The Enterprise DNA directory
Lowest-price models: Best cheap
Low $/Mtoken for high volume.
1,556 catalogue records · Reviewed guides appear first
24 tools on this page
KB Whisper
Kblab
Speech transcription model for accurate audio-to-text and captioning workflows
Whisper Large v3 Turbo
OpenAI
Speech transcription model for accurate audio-to-text and captioning workflows
BGE Reranker Base
Workers Ai
Reranking model for improving retrieval quality in search and recommendation systems
DeepSeek V4 Flash Latest
DeepSeek
This model always redirects to the latest model in the DeepSeek V4 Flash family.
Ling-2.6-flash
Inclusionai
Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, st
Qwen3 Embedding 0.6B
Qwen
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Qwen 3 Embedding 4B
Qwen
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Qwen3-Embedding-8B
Qwen
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Best for: Multilingual text retrieval
Qwen3 Reranker 0.6B
Qwen
Reranking model for improving retrieval quality in search and recommendation systems
DeepSeek V4 Flash 0731
DeepSeek
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoni
BGE M3
Workers Ai
Flagship model for demanding analysis, coding, and production agent workflows
Qwen3 Embedding 0.6B
Workers Ai
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Granite 4.0 H Micro
Cf
Efficient model for low-latency assistance, extraction, and routine automation
Granite 4.0 Micro
Ibm Granite
Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...
IBM Granite 4.0 H Micro
Workers Ai
Efficient model for low-latency assistance, extraction, and routine automation
gpt-oss-20b
OpenAI
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per f
PLaMo Embedding 1B
Workers Ai
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
BGE Small EN v1.5
Workers Ai
Efficient model for low-latency assistance, extraction, and routine automation
E5 Mistral 7B
Intfloat
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
GLM 4.6V FlashX
Z Ai
GLM vision model for visual reasoning, documents, and multimodal agents
Llama Guard 3 8B
Meta
Safety model for policy screening, moderation, and risk-aware routing workflows
Manta Flash 1.0
Meganova Ai
Efficient model for low-latency assistance, extraction, and routine automation
Manta Mini 1.0
Meganova Ai
Efficient model for low-latency assistance, extraction, and routine automation
PaddleOCR-VL
Paddlepaddle
Multimodal model for analyzing text, images, documents, and rich media