Source URL: https://simonwillison.net/2025/Sep/23/gpt-5-codex/#atom-everything
Source: Simon Willison’s Weblog
Title: GPT-5-Codex
Feedly Summary: GPT-5-Codex
OpenAI half-relased this model earlier this month, adding it to their Codex CLI tool but not their API.
Today they’ve fixed that – the new model can now be accessed as gpt-5-codex. It’s priced the same as regular GPT-5: $1.25/million input tokens, $10/million output tokens, and the same hefty 90% discount for previously cached input tokens, especially important for agentic tool-using workflows which quickly produce a lengthy conversation.
It’s only available via their Responses API, which means you currently need to install the llm-openai-plugin to use it with LLM:
llm install -U llm-openai-plugin
llm -m openai/gpt-5-codex -T llm_version ‘What is the LLM version?’
Outputs:
The installed LLM version is 0.27.1.
I added tool support to that plugin today, mostly authored by GPT-5 Codex itself using OpenAI’s Codex CLI.
The new prompting guide for GPT-5-Codex is worth a read.
GPT-5-Codex is purpose-built for Codex CLI, the Codex IDE extension, the Codex cloud environment, and working in GitHub, and also supports versatile tool use. We recommend using GPT-5-Codex only for agentic and interactive coding use cases.
Because the model is trained specifically for coding, many best practices you once had to prompt into general purpose models are built in, and over prompting can reduce quality.
The core prompting principle for GPT-5-Codex is “less is more.”
I tried my pelican benchmark at a cost of 2.156 cents.
llm -m openai/gpt-5-codex “Generate an SVG of a pelican riding a bicycle"
I asked Codex to describe this image and it correctly identified it as a pelican!
llm -m openai/gpt-5-codex -a https://static.simonwillison.net/static/2025/gpt-5-codex-api-pelican.png \
-s ‘Write very detailed alt text’
Cartoon illustration of a cream-colored pelican with a large orange beak and tiny black eye riding a minimalist dark-blue bicycle. The bird’s wings are tucked in, its legs resemble orange stick limbs pushing the pedals, and its tail feathers trail behind with light blue motion streaks to suggest speed. A small coral-red tongue sticks out of the pelican’s beak. The bicycle has thin light gray spokes, and the background is a simple pale blue gradient with faint curved lines hinting at ground and sky.
Tags: ai, openai, prompt-engineering, generative-ai, llms, ai-assisted-programming, pelican-riding-a-bicycle, llm-reasoning, llm-release, gpt-5, codex-cli
AI Summary and Description: Yes
Summary: The text provides updates on the release and capabilities of the GPT-5-Codex model from OpenAI, highlighting its integration with the Codex CLI and its specialized applications in coding. This is particularly relevant for professionals involved in AI development, including those focusing on AI security and software security, due to its implications for coding practices and tool use.
Detailed Description: The text describes several aspects of the newly released GPT-5-Codex model, emphasizing its suitability for coding and its integration with various tools. Key points include:
– **Model Release and Access**:
– The GPT-5-Codex model has been integrated into the Codex CLI tool and is now accessible through the Responses API, signifying a shift in its usability for developers.
– This model is priced similarly to regular GPT-5, making it economically viable for interactive workflows.
– **Tool Utilization**:
– The model is designed for agentic and interactive coding scenarios, making it a powerful assistant for software-related tasks.
– Users are encouraged to install the `llm-openai-plugin` for optimal functionality with the LLM.
– **Best Practices**:
– The model is specifically trained for coding tasks, meaning that traditional prompt strategies may not be necessary and that “less is more” is the guiding principle for optimal performance.
– Over prompting can potentially degrade output quality, which is critical for developers to consider in practice.
– **Highlighted Use Cases**:
– The text showcases the model’s capabilities through examples, such as generating an SVG and providing alt text for an image, demonstrating its potential in creative programming and design tasks.
– **Tagging and Insights**: The tags at the end further categorize the content within the AI landscape, including prompt engineering and AI-assisted programming, underscoring the model’s relevance in these areas.
In summary, GPT-5-Codex represents an advancement in AI that can significantly enhance programming workflows, making it essential for professionals focused on software security and AI development. The unique features of the model may require updates to existing coding practices, particularly concerning how developers approach interactions with AI tools.