models/gemini-2.5-flash is no longer available to new users

Some Gemini API keys get HTTP 404 on gemini-2.5-flash. Google's deprecations page says access to the 2.5 models is limited to users who have actively used them. It says the models are not deprecated.

• This model is no longer available
• gemini-2.5-flash
• gemini-3.8-flash
• Silent failures after a model shutdown

Error text

models/gemini-2.5-flash is no longer available to new users

Quoted from GitHub issue LebgaaAbderrahmane/ecomAssistant#92, checked October 24, 2026.

The issue says Google answers 404 with that message for some API keys, and that older keys still work. The deprecations page says it is limiting access to the 2.5 models to users who have actively used them in the past. It says these models are not deprecated and will continue to be served until further notice through the API. For any new projects it names 3.5 Flash-Lite or 3.8 Flash. The model table on that page uses the ids gemini-3.5-flash-lite and gemini-3.8-flash. The deprecations page does not print the 404 sentence. The issue records the sentence for gemini-2.5-flash. The same access note sits above the gemini-2.5-pro section and the Gemini 2.5 Flash section, which also lists gemini-2.5-flash-lite with no shutdown date announced. A different sentence, recorded for gemini-2.0-flash after that model shut down, is on [This model is no longer available](/errors/gemini-model-no-longer-available/). Source: Gemini API deprecations, checked October 24, 2026.

Affected models

Fix

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -X POST \
  -d '{"contents":[{"parts":[{"text":"Hello"}]}]}'

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.8-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -X POST \
  -d '{"contents":[{"parts":[{"text":"Hello"}]}]}'

import litellm
response = litellm.completion(
    model="gemini/gemini-3.8-flash",
    messages=[{"role": "user", "content": "Hello"}],
)

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

const { text } = await generateText({
  model: google("gemini-3.8-flash"),
  prompt: "Hello",
});

More request errors

• This model is no longer available
• Thinking budget is not supported for this model

All request errors