Skip to content

Evaluation and modelsBrief

Gemini 3.1 Flash-Lite and Nano Banana leave in 2027: what to move

Two low-cost Gemini ids have earliest shutdown dates in 2027: the original Nano Banana image model and Gemini 3.1 Flash-Lite. This brief maps each to Google's named replacement and a test plan you can run before either date.

By INFRO Editorial

Published

4 min read

A single amber path on a dark ground forking into two glass branches of slightly different brightness

In short

gemini-2.5-flash-image (original Nano Banana) leaves the Gemini API no earlier than March 15, 2027, and gemini-3.1-flash-lite no earlier than May 7, 2027. Google recommends Nano Banana 2 Lite and gemini-3.5-flash-lite respectively 1; test both on your own traffic before switching.

Key takeaways

  • Both shutdown dates are listed as earliest dates, so treat March 15 and May 7, 2027 as the latest safe cutover starts, not guarantees.
  • Google's named replacements are Nano Banana 2 Lite for gemini-2.5-flash-image and gemini-3.5-flash-lite for gemini-3.1-flash-lite.
  • A same-family replacement still changes outputs: image size, style and refusals for images; length, format and tool behaviour for text.
  • Find every caller first, including old pinned ids in config, then test on a sample of real prompts with explicit pass criteria.
  • Switch by percentage with a fallback to the old id until the shutdown date, then remove the fallback.

What is leaving and when

Two ids on the Gemini API have dated removals. gemini-2.5-flash-image, the original Nano Banana, stops answering no earlier than March 15, 2027, and Google recommends Nano Banana 2 Lite. gemini-3.1-flash-lite stops answering no earlier than May 7, 2027, and Google recommends gemini-3.5-flash-lite.1

Both are listed as earliest shutdown dates. That gives you a floor, not a promise of a later date. The dates also come from Google's Gemini API deprecations page as recorded in a timeline read in October; confirm them on Google's page before you commit a schedule. If you call Gemini through Vertex AI, its lifecycle page governs and may differ.

Current idEarliest shutdownGoogle's replacementWorkload
gemini-2.5-flash-imageMarch 15, 2027Nano Banana 2 LiteHigh-volume image generation and edits
gemini-3.1-flash-liteMay 7, 2027gemini-3.5-flash-liteHigh-volume text: classification, extraction, short generation
Removals covered in this brief, from the INFRO timeline's reading of Google's deprecations page.1

Find every caller first

High-volume pipelines hide old ids. The same model string tends to sit in a worker config, a feature flag default, an eval harness and a fallback list. Grep the repos, then confirm from traffic: group a week of requests by model id and look for the two above, including callers you did not know existed.

Also check what you pin. An id in code that you never revisit is how a shutdown turns into an outage. Keep one place, a route name or config key, that maps your application's purpose ("thumbnail-gen", "ticket-triage") to a model id, so the cutover is one change rather than twenty.

Replacement candidates and what can change

Take Google's named replacement as the first candidate, not the answer.

  • Original Nano Banana to Nano Banana 2 Lite. Same family, so prompts usually carry over, but test the things an image pipeline depends on: output dimensions and aspect ratios, how closely edits follow the instruction, how often the model refuses or returns no image, latency, and the per-image rate your account is billed.
  • Gemini 3.1 Flash-Lite to gemini-3.5-flash-lite. Test output format adherence (JSON validity, label vocabulary), answer length, tool-call behaviour if you use tools, and how often the answer is cut off by a length limit.
  • If the Lite replacement fails your checks, a larger Flash-tier Gemini model is the usual next candidate, and so is a model from another provider. Neither is Google's stated replacement, so run the same test against it and compare cost per accepted result rather than per call.

Check Google's pricing page for current rates on any candidate. Your own contract rate may differ from the list rate.

