Free
Free
Google describes EmbeddingGemma 2 as an open model. This listing does not include a hosted API price.
AI models & APIs · Official-source review 2026-10-13
EmbeddingGemma 2 is Google's open embedding model for text, images, audio and video in one vector space, aimed at on-device use.
Developers who need a lightweight open embedding model and can host it themselves. This is not a chatbot subscription.
The source is a Google blog post dated 6 October 2026, not a pricing page. No monthly plan, rate limit or hosted price was stated there. Quality claims on the post were not tested. No hands-on test.
Google's 6 October 2026 post says EmbeddingGemma 2 maps combinations of text, images, audio and video into one embedding space and is intended for on-device use. It is a model release. The post does not sell seats or credits.
What it can do
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Documented positioning | Introducing EmbeddingGemma 2, an open multimodal embedding model optimized for privacy-first use cases | Facts sourced | 2026-10-13 |
| Free access | Google describes EmbeddingGemma 2 as an open model. This listing does not include a hosted API price. | Facts sourced | 2026-10-13 |
| API | The reviewed page is a model announcement, not a priced API product. Check Google's developer docs for download and hosting options. | Facts sourced | 2026-10-13 |
Understand the total cost
Free
Free
Google describes EmbeddingGemma 2 as an open model. This listing does not include a hosted API price.
Ollama provides local and cloud access to open models through a popular runtime and API, emphasizing privacy with prompts that are not stored or trained on. The homepage highlights billions of model downloads and an expanding cloud offering with subscription tiers and pay-as-you-go token pricing.
Explore toolProtoface is an AI video and generative media inference platform offering pay-as-you-go API pricing for video, image, audio, and realtime avatar models, plus Studio and Realtime subscription plans for unlimited or live avatar workloads.
Explore toolMiniMax is an AI company offering multimodal foundation models and consumer products spanning text, video, speech, music, coding, and design. The public site showcases model families such as M3 and H3, links to MiniMax Code and Design, and publishes API access alongside subscription tiers for model usage.
Explore toolThe practical questions
The announcement calls it an open model. It does not list a subscription. Hosting it yourself, or any later Google API price, is separate from this page.
EmbeddingGemma 2 is Google's open embedding model for text, images, audio and video in one vector space, aimed at on-device use.
Google describes EmbeddingGemma 2 as an open model. This listing does not include a hosted API price.. This record lists ongoing free access; check the plan limits before starting.
No paid monthly price is listed; this record treats the product as free to start. See the plan cards for entitlements, billing commitments and seat minimums.
The reviewed page is a model announcement, not a priced API product. Check Google's developer docs for download and hosting options.. API access and subscription access may have different terms; consult the linked sources.
The source is a Google blog post dated 6 October 2026, not a pricing page. No monthly plan, rate limit or hosted price was stated there. Quality claims on the post were not tested. No hands-on test.
No retained pricing changes yet. A current price alone does not establish a historical trend.
Homepage retrieved over HTTPS and editorially summarized; no hands-on vendor application test.
Read original source ↗Plans and USD prices checked on the vendor pricing page
Read original source ↗6 October 2026 announcement of an open multimodal embedding model
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.