--- title: "Fireworks AI Older DeepSeek, GLM, Muse and Kimi models removed from Serverless on September 25, 2026: 2026-09-25 | Harbyn" description: "Fireworks AI Older DeepSeek, GLM, Muse and Kimi models removed from Serverless on September 25, 2026, effective Sep 25, 2026; replacement: accounts/fireworks/models/deepseek-v4p1-flash, accounts/fireworks/models/glm-..." canonical: "https://harbyn.com/changes/fireworks/2026-09-12-upcoming-serverless-deprecation-older-deepseek-glm-muse-and-kimi-models" last-updated: 2026-10-08 --- # Fireworks AI Older DeepSeek, GLM, Muse and Kimi models removed from Serverless on September 25, 2026 Markdown version of . Retirement - Fireworks AI. high severity. In effect. History: recorded after the fact. On September 25, 2026 Fireworks removed DeepSeek V4 Flash (0731), DeepSeek V4 Pro (0813), DeepSeek V4 Flash Vision Exp, GLM 5.2 (including GLM 5.2 Fast, Fast US and US), Muse Glimmer 30B, Kimi K2.6 and Kimi K2.7 Code from Serverless, including Fast and US-only Serverless endpoints. Dedicated deployments are unaffected. Fireworks confirmed on September 26 that the removal is in effect. The deadline passed on Sep 25, 2026. ## Facts | Fact | Value | | --- | --- | | Vendor | [Fireworks AI](https://harbyn.com/vendors/fireworks.md) | | Kind | Retirement | | Severity | high | | Status | In effect | | Announced | Sep 12, 2026 | | Effective | Sep 25, 2026 | | Added to Harbyn | Oct 8, 2026 | | Lead time | Recorded after the fact: added 13 days after the deadline | | Model IDs | `accounts/fireworks/models/deepseek-v4-flash-0731`, `accounts/fireworks/models/deepseek-v4-pro-0813`, `accounts/fireworks/models/deepseek-v4-flash-vision-exp`, `accounts/fireworks/models/glm-5p2`, `accounts/fireworks/models/muse-glimmer-30b`, `accounts/fireworks/models/kimi-k2p6`, `accounts/fireworks/models/kimi-k2p7-code` | | Replacement | `accounts/fireworks/models/deepseek-v4p1-flash`, `accounts/fireworks/models/glm-5p3`, `accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b`, `accounts/fireworks/models/kimi-k3`. DeepSeek models to DeepSeek V4.1 Flash; GLM 5.2 to GLM 5.3; Muse Glimmer 30B to NVIDIA Nemotron 3.5 Lightning 30B A3B; Kimi K2.6 and K2.7 Code to GLM 5.3 or Kimi K3. | | Review | Reviewed by a person, extracted by a model | ## Find it in your code ```sh npx harbyn scan ``` The scanner reads your repository on your machine and reports every file and line that uses the identifiers above, with the replacement. Nothing leaves your machine. ## Sources Where this event comes from: the page we read, when we read it, and the hash of that snapshot. - (changelog, fetched 2026-10-08 23:25 UTC, sha256 `1bf88eeee00d5d4f82b23a1df6c1364178076e65d44e23564222916ba51170d0`) ## Related changes ### More from Fireworks AI - [Deployment annotation keys must start with custom/ in the REST API](https://harbyn.com/changes/fireworks/2026-09-08-deployment-tags-and-annotation-api-changes.md) (Breaking change, announced Sep 8, 2026) - [Creating a deployment without a shape will soon require acceptShapelessRisk](https://harbyn.com/changes/fireworks/2026-09-16-new-deployment-creation-flags-deploymentshape-default-and-acceptshapelessrisk.md) (Deprecation, announced Sep 16, 2026) - [Managed RFT paused, no new reinforcement fine-tuning jobs accepted](https://harbyn.com/changes/fireworks/2026-10-01-managed-rft-is-paused-try-rl-on-the-training-api.md) (Breaking change, announced Oct 1, 2026) - [DeepSeek V4 Flash 0731 retires from Serverless Training November 2](https://harbyn.com/changes/fireworks/2026-10-18-upcoming-serverless-training-deprecation-deepseek-v4-flash-0731.md) (Retirement, effective Nov 2, 2026) ### Changes at other vendors - [OpenRouter: arcee-ai/trinity-large-thinking expire 2026-10-26](https://harbyn.com/changes/openrouter/2026-10-23-arcee-ai-trinity-large-thinking-expires-2026-10-26.md) (effective Oct 26, 2026) - [Google Cloud Run and Functions: Node.js 20 runtime decommission](https://harbyn.com/changes/google-cloud/2026-10-08-node-js-20-runtime-decommission.md) (effective Oct 30, 2026) - [Mistral AI: Z.ai GLM 5.2 (zai-glm-5-2) retires on Mistral on October 31, 2026](https://harbyn.com/changes/mistral/2026-09-29-z-ai-glm-5-2-deprecated-and-scheduled-for-retirement.md) (effective Oct 31, 2026) - [GitHub: GitHub Actions: macOS 14 runner image retired on November 2, 2026](https://harbyn.com/changes/github/2026-10-01-github-actions-macos-14-runner-image-retirement.md) (effective Nov 2, 2026) [All upcoming deadlines](https://harbyn.com/deadlines.md)