Where is the Gemini Embedding 2 documentation?

The Gemini Embedding 2 documentation on OpenRouter includes the Reranking in RAG: How to Fix Bad Retrieval with a Reranker blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

How much does Gemini Embedding 2 cost?

Gemini Embedding 2 costs $0.20/M tokens for Text Input, $0.45/M tokens for Image Input, $0.45/M tokens for File Input, $6.50/M tokens for Audio Input, and $12.00/M tokens for Video Input.

How much text can Gemini Embedding 2 process at once?

Gemini Embedding 2 accepts up to 8,192 tokens per input. Longer text has to be split into multiple inputs.

What inputs and outputs does Gemini Embedding 2 support?

Gemini Embedding 2 accepts text, images, files such as PDFs, audio, and video as input and returns embedding vectors.

Which providers serve Gemini Embedding 2?

Gemini Embedding 2 is served by 2 providers on OpenRouter: Google Vertex and Google AI Studio. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was Gemini Embedding 2 released?

Gemini Embedding 2 was released on May 20, 2026.

Google: Gemini Embedding 2

google/gemini-embedding-2

Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports input context up to 8,192 tokens and flexible output dimensions from 128 to 3,072 (recommended: 768, 1536, or 3,072). Designed for cross-modal similarity — you can embed a text query and retrieve the most relevant images, or vice versa — making it well-suited for multimodal search, recommendation, and document understanding pipelines.

Modalities

Price

$0.20/M tokens

Context

Released

May 20, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency


	$0.45	$6.50	$12.00	0.36s	100.00%
	$0.45	$6.50	$12.00	0.32s	100.00%
	$0.45	$6.50	$12.00	0.17s	100.00%
Not used in Standard routing:Why these endpoints are not used
	$0.495	$7.15	$13.20	0.14s	100.00%

Image $0.45Audio $6.50
0.36s latency100.00% uptime
Image $0.45Audio $6.50
0.32s latency100.00% uptime
Image $0.45Audio $6.50
0.17s latency100.00% uptime
Not used in Standard routing:Why these endpoints are not used
Image $0.495Audio $7.15
0.14s latency100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.2924/M tokens

Output

$0/M tokens

Gemini Embedding 2 — Price history

Price history

No effective price data for this selection

	$0.225	$0.00	0.0%	0.6%
	$0.243	$0.00	0.0%	61.5%
	$0.398	$0.00	0.0%	32.4%
Not used in Standard routing:Why these endpoints are not used
	$0.226	$0.00	0.0%	5.5%

Effective in $0.225Effective out $0.00
Token share
0.6%
Effective in $0.243Effective out $0.00
Token share
61.5%
Effective in $0.398Effective out $0.00
Token share
32.4%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.226Effective out $0.00
Token share
5.5%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.99%

Availability over the last 3 days

Last 72 hours

Availability 99.99%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.99%

Without Routing

99.99%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Available through EU in-region routing

Google: Gemini Embedding 2 is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).

Providers in Europe: Google Vertex
Base URL: https://eu.openrouter.ai/api/v1
Plan: Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing

Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs

More models from Google

Gemini 4 Hydrogen

Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than Gemini 4 Carbon. It takes text, image, audio, video and file input, supports long decode of up to 1M output tokens through continuation, and controls thinking depth with low, medium, high and xhigh reasoning effort.

Text1.0M context$1.50 / $7.50

Gemini 4 Hydrogen (batch)

Text1.0M context$0.75 / $3.75

Gemini Decision 1

Gemini Decision 1 is Google's model for the Decisions API. It answers structured questions about an input state (true/false, multiple choice with up to 255 options, and score with up to 255 levels) and returns a confidence for every answer, plus a legend and probabilities for score questions.

It reads text, images, audio, video, and documents (PDF, CSV, and Office files) sent inline as base64 or by public URL. Every question needs instructions.

Decisions$0.10 / $0

Gemini 4 Carbon

Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode of up to 1M output tokens through continuation, and controls thinking depth with low, medium and high reasoning effort.

Text1.0M context$2 / $10

Gemini 4 Carbon (batch)

Text1.0M context$1 / $5

Gemini Omni 1.2 Flash

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 audio in 16:9 or 9:16, from 360p drafts up to 4K, and supports text-to-video, image-to-video, first and last frame interpolation, subject and video references with improved reference management, and editing or extending an uploaded video. Multi-turn editing and extension of a prior generation is supported through previous_job_id.

Note: video generation is only supported through the Video Generation API. See the guide: https://openrouter.ai/docs/guides/overview/multimodal/video-generation

Text131K context$1.50 / $9

Gemini Omni 1.1 Flash

Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. It is suited for text-to-video, image-to-video, first and last frame interpolation, subject and video references (up to three reference clips), and editing or extending an uploaded video, and generates clips from 360p drafts up to 4K with native audio in 16:9 or 9:16. Multi-turn editing and extension of a prior generation is supported through previous_job_id, up to 40 seconds of total video.

Note: video generation is only supported through the Video Generation API. See the guide: https://openrouter.ai/docs/guides/overview/multimodal/video-generation

Text131K context$1.50 / $9

Gemini 4 Argon

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.

Text1.0M context$2 / $10

Gemini 4 Argon (batch)

Text1.0M context$1 / $5

Nano Banana 2.1

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization, mask- and ink-based editing, and factual accuracy, and renders photorealistic skin tones, detailed materials, lighting, and coherent backgrounds. It accepts text and image inputs, returns images with optional text, and supports 1K, 2K, and 4K output plus extended aspect ratios via the image_config API Parameter.

Image66K context$1.50 / $30

Gemini 3.5 Transcribe

Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers. Audio can be up to one hour, or 30 minutes when timestamps or diarization are enabled.

Transcription$2 / $12

Gemini 3.8 Flash Lite TTS

Gemini 3.8 Flash Lite TTS is a text-to-speech model from Google and the fast, high-throughput member of the 3.8 TTS family alongside Gemini 3.8 Flash TTS. It is suited for conversational voice-agent pipelines, high-volume read-aloud, and voice replication workloads where latency and cost matter more than maximum expressiveness.

It accepts the same speech configuration as Gemini 3.1 Flash TTS Preview, including the 30 prebuilt studio voices, and supports Google's Voice Design and Voice Replication through voice_... identifiers.

Speech$0.50 / $6

Gemini 3.8 Flash TTS

Gemini 3.8 Flash TTS is a text-to-speech model from Google and the successor to Gemini 3.1 Flash TTS Preview. It is the creative tier of the 3.8 TTS family, suited for narration, character work, and multi-speaker dialogue where voice fidelity, acting nuance, and regional dialect coverage matter more than latency.

It accepts the same speech configuration as its predecessor, including the 30 prebuilt studio voices, and supports Google's Voice Design (custom voices from a text description) and Voice Replication (voices cloned from a short sample) through voice_... identifiers.

Speech$0.50 / $9

Gemini 3.8 Flash

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Text1.0M context$0.75 / $3.75

Gemini 3.8 Flash (batch)

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Text1.0M context$0.375 / $1.875

Gemini 3.7 Flash

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.

Text1.0M context$0.75 / $3.75

Gemini 3.7 Flash (batch)

Text1.0M context$0.375 / $1.875

Gemini 3.6 Flash

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete a task.

Text1.0M context$0.75 / $3.75

Gemini 3.6 Flash (batch)

Text1.0M context$0.375 / $1.875

Gemini 3.5 Flash Lite

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.

Text1.0M context$0.30 / $2.50

Google: Gemini Embedding 2

Providers