Using CodeLlama 70B Instruct on Fireworks AI
Implementation guide · Code Llama · AI at Meta
Fireworks AI exposes CodeLlama 70B Instruct through model ID accounts/fireworks/models/code-llama-70b-instruct. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-09-18. Next refresh: weekly.
Quick Start
- 1
- 2Use the Fireworks AI SDK or REST API to call
accounts/fireworks/models/code-llama-70b-instruct— see the documentation for request format. - 3
Code Examples
pip install openaiFIREWORKS_API_KEYaccounts/fireworks/models/code-llama-70b-instructFireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".
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-70b-instruct",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on Fireworks AI
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.90 |
| Output tokens | $0.90 |
Capabilities
No model capability flags are currently sourced.
About CodeLlama 70B Instruct
CodeLlama 70B Instruct is a large-scale generative text model with 70 billion parameters, specifically designed for code synthesis and understanding tasks. Fine-tuned to follow user instructions effectively, it excels in interactive coding environments, supporting tasks such as code completion, infilling, and explanation. The model is optimized for efficient processing and is suitable for both commercial and research applications in English and various programming languages. While it offers advanced capabilities for AI-assisted coding, it's important to note that it doesn't support long contexts of up to 100k tokens, which may limit its use with extensive codebases.