Replacement for veo-2.0-generate-001: what changes when you switch

veo-2.0-generate-001 to veo-3.1-generate-001

Some values not published Checked 2026-10-23.

Price per 1M tokens

Context and max output

Capabilities that differ

No differing capability values are published for both models.

API changes

• The Veo guide shows client.models.generate_videos and POST https://generativelanguage.googleapis.com/v1beta/models/{model}:predictLongRunning. The sample uses that call and only swaps the model id. These two records are Vertex ids. The guide is the Gemini API page, so the curl host is generativelanguage.googleapis.com. Source

Code

from google import genai
client = genai.Client()
operation = client.models.generate_videos(
    model="veo-2.0-generate-001",
    prompt="A close up of two people staring at a cryptic drawing on a wall, torchlight flickering.",
)

from google import genai
client = genai.Client()
operation = client.models.generate_videos(
    model="veo-3.1-generate-001",
    prompt="A close up of two people staring at a cryptic drawing on a wall, torchlight flickering.",
)

import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
let operation = await ai.models.generateVideos({
  model: "veo-2.0-generate-001",
  prompt: "A close up of two people staring at a cryptic drawing on a wall, torchlight flickering.",
});

import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({});
let operation = await ai.models.generateVideos({
  model: "veo-3.1-generate-001",
  prompt: "A close up of two people staring at a cryptic drawing on a wall, torchlight flickering.",
});

curl -s "https://generativelanguage.googleapis.com/v1beta/models/veo-2.0-generate-001:predictLongRunning" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -X POST \
  -d '{"instances":[{"prompt":"A close up of two people staring at a cryptic drawing on a wall, torchlight flickering."}]}'

curl -s "https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-generate-001:predictLongRunning" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -X POST \
  -d '{"instances":[{"prompt":"A close up of two people staring at a cryptic drawing on a wall, torchlight flickering."}]}'

Checklist

1. Read the shutdown date for veo-2.0-generate-001 on the linked official page.
2. Point your requests at veo-3.1-generate-001.
3. Re-check price, context, and parameters on the provider pages linked here.
4. Ship the change before the published shutdown date.