the DeAI TPA Base Model
A next-gen foundation model built to power everything from intelligent apps to enterprise AI solutions. Fast, scalable, and designed for limitless possibilities.
gpt-oss-20B
Efficient open reasoning model for scalable AI deployment
Kimi K2 Instruct-0905
235B MoE model with 29B activation featuring enhanced instruction foll...
FLUX.1 Kontext
In-context image generation and editing model using both text and imag...
BGE-Base-EN v1.5
BAAI general embedding - base, english - model v1.5. FlagEmbedding can...
Qwen3-Next-8B-A3B-Instruct
80B parameters (3B activated), instruction-tuned MoE, 10x faster infer...
Qwen3 0.6B Base API
0.6B-parameter ultra-compact base model with 28-layer architecture tra...
DeepSeek-V3-0324
DeepSeek's latest open Mixture-of-Experts model challenging top AI mod...
Llama 3.1 8B API
NVIDIA NIM for GPU accelerated Llama 3.1 8B Instruct inference through...
Llama 3.2 3B Instruct
Multimodal LLM optimized for visual recognition, image reasoning, capt...
Gemma 3 27B
Lightweight model with vision-language input, multilingual support, vi...
Mistral (7B) Instruct v0.2 API
Improved instruct fine-tuned version of Mistral-7B-Instruct-v0.1.
GLM-4.5-Air
106B‑parameter efficient MoE model, 128K‑token context, hybrid reasoni...
Stage Immersive
Immersive model generating real estate, hotel, and environment experi...
Stage 3D Generator
3D model generating high-quality assets and scalable scene renderings.
Bigger Possibilities.
The DeAI TPA Base Model is your gateway to advanced AI development. Build, integrate, and scale without compromise.