GLM-5
Shutting down. GLM-5 shuts down on Google Vertex AI on Oct 21, 2026. Z.ai (GLM) names GLM-5.2 as the replacement.
7 days- Next shutdown
- 7 daysOct 21, 2026 · Google Vertex AI
- Arena Text
- 1,458#33 of 128 · Arena
- GPQA Diamond
- 87.8%#47 of 108 · Epoch AI
- Released
- Feb 12, 2026Z.ai (GLM)
Dates on every platform
| 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-5:1Active | – | 9 mo | – |
| Amazon BedrockAmazon Web Services: Amazon Bedrock ListFoundationModels, us-east-1 (opens in a new tab) · checked Oct 14, 2026 | zai.glm-5Active | – | ≥ 4 moNot sooner than | – |
| Google Vertex AIGoogle Cloud: Open model deprecations (opens in a new tab) · checked Oct 14, 2026 | glm-5-maasDeprecated | 7 days | – | |
| Together AITogether AI: Changelog (opens in a new tab) · checked Oct 14, 2026 | zai-org/GLM-5Shut down | – | Shut down | GLM-5.2 |
| Fireworks AIFireworks AI: GLM-5 model page (opens in a new tab) · checked Oct 14, 2026 | accounts/fireworks/models/glm-5Shut down | – | Shut down | GLM-5.1 |
Served by Fireworks through Foundry. Fireworks per-token models carry a 15-day retirement notice.
Google suggests self-deploying the model from Model Garden or moving to another managed endpoint.
Removed from serverless only; dedicated deployments of this model are unaffected.
What breaks when you move off GLM-5
- Availability
API requests to the retired model IDs fail after the retirement date.
DeepSeek-R1, DeepSeek-V3.2, DeepSeek-V3.1, GLM-5, GLM-4.7, gpt-oss-20b, Kimi K2 Thinking, Llama 3.3 70B Instruct, MiniMax-M2, Qwen3-235B-A22B-Instruct-2507, Qwen3-Coder-480B-A35B-Instruct, Qwen3-Next-80B-A3B-Instruct, Qwen3 Next 80B A3B Thinking · Google Vertex AI ·
- Availability
- Availability
Intelligence
| Benchmark | Publisher | Score | Rank | Published |
|---|---|---|---|---|
| Arena Text | Arena | 1,458 ± 2 | #33 of 128 | Oct 8, 2026 |
| GPQA Diamond | Epoch AI | 87.8% ± 2.3% | #47 of 108 | Feb 12, 2026 |
| Arena WebDev | Arena | 1,434 ± 4 | #41 of 69 | Oct 8, 2026 |
| OTIS Mock AIME 2024-2025 | Epoch AI | 80.0% ± 6.0% | #63 of 105 | Feb 12, 2026 |
| SWE-bench Verified | Epoch AI | 72.1% ± 2.1% | #18 of 28 | Feb 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].
List prices
| Platform | Input | Cached | Output | In effect | Source |
|---|---|---|---|---|---|
Amazon Bedrockzai.glm-5 | $1.00 | – | $3.20 | 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) |
Change history
ShutdownDeepSeek, GLM, Kimi, Llama, MiniMax, Qwen and GPT OSS endpoints retire on Agent PlatformGoogle Vertex AI1 break
Google retires its managed endpoints for DeepSeek, GLM, GPT OSS 20B, Kimi K2 Thinking, Llama 3.3 70B, MiniMax M2 and Qwen3 models on Gemini Enterprise Agent Platform. Google suggests self-deploying them from Model Garden.
- Platform
- Google Vertex AI
- Models
- DeepSeek-R1, DeepSeek-V3.2, DeepSeek-V3.1, GLM-5, GLM-4.7, gpt-oss-20b, Kimi K2 Thinking, Llama 3.3 70B Instruct, MiniMax-M2, Qwen3-235B-A22B-Instruct-2507, Qwen3-Coder-480B-A35B-Instruct, Qwen3-Next-80B-A3B-Instruct, Qwen3 Next 80B A3B Thinking
- Announced
- AvailabilityAPI requests to the retired model IDs fail after the retirement date.
Source: Google Cloud, Gemini Enterprise Agent Platform release notes (opens in a new tab); Google Cloud, Open model deprecations (opens in a new tab)
ShutdownGLM-5 leaves Together serverlessTogether AI1 break
Together removed zai-org/GLM-5 from serverless inference and recommends GLM-5.2.
- AvailabilityRequests to the removed serverless model ID fail, and Together does not offer it on on-demand dedicated endpoints.
Source: Together AI, Changelog (opens in a new tab); Together AI, Deprecations (opens in a new tab)
ShutdownFireworks removes eight older models from serverlessFireworks AI1 break
DeepSeek V3.1, DeepSeek V3.2, GLM 4.7, GLM 5, Qwen3 8B, both Qwen3 VL 30B A3B models and Llama 3.3 70B Instruct left serverless. Fireworks named Kimi K2.6, GLM 5.1, GPT-OSS 20B and GPT-OSS 120B as migration targets.
- Platform
- Fireworks AI
- AvailabilityServerless requests to these model IDs stop working after the date. Dedicated deployments are unaffected.