GPT-5 nano
Shutting down. The gpt-5-nano-2025-08-07 version of GPT-5 nano shuts down on the OpenAI API on Dec 11, 2026. OpenAI names GPT-5.6 Luna as the replacement for that version.
58 days- Next shutdown
- 58 daysDec 11, 2026 · OpenAI API
- Arena Text
- 1,337#101 of 128 · Arena
- GPQA Diamond
- 69.4%#77 of 108 · Epoch AI
- List price · $ per 1M
- $0.05 in $0.40 outOpenAI API · cached input $0.005
- Context window
- 400KMax output 128K 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 | gpt-5-nanoActive | – | None set | – |
| OpenAI APIOpenAI: Deprecations (opens in a new tab) · checked Oct 14, 2026 | gpt-5-nano-2025-08-07Deprecated | 58 days | GPT-5.6 Luna | |
| Azure AI FoundryMicrosoft: Model retirement schedule - Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026 | gpt-5-nano:2025-08-07Active | – | 4 mo | – |
Points to gpt-5-nano-2025-08-07. The models API lists no shutdown date for this alias; gpt-5-nano-2025-08-07 shuts down on 11 December 2026.
Microsoft names a replacement about 90 to 120 days before retirement.
What breaks when you move off GPT-5 nano
- Availability
- Availability
- Parameters
- Defaults
- Pricing
Intelligence
| Benchmark | Publisher | Score | Rank | Published |
|---|---|---|---|---|
| Arena Text | Arena | 1,337 ± 4 | #101 of 128 | Oct 8, 2026 |
| GPQA Diamond | Epoch AI | 69.4% ± 2.8% | #77 of 108 | Oct 30, 2025 |
| FrontierMath Tier 4 | Epoch AI | 2.4% ± 2.4% | #55 of 58 | Jun 12, 2026 |
| FrontierMath Tiers 1-3 | Epoch AI | 20.0% ± 2.4% | #62 of 71 | Jun 12, 2026 |
| OTIS Mock AIME 2024-2025 | Epoch AI | 81.1% ± 4.6% | #61 of 105 | Oct 31, 2025 |
| SimpleQA Verified | Epoch AI | 11.7% ± 1.0% | #64 of 68 | Aug 10, 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 APIgpt-5-nano | $0.05 | $0.005 | $0.40 | Oct 14, 2026Current · Batch and Flex bill less; Fast mode bills more. | OpenAI: Pricing (opens in a new tab) |
OpenAI APIgpt-5-nano-2025-08-07 | $0.05 | $0.005 | $0.40 | Oct 14, 2026Current · Billed at the gpt-5-nano rate on the pricing page; gpt-5-nano points to this snapshot. | OpenAI: Pricing (opens in a new tab) |
Azure AI Foundrygpt-5-nano:2025-08-07 | $0.05 | $0.005 | $0.40 | Aug 7, 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
ShutdownGPT-5, GPT-5 mini and GPT-5 nano retire on Azure AI FoundryAzure AI Foundry2 breaks
Version 2025-08-07 of gpt-5, gpt-5-mini and gpt-5-nano retires on Foundry, two months after the same snapshots shut down on the OpenAI API.
- Platform
- Azure AI Foundry
- Models
- GPT-5, GPT-5 Mini, GPT-5 nano
- AvailabilityInference requests to retired deployments return 410 Gone.
- AvailabilityMicrosoft has not listed a replacement yet; it names one about 90 to 120 days before retirement. Deployments set to NoAutoUpgrade stop working at retirement.
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)
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)