Skip to content

404 NOT_FOUND error when calling generateContent with uploaded video file on gemini-3-pro-preview model #1220

Description

@kazuyaseki

Note: I suspect this may be a product/backend issue rather than a client library issue, but I'm filing here first to confirm whether there's any SDK-side configuration needed to use Gemini 3 series models.

Environment details

  • Programming language: TypeScript / Node.js
  • OS: macOS (Sequoir 15.4)
  • Language runtime version: Node.js v22.21.0
  • Package version: @google/genai 1.34.0

Steps to reproduce

  1. Initialize GoogleGenAI with an API key (not Vertex AI):
 import { GoogleGenAI, createUserContent, createPartFromUri } from "@google/genai";
 const ai = new GoogleGenAI({ apiKey: "YOUR_API_KEY" });
  1. Call generateContent with a Gemini 3 series model (gemini-3-flash-preview or gemini-3-pro-preview):
 const response = await ai.models.generateContent({
   model: "gemini-3-pro-preview", // or "gemini-3-flash-preview"
   contents: createUserContent([
     createPartFromUri(fileUri, mimeType), // uploaded video file
     "Analyze this video",
   ]),
 });
  1. Observe the error:

Error: ApiError: {"error":{"code":404,"message":"Requested entity was not found.","status":"NOT_FOUND"}}

Expected behavior

The API should return a valid response or a more descriptive error message indicating why the model is unavailable.

Actual behavior

A generic 404 NOT_FOUND error is returned.

Additional context

Questions:

  • Is the Gemini 3 series (gemini-3-flash-preview, gemini-3-pro-preview) currently available via the Gemini API (not Vertex AI)?
  • Are there any specific configurations, regions, or permissions required to access these preview models?
  • If this is a backend availability issue, is there an ETA for general availability via the Gemini API?

Metadata

Metadata

Assignees

Labels

api:gemini-apipriority: p2Moderately-important priority. Fix may not be included in next release.status:awaiting user responseissues requiring a response from the userstatus:staleIssues tagged for cleanup by the stale issue workflow.type: bugError or flaw in code with unintended results or allowing sub-optimal usage patterns.

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions