Revision History
Fireworks AI · 15 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Updated stale funding, valuation, token-volume, revenue, GPU pricing and product-catalog claims after Fireworks' July 2026 Series D and June 2026 deprecation of image and audio inference; corrected the FireAttention V1/V2 descriptions, the RFT launch date, a misattributed Lightspeed memo author and 'inference is the new runtime' quote, misattributed TokenMix benchmark figures, and an incorrect GPT-5 mention in the Microsoft Foundry model list (plus 29 minor fixes)
Version 15 · Nov 2, 2026, 01:15 PM
- Added the Ultrafast preview, its waitlist status and limits of its speed demonstration
Version 13 · Oct 22, 2026, 11:54 PM
- Improve internal links (2026-10-13)
Version 12 · Oct 13, 2026, 10:09 AM
- Added 6 contextual internal links
Version 10 · Jul 23, 2026, 03:06 PM