No longer supported
This model is retired (released August 2021) and is no longer actively maintained or recommended by OpenAI. Consider using their current flagship model instead.
by OpenAI· Released August 2021· Cutoff June 2021
Codex cushman-001 is a legacy model from OpenAI's Codex series, specialized in translating natural language into code. It is a smaller, faster variant of the Codex davinci-002 model, designed for efficient code generation tasks. This model has been retired and replaced by newer GPT-3.5 and GPT-4 models with broader capabilities.
Input cost
$0.12 per 1K tokens
Output cost
$0.12 per 1K tokens
Context window
2048 tokens
Max output
2048 tokens
Modalities
License
proprietary
Efficient code generation and completion tasks requiring lower latency and cost.
