Calculate the cost of using gemini-embedding-2-preview from OpenRouter for your AI applications
Pricing data last updated:
Mode: Embedding
Max: 8,192 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
gemini-embedding-2-preview is an embedding model from OpenRouter, one of 25 embedding models they offer. It is priced at $0.20 per 1M input tokens and $0.0000 per 1M output tokens, ranking 144 out of 149 embedding models by cost and cheaper than 3% of models in this category. gemini-embedding-2-preview supports vision, audio input — one of only 6 embedding models with this combination. It accepts up to 8K input tokens.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 8,192 input tokens. The maximum output length is 7,372 tokens.
At $0.20 per 1M input tokens and $0.0000 per 1M output tokens, gemini-embedding-2-preview ranks 144 out of 149 embedding models by input cost. It is more expensive compared to the median of $0.10 for embedding models, and is cheaper than 3% of models in this category.
gemini-embedding-2-preview is one of 25 OpenRouter embedding models, one of only 6 embedding models combining audio input, vision.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs gemini-embedding-2-preview |
|---|---|---|---|---|
| gemini-embedding-2 | Google Gemini | $0.20 | $0.0000 | 0% |
| gemini-embedding-2-preview | Google Gemini | $0.20 | $0.0000 | 0% |
| amazon.nova-2-multimodal-embeddings-v1:0 | AWS Bedrock | $0.16 | $0.0000 | -19% |
Similar embedding models from other providers
No. gemini-embedding-2-preview 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-preview may offer different capabilities or performance characteristics that justify the price difference.
gemini-embedding-2-preview input pricing is $0.20 per 1M tokens, which is 100% above the median of $0.10 for embedding models. It ranks 144 out of 149 embedding models by input cost, making it cheaper than 3% of models in this category. For output, it costs $0.0000 per 1M tokens compared to the median of $0.02.
Among OpenRouter's 25 embedding models, gemini-embedding-2-preview ranks 25 by input cost. Its combination of audio input, vision is shared by only 5 other embedding models.
The most comparable embedding models to gemini-embedding-2-preview are: gemini-embedding-2 from Google Gemini ($0.20/1M input tokens); gemini-embedding-2-preview from Google Gemini ($0.20/1M input tokens); amazon.nova-2-multimodal-embeddings-v1:0 from AWS Bedrock ($0.16/1M input tokens); gemini-embedding-2-preview from Vertex AI ($0.20/1M 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.
You can monitor OpenRouter service health in real time on the Bifrost OpenRouter Status page. It tracks current component status, active incidents, and historical reliability data pulled from the official status page every 60 seconds.
gemini-embedding-2-preview 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.