GLM-5.1
Shutting down. GLM-5.1 shuts down on Azure AI Foundry on Jul 1, 2027.
9 mo- Next shutdown
- 260 daysJul 1, 2027 · Azure AI Foundry
- Arena Text
- 1,464#29 of 128 · Arena
- GPQA Diamond
- 89.9%#38 of 108 · Epoch AI
- Released
- Apr 7, 2026Z.ai (GLM)
Dates on every platform
2 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-GLM-5.1:1Active | – | 9 mo | – |
| Together AITogether AI: Changelog (opens in a new tab) · checked Oct 14, 2026 | zai-org/GLM-5.1Shut down | – | Shut down | – |
Served by Fireworks through Foundry. Fireworks per-token models carry a 15-day retirement notice.
What breaks when you move off GLM-5.1
Intelligence
Third-party results, credited below
| Benchmark | Publisher | Score | Rank | Published |
|---|---|---|---|---|
| Arena Text | Arena | 1,464 ± 2 | #29 of 128 | Oct 8, 2026 |
| GPQA Diamond | Epoch AI | 89.9% ± 2.1% | #38 of 108 | Aug 10, 2026 |
| Arena WebDev | Arena | 1,508 ± 4 | #31 of 69 | Oct 8, 2026 |
| FrontierMath Tiers 1-3 | Epoch AI | 36.8% ± 2.9% | #52 of 71 | Aug 29, 2026 |
| OTIS Mock AIME 2024-2025 | Epoch AI | 93.3% ± 3.8% | #38 of 105 | Aug 10, 2026 |
| SimpleQA Verified | Epoch AI | 34.0% ± 1.5% | #48 of 68 | Aug 27, 2026 |
| SWE-bench Verified | Epoch AI | 74.2% ± 2.0% | #13 of 28 | May 15, 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].
Change history
ShutdownQwen3 235B Instruct 2507 throughput, Llama 3 8B Lite and GLM-5.1 leave Together serverlessTogether AI1 break
Together removed Qwen/Qwen3-235B-A22B-Instruct-2507-tput, meta-llama/Meta-Llama-3-8B-Instruct-Lite and zai-org/GLM-5.1 from serverless inference.
- Platform
- Together AI
- AvailabilityRequests to the removed serverless model ID fail. The model can still run on an on-demand dedicated endpoint, billed per minute.
Source: Together AI, Changelog (opens in a new tab); Together AI, Deprecations (opens in a new tab)