Models
| Provider | Model | Input | Output | Context |
|---|---|---|---|---|
Gemini Embedding 2 is Google's advanced text embedding model designed for high-accuracy semantic representation across large-scale retrieval and understanding tasks. It converts text into dense vector embeddings optimized for semantic search, retrieval-augmented generation (RAG), clustering, classification, and recommendation systems. Built for production use, it offers strong multilingual support, improved semantic similarity accuracy, and efficient embedding generation, making it well suited for large knowledge indexing pipelines and enterprise-scale retrieval applications. EmbeddingMar 12, 2026 | Input$0.6/1M tokens | Output$2.40/1M tokens | Context8K | |
Gemini-Embedding-001 is Google's high-quality text embedding model designed for semantic understanding and retrieval tasks. It converts text into dense vector representations optimized for semantic search, retrieval-augmented generation (RAG), clustering, classification, and recommendation systems. The model emphasizes strong multilingual performance, high semantic accuracy, and efficient embedding generation, making it well suited for large-scale knowledge indexing and production retrieval pipelines. EmbeddingFeb 9, 2026 | Input$0.075/1M tokens | Output$0.3/1M tokens | Context128K | |
Mistral Embed is Mistral AI's text embedding model, built for semantic search and RAG workflows. It generates 1024-dimensional vectors that capture meaningful relationships between pieces of text. EmbeddingOct 30, 2025 | Input$0.125/1M tokens | Output$0/1M tokens | Context8K | |
Jina Embeddings V5 Text Small by Jina AI. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. Embedding | Input$0.05/1M tokens | Output$0/1M tokens | Context8K | |
Jina Embeddings V5 Text Nano by Jina AI. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. Embedding | Input$0.05/1M tokens | Output$0/1M tokens | Context8K | |
Jina Embeddings V2 Base ES by Jina AI. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. Embedding | Input$0.05/1M tokens | Output$0/1M tokens | Context8K | |
Jina Embeddings V2 Base DE by Jina AI. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. Embedding | Input$0.05/1M tokens | Output$0/1M tokens | Context8K | |
Jina Embeddings V4 by Jina AI. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. Embedding | Input$0.05/1M tokens | Output$0/1M tokens | Context8K | |
Jina Embeddings V3 by Jina AI. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. Embedding | Input$0.05/1M tokens | Output$0/1M tokens | Context8K | |
Jina ColBERT V1 EN by Jina AI. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. Embedding | Input$0.05/1M tokens | Output$0/1M tokens | Context8K | |
Jina Colbert V2 by Jina AI. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. Embedding | Input$0.05/1M tokens | Output$0/1M tokens | Context8K | |
Jina CLIP V1 by Jina AI. Use it from Apertis SDKs, provider-compatible SDKs, or direct HTTP requests. Embedding | Input$0.05/1M tokens | Output$0/1M tokens | Context8K |