AI Model Watch
Deprecations / Migrate

Migrate off Gemini Embedding Experimental

Retired

Gemini Embedding Experimental has been retired and shut down on 30 Oct 2025. Google's official replacement is Gemini Embedding 2. The cheapest comparable model we track is Llama 3.1 8B Instruct (Meta) at $0.022 per 1M tokens blended.

Last verified: 19 Aug 2026 · sourced from official provider documentation

StatusRetiredGoogle
Shut down30 Oct 2025plan ahead
Official replacementGemini Embedding 2GACheapest alternativeLlama 3.1 8B Instruct$0.022 /M blended
What changes

Gemini Embedding Experimental → Gemini Embedding 2

SpecGemini Embedding ExperimentalGemini Embedding 2
StatusRetiredGA
Blended price /1M——
Input / output /1M—$0.2 / —
Context window—8K
Max output——
Modalitytexttext, image, video, audio, pdf
Knowledge cutoff——

API string was gemini-embedding-exp → switch to gemini-embedding-2. See Gemini Embedding 2's full spec sheet →

Cheapest alternatives

Budget-friendly replacements for Gemini Embedding Experimental

Generally-available models that match Gemini Embedding Experimental's capabilities, ranked by blended price. Every number is computed from official catalog prices.

ModelBlended /1MInput / outputContext
Llama 3.1 8B Instruct
Meta
$0.022$0.02 / $0.03128K
Amazon Nova Micro
Amazon
$0.061$0.035 / $0.14128K
Command R7B
Cohere
$0.066$0.037 / $0.15128K
FAQ

Migrating off Gemini Embedding Experimental

What replaces Gemini Embedding Experimental?

Google's recommended migration for Gemini Embedding Experimental is Gemini Embedding 2. The cheapest comparable model in our catalog is Llama 3.1 8B Instruct (Meta) at $0.022/1M blended.

Is Gemini Embedding Experimental still available?

No — Gemini Embedding Experimental has been retired (shut down 30 Oct 2025) and is no longer available via Google's API.

What is the cheapest alternative to Gemini Embedding Experimental?

Llama 3.1 8B Instruct (Meta) is the cheapest generally-available alternative we track that matches Gemini Embedding Experimental's capabilities, at $0.02 per 1M input and $0.03 per 1M output tokens ($0.022/1M blended).

Browse the full deprecation watch → or see Gemini Embedding Experimental's full spec sheet →