GeekRadar / The comparison desk

COMPARE.

AI models

google

Gemini Embedding 2

AI model Released Apr 22, 2026

API mode: Embeddings^*
Context window: 8,192 tokens
Maximum output: 3,072 tokens
Open weights: No

No matched benchmark results are available for this entry yet.

Run it locally

Inference · memory estimate

Gemini Embedding 2

Closed weights. No supported local deployment or GPU requirement is published.

API cost

USD / month

Input tokens / monthOutput tokens / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Gemini Embedding 2

Provider offer

Gemini Embedding 2 / Pricing tiers 1

Provider / scope	Rate	Currency	Amount / unit
GoogleGemini Embedding 2Standard	Audio tokens	USD	6.5 / 1M tokens
	Image tokens	USD	0.45 / 1M tokens
	Input	USD	0.2 / 1M tokens
	Video tokens	USD	12 / 1M tokens

Capabilities

Context window: 8,192 tokens
Maximum input: 8,192 tokens^*
Maximum output: 3,072 tokens
Reasoning: No
Tool calling: No
Open weights: No
Knowledge cutoff: 2025-11
API mode: Embeddings^*

Input modalities

text
image
audio
video
pdf

Output modalities

text

System configuration

Detailed specifications

Specifications · 16 fields

input cost per audio token

6.5e-6^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per audio token batches

3.25e-6^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per image token

4.5e-7^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per image token batches

2.25e-7^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token

2.0e-7^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per token batches

1.0e-7^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per video token

1.2e-5^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

input cost per video token batches

6.0e-6^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

litellm provider

vertex_ai-embedding-models^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max input tokens

8,192^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

max tokens

8,192^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

mode

embedding^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output cost per token

0^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

output vector size

3,072^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

supports multimodal

Yes^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

uses embed content

Yes^*

Scope and conditions

native_context

provider: vertex_ai-embedding-models^*
mode: embedding^*
full_native_model_id: gemini-embedding-2^*
pricing_scope: Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.^*

* Provisional data