llmreference
Together AI

Using Llama 2 7B 32K on Together AI

Implementation guide · Together Llama 2 · Together.ai

ServerlessOpen Source

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 llama-2-7b-32k — 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
llama-2-7b-32k

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="llama-2-7b-32k",
    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

Structured Outputs

About Llama 2 7B 32K

LLaMA-2-7B-32K is an open-source language model engineered by Together, derived from Meta's LLaMA-2 7B. It boasts a unique extended context length of up to 32,000 tokens, which enhances its ability to tackle tasks involving long-range context, such as multi-document question answering and lengthy text summarization. The model integrates optimizations, including FlashAttention-2, to boost inference and training efficiency. It combines pre-training with instruction tuning data for improved task performance and offers fine-tuning examples for specialized applications, like book summarization or multi-document Q&A. This model marks a substantial progress in the domain of large language models, serving as a potent tool for natural language processing tasks 1311.

Model Specs

Released2023-07-18
Parameters7B
Context32K
ArchitectureDecoder Only
Knowledge cutoff2022-09

Provider

Together AI
Together AI

San Francisco, California, United States