CodeLlama 70B
codellama-70b
About
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. Intended for both commercial and research use, CodeLlama 70B aims to assist developers in generating code, understanding programming concepts, and enhancing productivity in software development .
CodeLlama 70B has a 16K-token context window.
CodeLlama 70B input tokens at $0.45/1M, output at $0.65/1M.
Capabilities
Providers(6)
Compare all →| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Together AI | $0.9 | $0.9 | Serverless | |
| NVIDIA NIM | — | — | Provisioned | |
| DeepInfra | $0.45 | $0.65 | Serverless | |
| Fireworks AI | $0.90 | $0.90 | Provisioned | |
| Microsoft Foundry | $3.78 | $11.34 | Provisioned | |
| Replicate API | $0.65 | $2.75 | Serverless |
Specifications
Created by
Large-scale open-source AI for social technologies.