SunsetDiff

Retired Fireworks AI models

15 Fireworks AI model records have status retired, sorted by shutdown date. The stored status is retired. The dataset records these models as already shut down. Every record on this page has a shutdown date. Each row links the model page and the replacement page. The official page is https://docs.fireworks.ai/updates/changelog. The model page records the day that page was checked. Last updated 2026-11-10, the dataset version (the newest changelog date). See all retired models. What retired means is on Retired.

Fireworks AI: 15 retired models, sorted by shutdown date.
ModelShutdownReplacement
DeepSeek V4 Pro
accounts/fireworks/models/deepseek-v4-pro
Changelog section: Serverless deprecation: MiniMax M2.7, GPT OSS 20B, Kimi K2.6 Turbo/Fast, Kimi K2.7 Code Fast, DeepSeek V4 Pro.
2026-08-27
source, checked 2026-11-12
accounts/fireworks/models/deepseek-v4-pro-0813 (official)
GPT OSS 20B
accounts/fireworks/models/gpt-oss-20b
Changelog section: Serverless deprecation: MiniMax M2.7, GPT OSS 20B, Kimi K2.6 Turbo/Fast, Kimi K2.7 Code Fast, DeepSeek V4 Pro.
2026-08-27
source, checked 2026-11-12
accounts/fireworks/models/gpt-oss-120b (official), accounts/fireworks/models/qwen3-8b (official)
MiniMax M2.7
accounts/fireworks/models/minimax-m2p7
Changelog section: Serverless deprecation: MiniMax M2.7, GPT OSS 20B, Kimi K2.6 Turbo/Fast, Kimi K2.7 Code Fast, DeepSeek V4 Pro.
2026-08-27
source, checked 2026-11-12
accounts/fireworks/models/minimax-m3 (official)
DeepSeek V4 Flash (0731)
accounts/fireworks/models/deepseek-v4-flash-0731
Changelog section: Serverless deprecation: DeepSeek V4 Pro (0813), DeepSeek V4 Flash (0731), and related models. Dedicated deployments are unaffected. Changelog section: Upcoming Serverless deprecation: older DeepSeek, GLM, Muse, and Kimi models. This applies only to serverless endpoints, including Fast and US-only Serverless endpoints for models that have those variants.
2026-09-25
source, checked 2026-11-12
accounts/fireworks/models/deepseek-v4p1-flash (official)
DeepSeek V4 Flash Vision Exp
accounts/fireworks/models/deepseek-v4-flash-vision-exp
Changelog section: Serverless deprecation: DeepSeek V4 Pro (0813), DeepSeek V4 Flash (0731), and related models. Dedicated deployments are unaffected. Changelog section: Upcoming Serverless deprecation: older DeepSeek, GLM, Muse, and Kimi models. This applies only to serverless endpoints, including Fast and US-only Serverless endpoints for models that have those variants.
2026-09-25
source, checked 2026-11-12
accounts/fireworks/models/deepseek-v4p1-flash (official)
DeepSeek V4 Pro (0813)
accounts/fireworks/models/deepseek-v4-pro-0813
Changelog section: Serverless deprecation: DeepSeek V4 Pro (0813), DeepSeek V4 Flash (0731), and related models. Dedicated deployments are unaffected. Changelog section: Upcoming Serverless deprecation: older DeepSeek, GLM, Muse, and Kimi models. This applies only to serverless endpoints, including Fast and US-only Serverless endpoints for models that have those variants.
2026-09-25
source, checked 2026-11-12
accounts/fireworks/models/deepseek-v4p1-flash (official)
GLM 5.2
accounts/fireworks/models/glm-5p2
Changelog section: Serverless deprecation: DeepSeek V4 Pro (0813), DeepSeek V4 Flash (0731), and related models. Dedicated deployments are unaffected. The same sentence also names GLM 5.2 Fast, GLM 5.2 Fast US, and GLM 5.2 US. Those names are not linked to model pages, so they are not stored as separate ids. Changelog section: Upcoming Serverless deprecation: older DeepSeek, GLM, Muse, and Kimi models. This applies only to serverless endpoints, including Fast and US-only Serverless endpoints for models that have those variants.
2026-09-25
source, checked 2026-11-12
accounts/fireworks/models/glm-5p3 (official)
Kimi K2.6
accounts/fireworks/models/kimi-k2p6
Changelog section: Serverless deprecation: DeepSeek V4 Pro (0813), DeepSeek V4 Flash (0731), and related models. Dedicated deployments are unaffected. Changelog section: Upcoming Serverless deprecation: older DeepSeek, GLM, Muse, and Kimi models. This applies only to serverless endpoints, including Fast and US-only Serverless endpoints for models that have those variants. Another changelog bullet links Kimi K2.6 Turbo / Fast and the text after it to the same model page, so no separate id is stored.
