Google's Gemini API release notes (Oct 8 entry) deprecate gemini-3.7-flash, with all requests now auto-routed to gemini-3.8-flash; gemini-3.5-flash is likewise routed to gemini-3.6-flash. The deep-research-pro-preview-12-2025 agent shuts down on Oct 23 and must migrate to the 04-2026 versions. Developers began receiving email notices on Oct 10.

Key Takeaways

  • ✓Two model IDs silently re-routed: gemini-3.7-flash → gemini-3.8-flash, gemini-3.5-flash → gemini-3.6-flash
  • ✓Same price: 3.8 Flash paid tier $0.75 in / $3.75 out per 1M tokens through 2026-12-31, then $1.50 / $7.50 from 2027-01-01
  • ✓deep-research-pro-preview-12-2025 shuts down 2026-10-23; migrate to deep-research-preview-04-2026 or deep-research-max-preview-04-2026
  • ✓Deprecations page lists 3.6 Flash with no shutdown date, so 3.7 was replaced before its predecessor
Gemini API deprecates 3.7 Flash and silently routes it to 3.8 Flash; 3.5 Flash moves to 3.6, old Deep Research agent shuts down Oct 23
🖼️Official Media
Click to view high-res
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
See how it ranks on the leaderboard
Full Leaderboard→
💰 Cost & PlansCompare
in: $0.75 / out: $3.75
Compare Plans↗
🛠️ Ecosystem & IDERules
Gemini · Google AI Studio · Deep Research
Setup IDE Rules↗
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
🔗

Project Links & Resources

Direct Access
Direct access to official project resources and documentation
📖
Gemini API release notes (Oct 8, 2026 entry)
ai.google.dev/gemini-api/docs/changelog
↗
📖
Gemini API deprecations
ai.google.dev/gemini-api/docs/deprecations
↗
📖
Gemini Developer API pricing
ai.google.dev/gemini-api/docs/pricing
↗
🔬

In-Depth Technical Analysis

Google's Gemini API release notes (Oct 8, 2026) deprecate gemini-3.7-flash, which only went GA on Aug 13 and was succeeded by 3.8 Flash on Sep 2. Every request to gemini-3.7-flash is now automatically routed to gemini-3.8-flash, and gemini-3.5-flash is routed to gemini-3.6-flash. Developers started receiving email notices on Oct 10.

Because this is a server-side alias rather than a hard shutdown, calls keep succeeding, but the model actually answering has changed, so output style, token usage, reasoning length and tool-calling behavior may shift and eval baselines go stale. The deprecations page still lists 3.6 Flash with no shutdown date, so 3.7 was replaced ahead of its predecessor.

Pricing is unchanged: 3.8 Flash paid tier is $0.75 input / $3.75 output per 1M tokens through Dec 31, 2026, then $1.50 / $7.50. No new benchmarks were published with this change.

Also in the same entry: the deep-research-pro-preview-12-2025 agent shuts down on Oct 23, 2026; switch the agent parameter to deep-research-preview-04-2026 or deep-research-max-preview-04-2026. Action items: pin model strings explicitly, re-run your eval set, and migrate Deep Research before the 23rd.

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