gpt-oss-120b
Shutting down. The FW-GPT-OSS-120B:1 version of gpt-oss-120b shuts down on Azure AI Foundry on Jul 1, 2027.
9 mo- Next shutdown
- 260 daysJul 1, 2027 · Azure AI Foundry
- Arena Text
- 1,352#96 of 128 · Arena
- GPQA Diamond
- 75.8%#72 of 108 · Epoch AI
- Context window
- 131.1KMax output 131.1K tokens
Dates on every platform
5 listings · a floor is the earliest possible date
| Platform | Model ID and status | Deprecated | Shuts down | Replacement |
|---|---|---|---|---|
| Azure AI FoundryMicrosoft: Model retirement schedule - Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026 | FW-GPT-OSS-120B:1Active | – | 9 mo | – |
| Azure AI FoundryMicrosoft: Model retirement schedule - Microsoft Foundry (opens in a new tab) · checked Oct 14, 2026 | gpt-oss-120b:1Active | – | None set | – |
| Amazon BedrockAmazon Web Services: Amazon Bedrock ListFoundationModels, us-east-1 (opens in a new tab) · checked Oct 14, 2026 | openai.gpt-oss-120b-1:0Active · also openai.gpt-oss-120b, us-gov.openai.gpt-oss-120b-1:0 | – | None set | – |
| Together AITogether AI: Changelog (opens in a new tab) · checked Oct 14, 2026 | openai/gpt-oss-120bActive | – | None set | – |
| Fireworks AIFireworks AI: OpenAI gpt-oss-120b model page (opens in a new tab) · checked Oct 14, 2026 | accounts/fireworks/models/gpt-oss-120bActive | – | None set | – |
Served by Fireworks through Foundry. Fireworks per-token models carry a 15-day retirement notice.
What breaks when you move off gpt-oss-120b
No breaking changes are recorded for gpt-oss-120b.
Intelligence
Third-party results, credited below
| Benchmark | Publisher | Score | Rank | Published |
|---|---|---|---|---|
| Arena Text | Arena | 1,352 ± 2 | #96 of 128 | Oct 8, 2026 |
| GPQA Diamond | Epoch AI | 75.8% ± 2.7% | #72 of 108 | Dec 11, 2025 |
| OTIS Mock AIME 2024-2025 | Epoch AI | 88.9% ± 4.5% | #46 of 105 | Dec 11, 2025 |
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
$ per 1M tokens, with each price’s source
| Platform | Input | Cached | Output | In effect | Source |
|---|---|---|---|---|---|
Azure AI Foundrygpt-oss-120b:1 | $0.15 | – | $0.60 | Mar 1, 2026Current · 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) |
Amazon Bedrockopenai.gpt-oss-120b-1:0 | $0.15 | – | $0.60 | Oct 1, 2026Current · Standard on-demand tier in us-east-1. | Amazon Web Services: AWS Price List API: AmazonBedrock, us-east-1 (opens in a new tab) |
Together AIopenai/gpt-oss-120b | $0.15 | – | $0.60 | Oct 14, 2026Current · Rate listed on the serverless models page on the date checked; Together published no effective date for it. | Together AI: Available models (serverless) (opens in a new tab) |
Fireworks AIaccounts/fireworks/models/gpt-oss-120b | $0.15 | $0.015 | $0.60 | Oct 14, 2026Current · Standard serverless mode. Batch inference is billed at half the Standard rate; Priority, Fast and US-only endpoints cost more. | Fireworks AI: Serverless Pricing (opens in a new tab) |