Packaging change·Jan 5 → Jan 13, 2026·Week 3, 2026·Marketing & Content
Fireworks Unifies Cached Pricing at 50% Across All Text and Vision Models
What changed
Package change
Cached pricing display restructured: per-row cached prices removed from all model rows. Unified footnote now states cached input tokens are 50% for all text and vision models. Previous Qwen3 VL series exception removed.
Before and after
Jan 5, 2026 vs Jan 13, 2026Pulse.
100%
What changed
Cached pricing display restructured: per-row cached prices removed from all model rows. Unified footnote now states cached input tokens are 50% for all text and vision models. Previous Qwen3 VL series exception removed.
Sign in to view the full comparison
See the before/after screenshots and every marked-up change.
Q4 2025 · Fireworks Pricing Restructured: DeepSeek R1 0528 Sees 55% Input and 32.5% Output Price ReductionFireworks overhauls AI model lineup with GLM-5 and MiniMax M2 additions · Week 8, 2026
More from Fireworks
Full history →- Week 40, 2026·packagingFireworks adds GLM 5.3 Flash with 200K context, per-token training pricing
- Week 37, 2026·improvedFireworks rebuilds Serverless Training API catalog: drops Qwen 3.5 9B, adds DeepSeek V4 Flash and Muse Glimmer 30B
- Week 34, 2026·increaseFireworks: On-Demand GPU pricing up 11-30% from Sep 1; region surcharge to 1.5x
- Week 33, 2026·improvedFireworks: New GB300 GPU tier ($18/hr) + region premium pricing
- Week 32, 2026·packagingFireworks: New Serverless Training API added (Qwen 3.5 9B, 3.6 27B, Kimi K3)