AI Model Watch
Models / OpenAI

o3-mini

Retired

Snapshot o3-mini-2025-01-31, including the o3-mini alias, was shut down on 2026-10-23 and OpenAI names gpt-5.6-sol as the replacement. Until 2026-10-24 the row was held at deprecated on OpenAI's own deprecations page, section '2026-04-22: Legacy GPT model snapshots', which stated the shutdown date and the recommended replacement as columns of a table; the date passing on 2026-10-23 was not treated as evidence on its own. Rates read the same day from developers.openai.com/api/docs/pricing (Standard tier), which priced deprecated models; on the 2026-10-24 read the pricing page's own data payload still carries these same rates, so they are kept as the last published ones. Standard-tier rates: input $1.10, cached input $0.55, output $4.40 per 1M. Note that o3-mini and o4-mini carry the same input and output rate but a different cached-input rate - this row's is exactly twice o4-mini's - so which of the two is cheaper depends on cache hit rate. Specs are from developers.openai.com/api/docs/models/o3-mini: 200,000 context window, 100,000 max output tokens, knowledge cutoff Oct 01, 2023, text only in and out. released carries the date embedded in the snapshot id, which is the only release date OpenAI publishes for it. THE DELAY IS OURS, NOT A PROVIDER EVENT: the announcement, the date and the replacement are all OpenAI's, published 2026-04-22; this catalog simply never carried the row. It was added 2026-09-21, 32 days before the shutdown. CONFIRMED RETIRED 2026-10-24. Signal (first-party, past tense): the same section of developers.openai.com/api/docs/deprecations now states "Access to these models was shut down on October 23, 2026." and lists o3-mini-2025-01-31 | o3-mini in its table with substitute gpt-5.6-sol - an executed shutdown, not a scheduled one. The substitute is unchanged.

o3-mini by OpenAI costs $1.10 per 1M input tokens and $4.40 per 1M output tokens ($1.93/1M blended), with a 200K (200.000-token) context window. It has been retired (shut down 23 Oct 2026); the recommended migration is GPT-5.6 Sol.

Last verified: 24 Oct 2026 · sourced from official provider documentation

Retired on 23 Oct 2026 · deprecated since 22 Apr 2026

Lifecycle warning

This model has been retired. Recommended migration: GPT-5.6 Sol.

Read the o3-mini migration guide → replacement & cheapest alternatives

Provider
OpenAI
Status
Retired
Input price
$1.10 / 1M tokens
Output price
$4.40 / 1M tokens
Cached input
$0.55 / 1M tokens
Blended price
$1.93 / 1M tokens
Context window
200.000 tokens (200K)
Max output
100.000 tokens
Modality
text
Open weights
No — API only
Knowledge cutoff
2023-10-01
Released
31 Jan 2025
API string
o3-mini-2025-01-31

Source: OpenAI official documentation ↗

See also

Explore more

All OpenAI models→

Prices, context windows and lifecycle status for every OpenAI model we track.

Compare models head-to-head→

Side-by-side price, context and status for the models developers weigh against each other.

FAQ

o3-mini — questions & answers

How much does o3-mini cost?

o3-mini is priced at $1.10 per 1M input tokens and $4.40 per 1M output tokens ($1.93/1M blended at a 3:1 input-to-output ratio), with cached input at $0.55 per 1M tokens.

What is the context window of o3-mini?

o3-mini has a 200.000-token context window (200K), with up to 100.000 output tokens per request.

Is o3-mini still available?

o3-mini has been retired and is no longer available. Its scheduled shutdown date is 23 Oct 2026. The recommended migration is GPT-5.6 Sol.

Does o3-mini support image or vision input?

Our catalog lists o3-mini's modalities as text; image/vision input is not among them.

Can I self-host o3-mini?

No — o3-mini is proprietary. Its weights are not publicly released, so it is available only through OpenAI's API (or hosted partners), not for self-hosting.

What is the API model string for o3-mini?

The API model identifier for o3-mini is "o3-mini-2025-01-31" when calling OpenAI's API.

What is o3-mini's knowledge cutoff?

o3-mini's training knowledge cutoff is 1 Oct 2023.