bge-reranker-v2-m3 Cost Calculator - Novita

Calculate the cost of using bge-reranker-v2-m3 from Novita for your AI applications

bge-reranker-v2-m3 Cost Calculator

Mode: Rerank

Input Tokens

Output Tokens

Cost Breakdown

Input Cost$0.00001000

Output Cost$0.00001000

Total Cost$0.00002000

Pricing Details

Input: $0.0000000100 per token

Output: $0.0000000100 per token

[ WE'RE OPEN SOURCE ]

Scale with the Fastest LLM Gateway

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

Book a Demo

or, Get started here

Model Specifications

Limits

Max Input Tokens8,000

Max Output Tokens8,000

Max Tokens8,000

About bge-reranker-v2-m3

bge-reranker-v2-m3 is a powerful rerank AI model offered by Novita. This comprehensive guide provides detailed pricing information, technical specifications, and capabilities to help you understand the costs and features of using bge-reranker-v2-m3 in your applications.

Pricing Information

Input Cost$0.01 per 1M tokens

Output Cost$0.01 per 1M tokens

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

Technical Specifications

Maximum Input Tokens8,000

Maximum Output Tokens8,000

Maximum Total Tokens8,000

Pro Tip

Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 8,000 input tokens. The maximum output length is 8,000 tokens.

When should you use bge-reranker-v2-m3?

bge-reranker-v2-m3 is best suited for the following scenarios:

Search reranking for RAG pipelines
Improving relevance for semantic search results
Reordering candidate documents or passages before generation

When should you avoid bge-reranker-v2-m3?

Conversational AI and free-form text generation
Summarization or creative writing workloads
Audio, image, or video generation tasks

How does bge-reranker-v2-m3 compare to similar models?

This is a reranking model. Compared to general-purpose generators, rerankers are optimized for ordering candidates by relevance. When comparing similar models, evaluate relevance quality on your retrieval set and how pricing scales with the number and length of candidates.

Understanding bge-reranker-v2-m3 pricing

bge-reranker-v2-m3 is a reranking model provided by Novita.
Input tokens are priced at $0.01 per 1M tokens.
Output tokens are priced at $0.01 per 1M tokens.
The model supports a maximum input capacity of 8,000 tokens.
Maximum output length is 8,000 tokens.
For this model, input tokens are more expensive than output tokens, so optimizing your prompts can help manage costs.
Novita offers bge-reranker-v2-m3 for reranking workloads — search relevance improvements and RAG reranking.

How to Use This Calculator

Step 1: Enter the number of input tokens you expect to use. Input tokens include your prompt, system messages, and any context you provide to the model.

Step 2: Specify the number of output tokens you anticipate. Output tokens are the text generated by the model in response to your input.

Step 3: Review the cost breakdown to see the total estimated cost for your usage. The calculator automatically updates as you adjust the token counts.

← Back to All Models View All Novita Models