Skip to main content
⚡ EfficientBudget-Friendly

Codex Mini

by OpenAI

Efficient coding-optimized model powering the OpenAI Codex app

Try OpenAI

Input Price

$1.5

per 1M tokens

Output Price

$6

per 1M tokens

Context Window

200K

tokens (32.768K max output)

Specifications

Release Date2026-02-02
Category⚡ Efficient
Context Window200,000 tokens
Max Output32,768 tokens
ProviderOpenAI
Input Cost$1.5 / 1M tokens
Output Cost$6 / 1M tokens
Price TierBudget-Friendly

Capabilities

textcodereasoning

Related Use Cases

Monthly Cost Estimates

Usage LevelDaily TokensDailyMonthlyYearly
Light~50 requests/day100K in / 20K out$0.27$8.10$99
Medium~200 requests/day500K in / 100K out$1.35$40.50$493
Heavy~1K requests/day2,000K in / 500K out$6.00$180.00$2190
Enterprise~5K requests/day10,000K in / 2,000K out$27.00$810.00$9855

Cost Calculator

Alternatives to Codex Mini

Frequently Asked Questions

How much does Codex Mini API cost per million tokens?
Codex Mini costs $1.5 per million input tokens and $6 per million output tokens as of 2026. These are the standard API rates from OpenAI.
What is the Codex Mini context window?
Codex Mini supports a 200K context window (200,000 tokens), which means you can process up to 200K tokens in a single API call.
How much does Codex Mini cost per month?
At medium usage (~200 requests/day with 500K input and 100K output tokens/day), Codex Mini costs approximately $40.50/month. Light usage runs about $8.10/month, and heavy usage (~1K requests/day) around $180.00/month.
Is there a cheaper alternative to Codex Mini?
Yes — Llama 3.1 405B by Meta (via Together AI) is a cheaper option at $3.5/M input tokens vs $1.5/M for Codex Mini. Other budget alternatives include models in the efficient tier.
Is Codex Mini good for ai agent / agentic workflows?
Codex Mini is a efficient model with support for text, code, reasoning. For ai agent / agentic workflows, it offers 200K context and costs $1.5/M input tokens — a budget-friendly choice for this use case.

Codex Mini Comparisons

Ready to use Codex Mini?

Get started with OpenAI's API — free tier available for most models.

Try OpenAI API →