llmreference
Together AI

Using Together AI CodeLlama-34B-Instruct on Together AI

Implementation guide · Code Llama · AI at Meta

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 together-codellama-34b-instruct — 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
together-codellama-34b-instruct

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="together-codellama-34b-instruct",
    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 Together AI CodeLlama-34B-Instruct

Together AI CodeLlama-34B-Instruct is Meta's Code Llama model. It offers a 100K-token context window with weights openly available for self-hosting.

Model Specs

Released2023-07-18
Parameters34B
Context100k
ArchitectureDecoder Only
Knowledge cutoff2024-03

Provider

Together AI
Together AI

San Francisco, California, United States