o4-mini
Shutting down. o4-mini shuts down on the OpenAI API on Oct 23, 2026. OpenAI names GPT-5.6 Terra as the replacement.
9 days- Next shutdown
- 9 daysOct 23, 2026 · OpenAI API
- Arena Text
- 1,391#81 of 128 · Arena
- GPQA Diamond
- 79.6%#63 of 108 · Epoch AI
- List price · $ per 1M
- $1.10 in $4.40 outOpenAI API · cached input $0.275
- Context window
- 200KMax output 100K tokens
Dates on every platform
| Platform | Model ID and status | Deprecated | Shuts down | Replacement |
|---|---|---|---|---|
| OpenAI APIOpenAI: Deprecations (opens in a new tab) · checked Oct 14, 2026 | o4-mini-2025-04-16Deprecated · also o4-mini | 9 days | GPT-5.6 Terra | |
| Azure AI FoundryMicrosoft: Model retirement schedule - Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026 | o4-mini:2025-04-16Deprecated | – | 36 days | GPT-5.6 Terra |
Fine-tuned versions of this model follow the same shutdown date.
Deprecated on Azure: only subscriptions that have already deployed this version can create new deployments.
Standard, Global Standard and Data Zone Standard deployments are upgraded to the replacement at retirement unless versionUpgradeOption is NoAutoUpgrade. Provisioned deployments are not upgraded and must be moved by hand.
What breaks when you move off o4-mini
- Behavior
Standard, Global Standard and Data Zone Standard deployments are upgraded to the replacement automatically unless versionUpgradeOption is NoAutoUpgrade. Provisioned deployments are not upgraded and stop working at retirement.
o1, o1-pro, o3, o3-deep-research, o3-mini, o3-pro, o4-mini · Azure AI Foundry ·
- Availability
- Parameters
- Defaults
- Pricing
Intelligence
| Benchmark | Publisher | Score | Rank | Published |
|---|---|---|---|---|
| Arena Text | Arena | 1,391 ± 2 | #81 of 128 | Oct 8, 2026 |
| GPQA Diamond | Epoch AI | 79.6% ± 2.4% | #63 of 108 | Apr 16, 2025 |
| FrontierMath Tier 4 | Epoch AI | 4.9% ± 3.4% | #52 of 58 | Jun 11, 2026 |
| FrontierMath Tiers 1-3 | Epoch AI | 36.1% ± 2.9% | #53 of 71 | Jun 11, 2026 |
| OTIS Mock AIME 2024-2025 | Epoch AI | 81.7% ± 4.7% | #60 of 105 | Apr 16, 2025 |
| SimpleQA Verified | Epoch AI | 19.6% ± 1.3% | #60 of 68 | Aug 27, 2026 |
Arena (arena.ai), https://arena.ai/leaderboard
Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource].
List prices
| Platform | Input | Cached | Output | In effect | Source |
|---|---|---|---|---|---|
OpenAI APIo4-mini-2025-04-16 | $1.10 | $0.275 | $4.40 | Oct 14, 2026Current · Listed as o4-mini on the pricing page. | OpenAI: Pricing (opens in a new tab) |
Azure AI Foundryo4-mini:2025-04-16 | $1.10 | $0.275 | $4.40 | Apr 16, 2025Current · Global Standard rate from the US East 2 price list. | Microsoft: Azure Retail Prices API (Foundry Models, US East 2) (opens in a new tab) |
Change history
Shutdowno1, o3 and o4-mini models retire on Azure AI FoundryAzure AI Foundry2 breaks
o1, o1-pro, o3, o3-deep-research, o3-mini, o3-pro and o4-mini are deprecated and retire on Foundry. Microsoft lists gpt-5.6-sol as the replacement, or gpt-5.6-terra for o3-mini and o4-mini.
- Platform
- Azure AI Foundry
- BehaviorStandard, Global Standard and Data Zone Standard deployments are upgraded to the replacement automatically unless versionUpgradeOption is NoAutoUpgrade. Provisioned deployments are not upgraded and stop working at retirement.
- AvailabilityInference requests to retired deployments return 410 Gone.
Source: Microsoft, Model retirement schedule - Microsoft Foundry (opens in a new tab); Microsoft, Microsoft Foundry Models lifecycle and support policy (opens in a new tab)
ShutdownLegacy GPT and o-series snapshots shut down on the OpenAI APIOpenAI API3 breaks
Requests to gpt-3.5-turbo-0125, gpt-4-0613, gpt-4-turbo, gpt-4.1-nano, gpt-4o-2024-05-13, o1, o1-pro, o3-mini and o4-mini, and their aliases, fail after the shutdown date. OpenAI names GPT-5.6 Sol, Terra or Luna as the substitute for each. Fine-tuned gpt-3.5-turbo, gpt-4, gpt-4.1-nano and o4-mini models shut down the same day.
- Platform
- OpenAI API
- Models
- GPT-3.5 Turbo, GPT-4, GPT-4 Turbo, GPT-4.1 nano, GPT-4o, o1, o1-pro, o3-mini, o4-mini
- Announced
- ParametersPro snapshots move to gpt-5.6-sol with reasoning.mode set to pro. There is no separate Pro model ID for GPT-5.6.
- DefaultsGPT-5.6 models reuse reasoning across turns by default (reasoning.context all_turns); earlier models default to current_turn.
- PricingGPT-5.6 bills cache writes at 1.25 times the uncached input rate. Replace prompt_cache_retention with prompt_cache_options.ttl.
Source: OpenAI, Deprecations (opens in a new tab); OpenAI, Using GPT-5.6 (opens in a new tab)