Baseten adds GLM-5.3 Fast, retires 6 models, cuts DeepSeek V4.1 Flash cache price 77%
What happened
Between the Sep 21, 2026 and Sep 28, 2026 captures of Baseten's pricing page, Pulse recorded 4 changes: New model GLM-5.3 Fast added to the Model APIs price list at $2.10 input / $0.21 cache input / $6.60 output per 1M tokens; DeepSeek V4.1 Flash cache-input price cut from $0.03 to $0.007 per 1M tokens (-77%); input $0.30 and output $1.20 unchanged; GLM 4.7 ($0.60/$0.12/$2.20) and DeepSeek V4 Pro ($1.74/$0.145/$3.48 per 1M tokens) removed from the Model APIs price list; DeepSeek V4 Pro 0813 remain. In detail: GLM 4.7 ($0.60/$0.12/$2.20) and DeepSeek V4 Pro ($1.74/$0.145/$3.48 per 1M tokens) removed from the Model APIs price list; DeepSeek V4 Pro 0813 remains; Kimi K2.6 and Kimi K2.7 Code ($0.95/$0.16/$4.00), Inkling-Small ($0.50/$0.10/$1.20) and Inkling ($1.00/$0.17/$4.05 per 1M tokens) removed from the Model APIs price list; Kimi K3 remains. Pulse files it as a pricing change (add-on removed, price decrease, new add-on) with a downward direction. Pulse's latest capture (Nov 15, 2026) lists Pro at $1, Enterprise at $1 and Basic at $1.32 DeepSeek V4 Pro 0813 input (per 1M tokens) + $0.30 Kimi K3 cache input (per 1M tokens).
This weekly roll-up includes the change Pulse first recorded in a shorter period: "Baseten slashes DeepSeek V4.1 Flash cached input 77% to $0.007 per 1M tokens" (Day 265, 2026, saved Sep 22, 2026). It also records changes none of that period did (add-on removed and new add-on), so Pulse counts it as a change of its own. Before that, Baseten's previous recorded change was "Baseten: added Kimi K3, Inkling-Small & DeepSeek-V4-Flash-0731 model APIs" (Aug 5, 2026). Baseten has been tracked since 2026-02-26.
In the same window Zen Planner, Wodify, Pike13 and Mindbody also changed their AI & Machine Learning pricing pages. Those moves are listed further down, and the Pulse Agent can compare them side by side.
- RemovedProAdd-on
BeforeGLM 4.7 ($0.60/$0.12/$2.20) and DeepSeek V4 Pro ($1.74/$0.145/$3.48 per 1M tokens)
AfterNot listed
- −77%—Price$0.03$0.007
- Add-on removedModel APIsAdd-on
Kimi K2.6 and Kimi K2.7 Code ($0.95/$0.16/$4.00), Inkling-Small ($0.50/$0.10/$1.20) and Inkling ($1.00/$0.17/$4.05 per 1M tokens) removed from the Model APIs price list; Kimi K3 remains.
- AddedModel APIsAdd-onNot listedmodel GLM-5.3 Fast
| Plan | Field | Before | After | Change |
|---|---|---|---|---|
| Pro | Add-on | GLM 4.7 ($0.60/$0.12/$2.20) and DeepSeek V4 Pro ($1.74/$0.145/$3.48 per 1M tokens) | Not listed | Removed |
| — | Price | $0.03 | $0.007 | −77% |
| Model APIs | Add-on | Kimi K2.6 and Kimi K2.7 Code ($0.95/$0.16/$4.00), Inkling-Small ($0.50/$0.10/$1.20) and Inkling ($1.00/$0.17/$4.05 per 1M tokens) removed from the Model APIs price list; Kimi K3 remains. | Add-on removed | |
| Model APIs | Add-on | Not listed | model GLM-5.3 Fast | Added |
Values as written on Baseten's public pricing page in the two captures Pulse compared; where the page states no number, the cells give the wording before and after.
Evidence
The two captures Pulse comparedFull-page captures of Baseten's pricing page (www.baseten.co) from Sep 21, 2026 and Sep 28, 2026; the change is marked around the middle of the page, where price reads $0.03 and then $0.007.
Sign in to see the evidence
The two full-page captures with this change marked up are free with an account.
Baseten, the last 90 days
Full historyDates are the day each change was detected, Eastern time.
- Oct 18, 2026ImprovementBaseten adds DeepSeek V4.1 Flash 1017 at $0.30 input, $1.20 output per 1M tokens
- Oct 17, 2026PackagingBaseten adds Reflection Beam and Meta Muse Spark Open to Model APIs lineup
- Oct 16, 2026PackagingBaseten adds Nemotron 3.5 Super VL at $0.20 per 1M input tokens
- Sep 27, 2026Price decreaseBaseten adds GLM-5.3 Fast, retires 6 models, cuts DeepSeek V4.1 Flash cache price 77% This change
- Sep 22, 2026Price decreaseBaseten slashes DeepSeek V4.1 Flash cached input 77% to $0.007 per 1M tokens
- Aug 5, 2026ImprovementBaseten: added Kimi K3, Inkling-Small & DeepSeek-V4-Flash-0731 model APIs
- Jul 28, 2026ImprovementBaseten: Kimi K3 model added to Model APIs ($3.00/$0.30/$15.00 per 1M)
- Jul 26, 2026Price decreaseBaseten: GLM 5.2 cache-input price cut from $0.26 to $0.14/1M tokens
- Jul 25, 2026Price decreaseBaseten: GLM-5.2 cache input price cut ($0.26→$0.14/1M tokens)
Across AI & Machine Learning in the same window
All AI & Machine Learning changes- Zen PlannerSep 21Zen Planner adds 3 bundled Packages plans, topping out at $348/mo Ultimate
- WodifyAug 4Wodify: Starting price increased $79→$99/month per location
- Pike13Jul 13Pike13: New FAQ discloses per-location billing for franchise networks
- MindbodyJul 13Mindbody Online: Starting price cut $99→$79/mo + AI Concierge now included on Ultimate
Questions about this change
Did Baseten raise prices in September 2026?
No — prices went down. Between Sep 21, 2026 and Sep 28, 2026 UTC Baseten's pricing page showed 1 price cut: $0.03 → $0.007 (−77%).
What changed on Baseten's pricing page between Sep 21, 2026 and Sep 28, 2026 UTC?
Pro add-on removed: GLM 4.7 ($0.60/$0.12/$2.20) and DeepSeek V4 Pro ($1.74/$0.145/$3.48 per 1M tokens); price: $0.03 → $0.007 (−77%); Kimi K2.6 and Kimi K2.7 Code ($0.95/$0.16/$4.00), Inkling-Small ($0.50/$0.10/$1.20) and Inkling ($1.00/$0.17/$4.05 per 1M tokens) removed from the Model APIs price list; Kimi K3 remains; Model APIs add-on added: model GLM-5.3 Fast. Pulse compared the captures it took on Sep 21, 2026 and Sep 28, 2026 UTC; the before/after table above lists each item as written on the page.
How often does Baseten change its pricing?
This weekly roll-up includes the change Pulse first recorded in Day 265, 2026 and also records changes none of them did (add-on removed, new add-on), so Pulse counts it as a change of its own; Pulse recorded 3 other pricing-page changes for Baseten in the 90 days before this one; the previous change was "Baseten: added Kimi K3, Inkling-Small & DeepSeek-V4-Flash-0731 model APIs" on Aug 5, 2026; Baseten has been tracked since 2026-02-26.