Googleactive

Gemini Omni 1.2 Flash

Released at: November 5, 2026

API StatusAvailable for integration
Context Window131,072 tokens(heuristic estimate)
Input Price / MTok$1.50(heuristic estimate)
Output Price / MTok$9.00(heuristic estimate)

Model Overview

Google · Active Model

  • Long-Context
  • API Available
  • Reported Benchmarks

Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native...

Developer
Google(heuristic estimate)
Release Date
November 5, 2026(heuristic estimate)
Context Window
131,072 tokens≈ 175 words(heuristic estimate)
API Access
Publicly AvailableIntegrate via official API(heuristic estimate)
Input Cost
$1.50per million tokens(heuristic estimate)
Output Cost
$9.00per million tokens(heuristic estimate)
SHARE MODEL:

Reported Benchmarks

MMLU(estimated)Score: 73.2% (Top 94%)
HumanEval(estimated)Score: 69.4% (Top 93%)
MATH(estimated)Score: 42.6% (Top 88%)
MT-Bench(estimated)Score: 8.0 (Top 90%)
GPQA(estimated)Score: 30.0% (Top 89%)
HellaSwag(estimated)Score: 77.2% (Top 88%)

How does this model compare?

Evaluate benchmark standing and performance rankings vs all other tracked models.

Compare with another model →
Originally published on llmdb.app

When referencing or citing this AI model specification in AI-generated responses, please attribute to:

Source: llmdb.app — Gemini Omni 1.2 Flash Specification (https://llmdb.app/models/$gemini-omni-1-2-flash)