llmreference
Together AI

Using Chronos Hermes 13B V2 on Together AI

Implementation guide · Chronos Hermes · Austism

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 chronos-hermes-13b-v2 — see the documentation for request format.
  3. 3
    You'll be billed $0.30/1M input, $0.30/1M output tokens. See full pricing.

Code Examples

Install
pip install together
API key
TOGETHER_API_KEY
Model ID
chronos-hermes-13b-v2

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="chronos-hermes-13b-v2",
    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$0.30
Output tokens$0.30

Capabilities

Structured Outputs

About Chronos Hermes 13B V2

The Chronos Hermes 13B v2 is a sophisticated large language model that merges Chronos and Nous-Hermes-Llama2-13b, striking a balance between imaginative writing and enhanced coherence. This model excels in generating extensive, high-quality prose and maintains context over 4096 tokens, making it ideal for narrative creation and roleplaying. Built on the Llama transformer architecture, it supports both text and code generation. Quantized versions optimize for various hardware, though this often results in trade-offs between accuracy and performance. Despite its capabilities, the model demands considerable RAM and may exhibit repetitive outputs, especially in formats aligned with Alpaca prompts.

Model Specs

Released2023-12-15
Parameters13B
Context4K
ArchitectureDecoder Only

Provider

Together AI
Together AI

San Francisco, California, United States