This model is no longer available

After a Gemini API model is shut down, the deprecations page says the endpoint is no longer available. The 404 sentence below was recorded for gemini-2.0-flash, which shut down June 1, 2026.

Error text

This model models/gemini-2.0-flash is no longer available. Please update your code to use a newer model for the latest features and improvements.

Quoted from GitHub issue google/adk-python#6010, checked October 20, 2026.

Google's deprecations page says that once a model is shutdown, it is completely turned off and the endpoint is no longer available. The October 22, 2026 rows are veo-3.1-lite-generate-preview, veo-3.1-generate-preview, veo-3.1-fast-generate-preview, and gemini-omni-flash-preview, with replacement gemini-omni-1.1-flash. SunsetDiff has not recorded this 404 sentence for those four ids. The Error text block is the message in https://github.com/google/adk-python/issues/6010 for models/gemini-2.0-flash. A different sentence, from https://github.com/googleapis/python-genai/issues/2087, was recorded while new API keys were blocked and the model was not yet shut down for everyone: This model models/gemini-2.0-flash is no longer available to new users. Please update your code to use a newer model for the latest features and improvements. Source: Gemini API deprecations, checked October 20, 2026.

Affected models

The quoted 404 was recorded for gemini-2.0-flash. The October 22, 2026 ids are the upcoming Gemini API shutdown.
Model id	What the source says
`gemini-2.0-flash`	Shut down June 1, 2026. The GitHub issue records the 404 for models/gemini-2.0-flash. Replacement on the deprecations page checked October 20, 2026: gemini-3.6-flash.
`gemini-omni-flash-preview`	Shutdown date October 22, 2026. Replacement: gemini-omni-1.1-flash. The exact 404 sentence is not recorded here for this id.
`veo-3.1-generate-preview`	Shutdown date October 22, 2026. Replacement: gemini-omni-1.1-flash.
`veo-3.1-fast-generate-preview`	Shutdown date October 22, 2026. Replacement: gemini-omni-1.1-flash.
`veo-3.1-lite-generate-preview`	Shutdown date October 22, 2026. Replacement: gemini-omni-1.1-flash.
`gemini-3.6-flash`	Replacement named for gemini-2.0-flash on the deprecations page checked October 20, 2026.
`gemini-omni-1.1-flash`	Replacement named for the October 22, 2026 Gemini API rows.

Fix

Raw SDK

Stop calling the retired model id. For gemini-2.0-flash, the deprecations page checked October 20, 2026 names gemini-3.6-flash. The October 22 rows name gemini-omni-1.1-flash. The sample is a generateContent call, which is the call in the GitHub issue. It is not a Veo video request.

Before

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -X POST \
  -d '{"contents":[{"parts":[{"text":"Hello"}]}]}'

After

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.6-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -X POST \
  -d '{"contents":[{"parts":[{"text":"Hello"}]}]}'

Source: Gemini API deprecations, checked October 20, 2026.

LiteLLM

LiteLLM's Gemini API route is the gemini/ prefix plus the model id. Change the id. The docs show gemini/gemini-2.0-flash as a Gemini API model string.

Python

import litellm
response = litellm.completion(
    model="gemini/gemini-3.6-flash",
    messages=[{"role": "user", "content": "Hello"}],
)

Source: LiteLLM Gemini provider, checked October 20, 2026.

Vercel AI SDK

generateText takes the model id from google(). Use the replacement id from the deprecations page.

TypeScript

import { google } from "@ai-sdk/google";
import { generateText } from "ai";

const { text } = await generateText({
  model: google("gemini-3.6-flash"),
  prompt: "Hello",
});

Source: AI SDK generateText, checked October 20, 2026.

Shutdown pages

Gemini API October 22, 2026 batch

Switch guides

More request errors

Thinking budget is not supported for this model

All request errors

Questions

Which Gemini API models shut down on October 22, 2026?

veo-3.1-lite-generate-preview, veo-3.1-generate-preview, veo-3.1-fast-generate-preview, and gemini-omni-flash-preview. The list is on Gemini API models shutting down October 22, 2026.

Is the 404 sentence verified for those four models?

No. It is verified in a GitHub issue for gemini-2.0-flash. The deprecations page says a shutdown turns the endpoint off. It does not print that 404 sentence.