MajorGoogle AINew Launchgemini-3.1-flash-lite
Gemini Embedding 2 Model Launch
Google announced the release of gemini-embedding-2-preview, a multimodal embedding model supporting text, image, video, audio, and PDF inputs, replacing the Gemini 3.1 Flash-Lite Preview.
Mar 10, 2026 (UTC)Views:1
Impact Assessment
Cost0
Reliability0
Migration2
Quality4
Compliance0
Alternative models
Directional candidates based on stored listed rates and editorial scenario tags; validate quality and current terms before switching
Candidates with lower listed rates
Mistral NemoMistral
Significant cost savings
$0.02 / $0.03
Stored listed rate / 1M tokens
Listed average about 97% lower
Mistral Nemoopenrouter
Significant cost savings
$0.03 / $0.03
Stored listed rate / 1M tokens
Listed average about 97% lower
Llama Prompt Guard 2 22MGroq
Significant cost savings
$0.03 / $0.03
Stored listed rate / 1M tokens
Listed average about 97% lower
Qwen3-ASR FlashQwen
Significant cost savings
$0.04 / $0.04
Stored listed rate / 1M tokens
Listed average about 96% lower
Voxtral Mini 3B 2507AWS Bedrock
Significant cost savings
$0.04 / $0.04
Stored listed rate / 1M tokens
Listed average about 95% lower
Sources
changelog
Google AI Changelog
Announcing Gemini Embedding 2 , our first fully multimodal embedding model.
Comments
Loading comments...
AI Cost Optimization
Does this change your best option?
Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.