← All models

GPT-5.1-Codex-Mini

Published Publisher OpenAIgpt-5.1-codex-mini

Overview

GPT-5.1-Codex-Mini is a smaller, more cost-effective, but less capable version of GPT-5.1-Codex. It was designed for agentic coding tasks in Codex or similar environments, including longer-running coding workflows. (developers.openai.com)

Release and availability

Capabilities and limits

  • Accepts text and image input and produces text output; audio and video are not supported.
  • Context window: 400,000 tokens; maximum output: 128,000 tokens.
  • Knowledge cutoff: September 30, 2024. Supports reasoning tokens, streaming, function calling, and structured outputs.
  • The model documentation lists the Responses API as supported, but not Chat Completions, Batch, or fine-tuning. These capabilities describe the model before shutdown, not current availability. (developers.openai.com)

API pricing

The official model page still lists the following USD text-token rates, queried November 17, 2026. These are listed rates for a shut-down model, not an offer of current access:

  • Input: $0.25 per 1 million tokens.
  • Cached input: $0.025 per 1 million tokens.
  • Output: $2.00 per 1 million tokens. (developers.openai.com)

Official sources