Using CodeLlama 70B on Replicate API
Implementation guide · Code Llama · AI at Meta
Replicate API exposes CodeLlama 70B through model ID codellama-70b. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-07-09. Next refresh: weekly.
Quick Start
- 1
- 2Use the Replicate API SDK or REST API to call
codellama-70b— see the documentation for request format. - 3
Code Examples
pip install replicateREPLICATE_API_TOKENcodellama-70bReplicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
import replicate
# reads REPLICATE_API_TOKEN from env
# codellama-70b format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"codellama-70b",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Pricing on Replicate API
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.65 |
| Output tokens | $2.75 |
Capabilities
About CodeLlama 70B
CodeLlama 70B is a state-of-the-art generative text model by Meta, specifically designed for code synthesis and understanding. It utilizes an auto-regressive transformer architecture and has been fine-tuned with up to 16,000 tokens, supporting inference with up to 100,000 tokens. The model excels in code completion, infilling, and instruction following, making it versatile for various programming languages and applications. With 70 billion parameters, it offers advanced capabilities for general code generation tasks, while also providing specialized variants for Python and instruction-following.