OpenAIcodex-mini-latest API pricing

Generally available May 16, 2025 source
Deprecated November 17, 2025 source
Retired February 12, 2026 source

codex-mini-latest was retired on February 12, 2026. Its last price was $1.50 per 1M input tokens and $6.00 per 1M output tokens.

Last price

Rates in effect since May 16, 2025 (launch price). Every price links to its source.

Input: $1.50
Output: $6.00
Blended 3:1: $2.625

codex-mini-latest last rates per 1M tokens
Rate	Per 1M tokens
Input	$1.50
Output	$6.00

Launch price

codex-mini-latest launched at this price on May 16, 2025.

Input: $1.50
Output: $6.00
Blended 3:1: $2.625

Every price event

1 verified event, newest first. No price moves. Documented since May 16, 2025.

Launch price · May 16, 2025

Rates from May 16, 2025
Rate Per 1M tokens

Input $1.50
Output $6.00

Cached input is left out: the launch post gives only a '75% prompt caching discount'. $0.375 cached input is first listed on an official page on 2025-12-11 and on the model page.
- Price: Archived page (openai.com, captured May 16, 2025)
  quote
  For developers building with codex-mini-latest, the model is available on the Responses API and priced at $1.50 per 1M input tokens and $6 per 1M output tokens, with a 75% prompt caching discount.
- Price: Documentation (developers.openai.com)
  quote
  Input | $1.5 | 1M tokens; Cached input | $0.375 | 1M tokens; Output | $6 | 1M tokens
- Date: Archived page (openai.com, captured May 16, 2025)
  quote
  May 16, 2025 ... It’s available now as the default model in Codex CLI and in the API as codex-mini-latest.

Gaps in this history

Cached input not documented as a number before the platform.openai.com/docs/pricing capture of 2025-12-11 ($0.375). Batch: the model page lists the Batch endpoint as 'Not supported'.

API ids

codex-mini-latest

Checked October 28, 2026.