GPT 5 Codex
Chat
Deprecated
by OpenAI
This model has been deprecated by OpenAI and is no longer available for use. Please explore other available models below.
Overview
GPT-5 Codex is the original GPT-5 coding variant optimized for software engineering tasks. Features adaptive routing between instant answers and deep thinking based on task complexity with strong agentic coding capabilities.
Key Features
- Original GPT-5 coding variant optimized for software engineering and development tasks.
- 400,000-token context window with 128,000 max output tokens and adaptive reasoning.
- Adaptive routing automatically switches between instant answers and deep thinking.
- Supports function calling, structured outputs, and streaming for developer workflows.
- Pricing is $1.25 per 1M input tokens and $10 per 1M output tokens.
Input Capabilities
Text
Image
Document
Technical Specifications
Context Window
400,000
Max Output
128,000
Streaming
Supported
Model Information
Provider: OpenAI
Model Code: gpt-5-codex
Category: Chat
File Support
Max Files
20
Max Size
50MB
Supported Formats
.png
.jpg
.jpeg
.webp
.gif
.pdf
+24 more
Other OpenAI Models
GPT 5.6 SolGPT-5.6 Sol is OpenAI's flagship model in the GPT-5.6 family, released July 9, 2026, for the most complex professional work spanning software engineering, long-horizon research, agentic tool use, and careful result refinement.
GPT 5.6 TerraGPT-5.6 Terra balances capability and cost efficiency for everyday production workloads in the GPT-5.6 family, released July 9, 2026.
GPT 5.6 LunaGPT-5.6 Luna is the fastest, most cost-optimized model in the GPT-5.6 family, released July 9, 2026, built for high-volume and latency-sensitive workloads.