2026-09-25
source, checked 2026-11-12
accounts/fireworks/models/glm-5p3 (official), accounts/fireworks/models/kimi-k3 (official)
Kimi K2.7 Code
accounts/fireworks/models/kimi-k2p7-code
Changelog section: Serverless deprecation: DeepSeek V4 Pro (0813), DeepSeek V4 Flash (0731), and related models. Dedicated deployments are unaffected. Changelog section: Upcoming Serverless deprecation: older DeepSeek, GLM, Muse, and Kimi models. This applies only to serverless endpoints, including Fast and US-only Serverless endpoints for models that have those variants. Another changelog bullet links Kimi K2.7 Code Fast and the text after it to the same model page, so no separate id is stored.
2026-09-25
source, checked 2026-11-12
accounts/fireworks/models/glm-5p3 (official), accounts/fireworks/models/kimi-k3 (official)
Muse Glimmer 30B
accounts/fireworks/models/muse-glimmer-30b
Changelog section: Serverless deprecation: DeepSeek V4 Pro (0813), DeepSeek V4 Flash (0731), and related models. Dedicated deployments are unaffected. Changelog section: Upcoming Serverless deprecation: older DeepSeek, GLM, Muse, and Kimi models. This applies only to serverless endpoints, including Fast and US-only Serverless endpoints for models that have those variants.
2026-09-25
source, checked 2026-11-12
accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b (official)
DeepSeek V4 Flash (0731) Serverless Training
accounts/fireworks/models/deepseek-v4-flash-0731
Changelog section: Upcoming Serverless Training deprecation: DeepSeek V4 Flash (0731). This change applies only to Serverless Training.
2026-11-02
source, checked 2026-11-12
accounts/fireworks/models/deepseek-v4p1-flash-1017 (official)
GPT OSS 120B
accounts/fireworks/models/gpt-oss-120b
Changelog section: Upcoming Serverless deprecation: GPT OSS 120B, Inkling, Nemotron, and US endpoints for MiniMax M3 and GLM 5.3 Flash. Dedicated deployments and Reserved Throughput are unaffected. This applies only to serverless inference. The changelog says: move to a dedicated deployment of GPT OSS 120B.
2026-11-07
source, checked 2026-11-12
Not published
NVIDIA Nemotron 3 Ultra
accounts/fireworks/models/nemotron-3-ultra-nvfp4
Changelog section: Upcoming Serverless deprecation: GPT OSS 120B, Inkling, Nemotron, and US endpoints for MiniMax M3 and GLM 5.3 Flash. Dedicated deployments and Reserved Throughput are unaffected. This applies only to serverless inference. The changelog says: move to a dedicated deployment of Nemotron Super VL.
2026-11-07
source, checked 2026-11-12
Not published
NVIDIA Nemotron 3.5 Lightning 30B A3B
accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b
Changelog section: Upcoming Serverless deprecation: GPT OSS 120B, Inkling, Nemotron, and US endpoints for MiniMax M3 and GLM 5.3 Flash. Dedicated deployments and Reserved Throughput are unaffected. This applies only to serverless inference. The changelog says: move to a dedicated deployment of Nemotron Super VL.
2026-11-07
source, checked 2026-11-12
Not published
GLM 5.3 Flash
accounts/fireworks/routers/glm-5p3-flash-us
Changelog section: Upcoming Serverless deprecation: GPT OSS 120B, Inkling, Nemotron, and US endpoints for MiniMax M3 and GLM 5.3 Flash. Dedicated deployments and Reserved Throughput are unaffected. This applies only to serverless inference. US endpoint only. The global GLM 5.3 Flash endpoint remains available. Call https://us.api.fireworks.ai and pass one of the US model IDs from the table above as model.
2026-11-07
source, checked 2026-11-12
accounts/fireworks/routers/deepseek-v4p1-flash-1017-us (official)

Questions

How many Fireworks AI models are retired?

15 Fireworks AI model records have status retired.

What is the latest shutdown date among retired Fireworks AI models?

The latest shutdown date on a retired model record is 2026-11-07. 4 retired model records share that date, including GPT OSS 120B (Fireworks AI).

How many retired Fireworks AI models list a replacement?

12 of 15 retired model records list a replacement. The table links each replacement page.

Where does SunsetDiff read the dates for retired Fireworks AI models?

The official page is https://docs.fireworks.ai/updates/changelog. Each model page records the day that page was checked. Dataset version 2026-11-10.