gemini-embedding-2 · Google
Google's first multimodal embedding model .
Google's first multimodal embedding model .
On AIHubMix, Gemini Embedding 2 costs $0.2 per million input tokens.
Gemini Embedding 2 accepts text, image, audio and video input.
Gemini Embedding 2 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to gemini-embedding-2 — no other code changes needed.
Gemini Embedding 2 is developed by Google. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Gemini Embedding 2 was released on April 22, 2026 by Google.
Gemini Nano Banana 2.1 (gemini-nano-banana-2.1) is Google's latest high-efficiency image…
Gemini 3.8 Flash-Lite TTS (gemini-3.8-flash-lite-tts) is Google's fast and affordable…
Gemini 3.8 Flash TTS (gemini-3.8-flash-tts) is Google's 3.8 Flash text-to-speech audio…
Gemini 3.8 Flash is Google's most intelligent Flash-series model, designed for…
Gemini 3.7 Flash is Google’s natively multimodal reasoning model for coding, agents, web…
Gemini 3.6 Flash provides sustained frontier-level intelligence optimized for real-world…
Use Gemini Embedding 2 via the AIHubMix unified API — one interface for every major LLM.