GPT-5 Codex (batch)

GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the docs here Codex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.

ChatOpenAI400k tokens$0.6813 / $5.4503 · 1M

openai/gpt-5-codex:batch

Context
400k tokens
Completion cap
128,000
Tools
Yes
JSON
Yes
Released
2025-09-23

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5-codex:batch",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is GPT-5 Codex (batch)?
GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the docs here Codex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications. GPT-5 Codex (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: openai/gpt-5-codex:batch.
Is GPT-5 Codex (batch) free?
No. Input is $0.6813 per 1M tokens and output is $5.4503 per 1M tokens on Geek Hub (markup included).
What is the context length of GPT-5 Codex (batch)?
GPT-5 Codex (batch) has a 400k tokens context window. It supports up to 128,000 completion tokens.
Does GPT-5 Codex (batch) support tool calling and structured outputs?
GPT-5 Codex (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was GPT-5 Codex (batch) released?
GPT-5 Codex (batch) was released on 2025-09-23.

More models from OpenAI