Migrate off Gemini 2.5 Pro
DeprecatedGemini 2.5 Pro is deprecated and shuts down on 1 Dec 2026. Google's official replacement is Gemini 3.8 Flash. The cheapest comparable model we track is Llama 4 Scout (17B-16E Instruct) (Meta) at $0.15 per 1M tokens blended.
Last verified: 13 Nov 2026 · sourced from official provider documentation
◎ You're on the watch list. We'll ping you the moment a model launches, changes price, or gets deprecated.
✕ Couldn't subscribe right now — please try again in a moment.
Free forever · no spam · unsubscribe anytime.
Gemini 2.5 Pro → Gemini 3.8 Flash
Moving to Gemini 3.8 Flash means 2.3× cheaper ($3.44 → $1.50 /1M blended).
| Spec | Gemini 2.5 Pro | Gemini 3.8 Flash |
|---|---|---|
| Status | Deprecated | GA |
| Blended price /1M | $3.44 | $1.50 |
| Input / output /1M | $1.25 / $10 | $0.75 / $3.75 |
| Context window | 1.0M | 1.0M |
| Max output | 65.536 | 65.536 |
| Modality | text, image, video, audio, pdf | text, image, video, audio, pdf |
| Knowledge cutoff | Jan 2025 | — |
API string was gemini-2.5-pro → switch to gemini-3.8-flash. See Gemini 3.8 Flash's full spec sheet →
Budget-friendly replacements for Gemini 2.5 Pro
Generally-available models that match Gemini 2.5 Pro's capabilities (and at least half its 1.0M context), ranked by blended price. Every number is computed from official catalog prices.
| Model | Blended /1M | Input / output | Context |
|---|---|---|---|
| Llama 4 Scout (17B-16E Instruct) Meta | $0.15 | $0.1 / $0.3 | 10M |
| Gemini 2.5 Flash-Lite Google | $0.175 | $0.1 / $0.4 | 1.0M |
| Qwen3.5-Flash Alibaba | $0.175 | $0.1 / $0.4 | 1M |
Migrating off Gemini 2.5 Pro
What replaces Gemini 2.5 Pro?
Google's recommended migration for Gemini 2.5 Pro is Gemini 3.8 Flash. The cheapest comparable model in our catalog is Llama 4 Scout (17B-16E Instruct) (Meta) at $0.15/1M blended.
When is Gemini 2.5 Pro shut down?
Gemini 2.5 Pro is deprecated and scheduled to shut down on 1 Dec 2026 (deprecated 2 Nov 2026). Migrate before that date to avoid a 404.
What is the cheapest alternative to Gemini 2.5 Pro?
Llama 4 Scout (17B-16E Instruct) (Meta) is the cheapest generally-available alternative we track that matches Gemini 2.5 Pro's capabilities, at $0.1 per 1M input and $0.3 per 1M output tokens ($0.15/1M blended).
Browse the full deprecation watch → or see Gemini 2.5 Pro's full spec sheet →
Get a heads-up before your model is retired
New models, price cuts, and deprecations — a short email when something actually changes. No spam, unsubscribe anytime.
The last few changes we caught — this is what lands in your inbox:
- New modelGemini 4 Hydrogen launched (GA) - $1.50/$7.50 per MTok, free tier, 1M context
- New modelGemini Decision launched with the new Decisions API - $0.10 per MTok input, zero output tokens; 262K input
- New modelGemini 4 Carbon launched (GA) - $2/$10 per MTok introductory through Nov 30, then $4/$20; 1M context
◎ You're on the watch list. We'll ping you the moment a model launches, changes price, or gets deprecated.
✕ Couldn't subscribe right now — please try again in a moment.
Free forever · powered by the same data on this page.