o3
Shutting down. o3 shuts down on Azure AI Foundry on Nov 19, 2026. OpenAI names GPT-5.6 Sol as the replacement.
36 days- Next shutdown
- 36 daysNov 19, 2026 · Azure AI Foundry
- Arena Text
- 1,432#56 of 128 · Arena
- GPQA Diamond
- 81.8%#60 of 108 · Epoch AI
- List price · $ per 1M
- $2.00 in $8.00 outOpenAI API · cached input $0.50
- Context window
- 200KMax output 100K tokens
Dates on every platform
| Platform | Model ID and status | Deprecated | Shuts down | Replacement |
|---|---|---|---|---|
| OpenAI APIOpenAI: List models (GET /v1/models) (opens in a new tab) · checked Oct 14, 2026 | o3Active | – | None set | – |
| OpenAI APIOpenAI: Deprecations (opens in a new tab) · checked Oct 14, 2026 | o3-2025-04-16Deprecated | 58 days | GPT-5.6 Sol | |
| Azure AI FoundryMicrosoft: Model retirement schedule - Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026 | o3:2025-04-16Deprecated | – | 36 days | GPT-5.6 Sol |
Points to o3-2025-04-16. The models API lists no shutdown date for this alias; o3-2025-04-16 shuts down on 11 December 2026.
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 o3
- Parameters
- Defaults
- Pricing
- 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
Intelligence
| Benchmark | Publisher | Score | Rank | Published |
|---|---|---|---|---|
| Arena Text | Arena | 1,432 ± 2 | #56 of 128 | Oct 8, 2026 |
| GPQA Diamond | Epoch AI | 81.8% ± 2.1% | #60 of 108 | Apr 16, 2025 |
| FrontierMath Tiers 1-3 | Epoch AI | 33.3% ± 2.8% | #56 of 71 | Aug 27, 2026 |
| OTIS Mock AIME 2024-2025 | Epoch AI | 84.4% ± 5.5% | #57 of 105 | Aug 7, 2026 |
| SimpleQA Verified | Epoch AI | 49.4% ± 1.6% | #24 of 68 | Aug 27, 2026 |
| SWE-bench Verified | Epoch AI | 62.3% ± 2.2% | #23 of 28 | Feb 12, 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 APIo3 | $2.00 | $0.50 | $8.00 | Oct 14, 2026Current · Batch and Flex bill less; Fast mode bills more. | OpenAI: Pricing (opens in a new tab) |
OpenAI APIo3-2025-04-16 | $2.00 | $0.50 | $8.00 | Oct 14, 2026Current · Billed at the o3 rate on the pricing page; o3 points to this snapshot. | OpenAI: Pricing (opens in a new tab) |
Azure AI Foundryo3:2025-04-16 | $2.00 | $0.50 | $8.00 | Jun 1, 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
ShutdownFirst GPT-5 and o3 snapshots shut down on the OpenAI APIOpenAI API3 breaks
gpt-5-2025-08-07, gpt-5-mini-2025-08-07, gpt-5-nano-2025-08-07, gpt-5-pro-2025-10-06, o3-2025-04-16 and o3-pro-2025-06-10 are removed. OpenAI recommends GPT-5.6 Sol for GPT-5, GPT-5 Pro, o3 and o3-pro, GPT-5.6 Terra for GPT-5 mini, and GPT-5.6 Luna for GPT-5 nano.
- Platform
- OpenAI API
- Models
- GPT-5, GPT-5 Mini, GPT-5 nano, GPT-5 Pro, o3, o3-pro
- 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)
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)