardware, ensuring compatibility with a wide range of tools and frameworks.

Model Specs

Released2023-12-15
Parameters7B
Context32K
ArchitectureDecoder Only
Knowledge cutoff2023-12

Provider

Together AI
Together AI

San Francisco, California, United States