CodeLlama 13B Instruct on Fireworks AI

Code Llama · AI at Meta

ServerlessOpen Weights

Last refreshed 2026-09-18. Next refresh: weekly.

Why use CodeLlama 13B Instruct on Fireworks AI?

Fireworks AI offers CodeLlama 13B Instruct with pay-as-you-go pricing at $0.20/1M input tokens. Fireworks AI offers a generative AI platform as a service, focusing on rapid product iteration and cost-efficient AI deployment.

Input / 1M
$0.20
Output / 1M
$0.20
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install openai
Auth
export FIREWORKS_API_KEY=...
Call
import os
from openai import OpenAI
client = OpenAI(
    api_key=os.environ["FIREWORKS_API_KEY"],
Model ID
accounts/fireworks/models/code-llama-13b-instruct

Request example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["FIREWORKS_API_KEY"],
    base_url="https://api.fireworks.ai/inference/v1"
)
response = client.chat.completions.create(
    model="accounts/fireworks/models/code-llama-13b-instruct",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Gotchas

  • Use provider model ID "accounts/fireworks/models/code-llama-13b-instruct", not the LLMReference slug "codellama-13b-instruct".
  • Fireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".
  • The examples expect FIREWORKS_API_KEY; rename it only if your application config maps the new variable.

Pricing

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

Capabilities

No model capability flags are currently sourced.

About CodeLlama 13B Instruct

CodeLlama 13B Instruct is a specialized generative text model developed by Meta, released on August 24, 2023. Part of the Code Llama family, this 13B parameter model is optimized for instruction-following and code-related tasks. It excels in code completion, infilling, and Python programming, utilizing an auto-regressive transformer architecture. Trained on a diverse dataset similar to Llama 2, it offers robust understanding of programming languages and practices. The model incorporates safety mechanisms to reduce harmful content generation, making it suitable for real-world applications. AI engineers can access and utilize this model through the Hugging Face platform .

Get Started

Model Specs

Released2023-08-24
Parameters13B
Context16k
ArchitectureDecoder Only
Knowledge cutoff2022-09