A short test plan

You need a decision in days, not a research project. Four steps:

  1. Sample. Pull 300 to 1,000 real requests per workload, covering your typical and your worst inputs: long documents, odd languages, edge-case prompts. Keep identical inputs for both models.
  2. Define pass criteria before running. For text: schema-valid output, label agreement with the current model or with human labels on a subset, length within bounds. For images: correct size, no refusals, and a human or judge-model review of a blind side-by-side. If you use an LLM judge, calibrate it first (can an LLM judge be trusted).
  3. Run both, record cost and latency. Compare p50 and p95 latency, failure rate and cost per accepted output.
  4. Shift traffic in steps. Send 5%, then 25%, then 100% to the new id, with the old id as fallback until the shutdown date. Replaying production traffic safely is covered in this brief.
compare.py
import json

def passes(raw: str, allowed: set[str]) -> bool:
    try:
        out = json.loads(raw)
    except ValueError:
        return False
    return out.get("label") in allowed

# run the same sampled prompts through old_id and new_id,
# then compare pass rate, length and latency per id

Where a gateway helps

If your calls already go through a gateway, the cutover is a route edit instead of a deploy. INFRO's model lifecycle records vendor deprecations and shutdown dates, warns organizations still sending a retiring model, and from the shutdown date refuses the call before any provider call, naming the replacement. Model availability from your keys is read every three hours, so a model your key stops listing is no longer offered. Weighted routes and routing rules can send a share of traffic to the new id, and per-request usage records show latency and estimated cost for each side. The INFRO docs (opens in a new tab) list the endpoints, including POST /v1/chat/completions for text and POST /v1/images/generations and POST /v1/images/edits for images.2 You run these on your own provider keys; none of it changes what Google bills you.

Start the tests in the next few weeks. Image quality review takes human time, and the earliest date is March 15.

Questions readers ask

Do these dates apply to Vertex AI?
The dates here are for the Gemini API. Vertex AI keeps its own lifecycle page and dates, and this brief did not confirm Vertex dates for these two ids, so check that page if you call Gemini through Google Cloud.
Can I wait until the day before the shutdown?
Both dates are listed as the earliest shutdown date, so the real date could be later but not earlier 1. Plan to finish testing well before it; a late discovery that the replacement fails your checks leaves no time to choose another model.

From the team that builds it

Where this shows up in INFRO

INFRO is a control plane in front of the provider accounts you already hold. The capabilities below are the parts of it this article touches, each with the documentation that defines its behaviour.

  • Model retirements

    Available with a plan

    INFRO records each vendor's model deprecations and shutdown dates, warns organizations still sending a retiring model, and from the shutdown date refuses it before any provider call, naming the replacement.

  • Model availability from your keys

    Available with a plan

    INFRO reads the model list your own provider key returns every three hours, and stops offering a model your key has stopped listing, with the date it stopped.

  • Health-aware routing

    Available with a plan

    Named routes use priority or weighted targets over your own connections, with health checks, retries and failover.

    Read the documentation for Health-aware routing
  • Routing rules

    Available with a plan

    If-rules on a route send matching requests to their own targets, by metadata, feature, end user, key, project, prompt size, streaming, images, tools or time of day. Failure rules decide per failure kind whether to retry, move on or stop.

    Read the documentation for Routing rules
  • Usage and cost per request

    Available with a plan

    Every request records its model, latency, token or unit counts, and estimated provider cost, queryable by project and key.

    Read the documentation for Usage and cost per request

INFRO accounts are self-serve. Provider usage is billed to you by your providers; INFRO charges a software subscription and takes 0% of model spend. See plans.

Sources

Numbered in order of first citation. Each was opened and checked against the claim on the date shown.

  1. 1.AI updates: what changed, and what changes next (Markdown timeline, updated 29 October 2026) (opens in a new tab) — INFRO. Accessed Nov 5, 2026.
  2. 2.INFRO documentation overview (opens in a new tab) — INFRO. Accessed Nov 5, 2026.

About this article

Read INFRO's AI updates timeline (updated 29 October 2026, which records Google's Gemini deprecations page as read on 2026-10-17 and 2026-10-19) and the INFRO docs overview on 2026-11-05. Google's own deprecations, pricing and changelog pages could not be opened directly in this session, so replacement rates, context limits and feature parity are left out as unconfirmed.

Last checked against its sources on . The next review is due by . No separate named reviewer is recorded for this article.

How articles are written, sourced and corrected is set out in the editorial standards.