mondk/Safetensors.chatgpt-gpt-codex-V2

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:4BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 17, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

The mondk/Safetensors.chatgpt-gpt-codex-V2 model is a language model developed by mondk, claiming to offer cleaner code and faster responses. It was trained using a combination of datasets including mondk/chatgpt-gpt-chat-jsonl, mondk/joke-redteam-safety-dataset, TeichAI/gpt-5.1-codex-max-1000x, and TeichAI/glm-4.7-350x. This model is primarily optimized for code generation, though it notes a slight reduction in code accuracy compared to its claimed ChatGPT base. It aims to provide efficient code outputs for developers.

Loading preview...

Model Overview

mondk/Safetensors.chatgpt-gpt-codex-V2 is a language model developed by mondk, designed with a focus on code generation. It is presented as an alternative to ChatGPT, emphasizing cleaner code outputs and faster response times.

Key Characteristics

  • Code Generation Focus: The model is specifically tailored for generating code, aiming for clarity and efficiency in its outputs.
  • Response Speed: It is noted for providing faster responses, which can be beneficial in interactive development environments.
  • Dataset Diversity: Training involved a mix of datasets, including conversational data (mondk/chatgpt-gpt-chat-jsonl), safety-focused content (mondk/joke-redteam-safety-dataset), and advanced code-centric datasets (TeichAI/gpt-5.1-codex-max-1000x, TeichAI/glm-4.7-350x).

Noteworthy Trade-offs

While aiming for cleaner code and speed, the model acknowledges a "slight drop in code accuracy." Users should consider this trade-off when deploying the model for critical coding tasks where absolute accuracy is paramount.

Use Cases

This model is suitable for developers seeking:

  • Rapid Code Prototyping: Its faster response times can accelerate the initial stages of code development.
  • Code Refinement: The emphasis on "cleaner code" suggests utility in generating more readable and maintainable code snippets.
  • Exploratory Coding: For tasks where a quick, understandable code suggestion is more valuable than absolute, verified correctness.

For those requiring a GGUF format, mondk/GGUF.chatgpt-gpt-codex-V2 is also available.

Finetunes
1 models