Try Bifrost Enterprise free for 14 days.
Request access

gemini-embedding-2 Cost Calculator - Google Gemini

Calculate the cost of using gemini-embedding-2 from Google Gemini for your AI applications

Pricing data last updated:

gemini-embedding-2 Cost Calculator

Mode: Embedding

Max: 8,192 tokens

Cost Breakdown

Input Cost$0.00020000
Total Cost$0.00020000

Pricing Details

Input: $0.0000002000 per token
[ WE'RE OPEN SOURCE ]

Scale with the Fastest LLM Gateway

Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.

Model Specifications

Capabilities

✓Vision
✓Audio Input

Limits

Max Input Tokens8,192
Max Tokens8,192

About gemini-embedding-2

gemini-embedding-2 is an embedding model from Google Gemini, one of 3 embedding models they offer. It is priced at $0.20 per 1M input tokens and $0.0000 per 1M output tokens, ranking 146 out of 156 embedding models by cost and cheaper than 4% of models in this category. gemini-embedding-2 supports vision, audio input — one of only 5 embedding models with this combination. It accepts up to 8K input tokens.

Pricing Information

Input Cost$0.20 per 1M tokens

Note: Use the interactive calculator above to estimate costs for your specific usage patterns.

Technical Specifications

Maximum Input Tokens8,192
Maximum Total Tokens8,192

Pro Tip

Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 8,192 input tokens.

Model Capabilities

✓Vision - Process and understand images
✓Audio Input - Accept audio data as input

How gemini-embedding-2 Pricing Compares

At $0.20 per 1M input tokens and $0.0000 per 1M output tokens, gemini-embedding-2 ranks 146 out of 156 embedding models by input cost. It is more expensive compared to the median of $0.10 for embedding models, and is cheaper than 4% of models in this category.

gemini-embedding-2 is one of 3 Google Gemini embedding models, one of only 5 embedding models combining audio input, vision.

ModelProviderInput / 1M tokensOutput / 1M tokensvs gemini-embedding-2
gemini-embedding-2OpenRouter$0.20-0%
gemini-embedding-2-previewOpenRouter$0.20-0%
amazon.nova-2-multimodal-embeddings-v1:0AWS Bedrock$0.16$0.0000-19%

Alternatives to gemini-embedding-2

Similar embedding models from other providers

OpenRouter
gemini-embedding-2
$0.20/1M input
0% vs gemini-embedding-2
OpenRouter
gemini-embedding-2-preview
$0.20/1M input
0% vs gemini-embedding-2
AWS Bedrock
amazon.nova-2-multimodal-embeddings-v1:0
$0.16/1M input
-19% vs gemini-embedding-2
OpenRouter
gemini-embedding-2:batch
$0.10/1M input
-50% vs gemini-embedding-2
Vertex AI
gemini-embedding-2-preview
$0.20/1M input
0% vs gemini-embedding-2

Frequently Asked Questions

Is gemini-embedding-2 cheaper than gemini-embedding-2?

No. gemini-embedding-2 costs $0.20 per 1M input tokens while gemini-embedding-2 costs $0.20 per 1M input tokens, making gemini-embedding-2 0% more affordable for input. However, gemini-embedding-2 may offer different capabilities or performance characteristics that justify the price difference.

How does gemini-embedding-2 pricing compare to the average embedding model?

gemini-embedding-2 input pricing is $0.20 per 1M tokens, which is 100% above the median of $0.10 for embedding models. It ranks 146 out of 156 embedding models by input cost, making it cheaper than 4% of models in this category. For output, it costs $0.0000 per 1M tokens compared to the median of $0.02.

What makes gemini-embedding-2 different from other Google Gemini models?

Among Google Gemini's 3 embedding models, gemini-embedding-2 ranks 2 by input cost. Its combination of audio input, vision is shared by only 4 other embedding models.

What are the best alternatives to gemini-embedding-2?

The most comparable embedding models to gemini-embedding-2 are: gemini-embedding-2 from OpenRouter ($0.20/1M input tokens); gemini-embedding-2-preview from OpenRouter ($0.20/1M input tokens); amazon.nova-2-multimodal-embeddings-v1:0 from AWS Bedrock ($0.16/1M input tokens); gemini-embedding-2:batch from OpenRouter ($0.10/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.

How do I calculate gemini-embedding-2 costs?

gemini-embedding-2 is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.20 and generating 1M output tokens costs $0.0000.