CodeLlama 34B Instruct
Mid-size CodeLlama. Single-GPU friendly code model from 2023.
CodeLlama 34B Instruct is a efficient AI model from Meta. It costs $0.3500 per million input tokens and $0.3500 per million output tokens (blended $0.3500/M), with a 16,000-token context window.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
Hand-maintained from Meta's published pricing; no check date on record.
- Open weights
- Code-tuned
- Single-GPU
- Self-hosted code completion (legacy)
Benchmarks
More from Meta
See all 20 →Frequently asked questions
How much does CodeLlama 34B Instruct cost?
CodeLlama 34B Instruct costs $0.3500 per million input tokens and $0.3500 per million output tokens, for a blended reference rate of $0.3500 per million tokens.
What is CodeLlama 34B Instruct's context window?
CodeLlama 34B Instruct supports up to 16,000 tokens of context in a single request.
What is CodeLlama 34B Instruct best for?
CodeLlama 34B Instruct is well suited to Open weights, Code-tuned and Single-GPU.
Who makes CodeLlama 34B Instruct?
CodeLlama 34B Instruct is developed and served by Meta. It was released in Aug 2023.
