Model Library
Browse and deploy state-of-the-art AI models through the DEVUP Gateway.
Browse and deploy state-of-the-art AI models through the DEVUP Gateway.
Browse and deploy state-of-the-art AI models through the DEVUP Gateway.
DeepSeek V4 Pro is the flagship of the DeepSeek V4 series: a Mixture-of-Experts model with 1.6 trillion total parameters, 49 billion of which activate per token, and a one-million-token context window. Its hybrid attention stack was designed specifically to make that window practical rather than nominal, cutting per-token compute to roughly a quarter and key-value cache to roughly a tenth of the previous generation at full context. Reasoning effort is a per-request control with three levels, and at its deepest setting the model reaches its strongest results on world knowledge, long-context retrieval, and multi-step agentic work. Released under the MIT license, it is the model to reach for on DEVUP AI when the input is enormous, the question is genuinely hard, or accuracy outweighs everything else.
Ling-3.0-flash-Fin is the first finance-enhanced model in Ant Group's Ling family, built by continuing the training of Ling-3.0-flash on high-quality financial data with input from financial institutions and domain experts. It carries 124 billion total parameters but activates only 5.1 billion per token — roughly four percent — which keeps inference light enough for the long agent runs financial research actually requires. Across a 256K context it connects retrieval, evidence review, calculation, modelling, and report preparation as one workflow rather than separate tasks, reconciling conflicting figures across annual reports, earnings releases, and filings. Released under the MIT licence, it retains the general reasoning, coding, and mathematics of the model it extends.
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled build of V4 Flash, and it takes an unusual approach to image cost: every image is capped at 384 tokens regardless of its resolution. A two-megapixel scan and a twenty-five-megapixel one bill identically, because both are resized to the same working size before inference. That turns document processing from an open-ended cost into arithmetic you can do before sending the request. It accepts up to six hundred images per call, matches the text model it is built on across agents, reasoning, and world knowledge, and holds the same million-token context. On DEVUP AI it is the choice when the workload is pages rather than paragraphs.
GLM-5.3 is Z.ai's flagship coding model, and it makes an unusual argument: it shares its base model entirely with the previous generation. No new pre-training, no larger foundation — every gain comes from post-training alone, and the gains are large. Terminal Bench 3.0 moves from 4.6 to 28.3 on identical weights. Alongside coding, Z.ai reports that cyber capability emerged faster than expected during that scaling, putting the model at the state of the art for vulnerability discovery and more than doubling its predecessor further up the exploitation chain. It holds a one-million-token context with a 128K maximum output, generates roughly three times faster than comparable frontier models, and reasons at three selectable effort levels.
GLM-5.3-Flash is the first natively multimodal model in the GLM-5 series, and it was built from a new base model rather than adapted from an existing one. It carries 320B total parameters but activates only 18B per token, routing each token through 8 of 288 experts across 45 layers. Its defining architectural choice is a hybrid attention stack combining linear and sparse attention — a first for the series — which cuts the serving cost of very long inputs while keeping long-context accuracy intact. Trained on a 30-trillion-token multimodal corpus, it accepts images alongside text and holds a full one-million-token context. Released under the MIT license, it is the model to reach for on DEVUP AI when your input is visual, very long, or both.
Granite 4.2 30B is the flagship of IBM's Granite 4.2 reasoning family and the model that goes furthest through its training pipeline. On top of the chain-of-thought reasoning and the agentic reinforcement-learning block shared with the mid-size tier, the 30B adds a third round of verifiable-reward training and a second supervised fine-tuning phase dedicated entirely to agentic coding — reading real repositories, editing files, and running test suites. It leads the family across software engineering, terminal operation, mathematics, and long-context recall, holding a 128K window with the strongest retention of the three sizes. Tested across twelve languages and released under Apache 2.0, it is the model to reach for on DEVUP AI when the task is genuinely hard and a wrong answer costs more than a slow one.
Granite 4.2 8B is IBM's mid-size open reasoning model, and the smallest one in its family trained to act. Beyond the chain-of-thought reasoning shared across Granite 4.2, the 8B goes through an additional agentic reinforcement-learning stage in real sandboxed environments — editing real repositories, driving a live terminal, and running multi-hop web searches — which is why it is the smallest Granite 4.2 model with reported agentic coding results. Three thinking modes let you trade reasoning depth against latency per request, and it holds a 128K context with substantially better long-context recall than the compact tier. Tested across twelve languages and released under Apache 2.0, it is the balanced default on DEVUP AI for production agents, coding assistants, and long-document work.
Granite 4.2 3B is IBM's compact open reasoning model — a three-billion-parameter dense transformer that thinks before it answers. It emits an explicit chain of thought inside <think> tags before producing a final response, which lifts its accuracy on math, code and multi-step logic well beyond what its size would suggest. Three thinking modes — full, low-effort, and off — let you trade depth against latency on a per-request basis, so a single model can serve both a fast autocomplete and a careful agent. It handles a 128K context window, calls tools with explicit reasoning about why each call is made, and is tested across twelve languages. Released under Apache 2.0, it is a strong default on DEVUP AI for agentic workflows, structured extraction, and reasoning tasks that need to stay lightweight.
Wan3.0-Video is an all-in-one multimodal AI model launched by Alibaba's Tongyi Lab, integrating video generation and precise editing into a single unified architecture. Replaced the previous task-specific versions, it supports native 30-second clips at up to 1080p with simultaneous native audio-visual generation in one single pass. Beyond standard text and images, its signature Omni-Reference capability allows it to parse up to 20 assets—including documents (PDFs, PPTs) and webpages—to directly drive character consistency, movement replication, and precise pixel-level interactive editing.
all-mpnet-base-v2 is an open-source sentence embedding model developed by Sentence Transformers, built upon Microsoft's 109-million parameter MPNet (Masked and Permuted Pre-training) architecture. By combining the strengths of masked language modeling (BERT) and permuted language modeling (XLNet), it maps text into a dense 768-dimensional vector space. Fine-tuned on over 1 billion sentence pairs using contrastive learning, it long served as the primary quality gold standard among Sentence Transformers for semantic similarity, classification, and retrieval tasks.
all-MiniLM-L6-v2 is an ultra-lightweight, high-speed sentence embedding model developed by Sentence Transformers. Built on the 22.7-million parameter nreimers/MiniLM-L6-H384-uncased architecture (a 6-layer distilled version of BERT), it maps text into a compact 384-dimensional dense vector space. Trained on over 1 billion sentence pairs using self-supervised contrastive learning, it serves as the industry standard benchmark for edge deployments, in-browser inference, and real-time semantic search with minimal latency.
all-MiniLM-L12-v2 is a widely used, highly efficient sentence embedding model developed by Sentence Transformers. Based on the 33.4-million parameter microsoft/MiniLM-L12-H384-uncased architecture, it maps sentences and short paragraphs into a dense 384-dimensional vector space. Fine-tuned on over 1 billion sentence pairs using self-supervised contrastive learning, it offers an excellent balance between retrieval speed, memory footprint, and semantic accuracy, making it a foundational baseline for lightweight semantic search and clustering applications.
