{"entries":[{"title":"Lifecycle poisoning of reusable agent skills","cveId":"fc8f356e","paperTitle":"Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation","paperUrl":"https://arxiv.org/abs/2607.13987","paperDate":"2026-07-15","analysisDate":"2026-07-21T03:21:03.162Z","tags":["application-layer","agent","coding-agent","model-supply-chain","injection","prompt-layer","poisoning","embedding","data-security","integrity","safety","reliability"],"affectedModels":["all-MiniLM-L6-v2","Gemini 3.1 Pro","Gemini 1.5 Flash"],"description":"The paper presents SkillSec-Eval, a controlled evaluation of attacks against reusable agent skills across repository admission, semantic retrieval, planner selection, runtime execution, and updates. It reports that malicious metadata, retrieval manipulation, unsafe workflow composition, and poisoned updates can cause agents to retrieve, select, or execute unintended skills. These are paper-reported benchmark results, not independently verified vulnerabilities in a named production product.","slug":"lifecycle-poisoning-of-reusable-agent-skills","hasDedicatedEvidence":true},{"title":"Cross-Site Prompt Injection in Web Agents","cveId":"9d8b3bc1","paperTitle":"Prismata: Confining Cross-Site Prompt Injection in Web Agents","paperUrl":"https://arxiv.org/abs/2607.08147","paperDate":"2026-07-09","analysisDate":"2026-07-21T03:29:25.271Z","tags":["application-layer","computer-use","agent","injection","integrity","prompt-layer","data-security","reliability"],"affectedModels":["GPT-5.4","GPT-5.4-mini","GPT-5.4 Nano","Gemini 3 Flash","GPT-oss 120B","Qwen 3 8B","MiniMax M2.5"],"description":"The paper defines Cross-Site Prompting (XSP): attacker-controlled text in reviews, posts, seller listings, advertisements, or embeds can be interpreted as instructions by a web agent and steer its browser actions. It evaluates three reproducible WebArena attack templates—Shortcut, Fake Completion, and Ignore Instruction—plus WASP and adaptive stress tests. This is an evaluated agent-security issue and mitigation, not a claimed production CVE.","slug":"cross-site-prompt-injection-in-web-agents","hasDedicatedEvidence":true},{"title":"Semantic-Bridging Jailbreaks Reroute Llama-2 Safety Pathways","cveId":"070700e7","paperTitle":"Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs","paperUrl":"https://arxiv.org/abs/2607.07903","paperDate":"2026-07-08","analysisDate":"2026-07-20T18:12:51.320Z","tags":["model-layer","jailbreak","whitebox","safety","reliability"],"affectedModels":["Llama 2 7B Chat"],"description":"The paper reports a reproducible white-box evaluation in which semantically bridging a benign topic into a harmful request bypassed Llama-2-7B-chat-hf safety behavior in 4 of 30 tested prompt pairs. Paired internal attribution graphs associated successful jailbreaks with path rerouting rather than simple suppression of safety features. This is a paper-reported result, not independently verified here. Defensive reproduction should use the paper’s supplied dataset and code in an isolated evaluation environment, measure refusal behavior and graph/path deviations, and avoid operational harmful payloads.","slug":"semantic-bridging-jailbreaks-reroute-llama-2-safety-pathways","hasDedicatedEvidence":true},{"title":"Agent Data Injection via Trusted-Metadata Spoofing","cveId":"bb06bcfb","paperTitle":"Agent Data Injection Attacks are Realistic Threats to AI Agents","paperUrl":"https://arxiv.org/abs/2607.05120","paperDate":"2026-07-06","analysisDate":"2026-07-20T18:04:48.104Z","tags":["application-layer","injection","agent","coding-agent","computer-use","data-security","integrity"],"affectedModels":["GPT-5.2","GPT-5 Mini","Claude Opus 4.5","Claude Sonnet 4.5","Gemini 3 Pro","Gemini 3 Flash"],"description":"Agent data injection (ADI) is a reproducible indirect injection class in which attacker-controlled external content is formatted to resemble trusted metadata or agent-context structure. The paper reports that probabilistic delimiter injection can cause agents to misinterpret untrusted content as trusted element IDs, author identities, or tool responses, leading to unintended clicks, command execution, or PR merges. Safe defensive reproduction should use the authors’ synthetic LLM/AgentDojo benchmarks in an isolated environment with inert actions; the artifact repository explicitly omits executable real-world attack demonstrations.","slug":"agent-data-injection-via-trusted-metadata-spoofing","hasDedicatedEvidence":true},{"title":"GhostWriter Persistent Memory Poisoning in Tool-Using Agents","cveId":"e9cd87a8","paperTitle":"When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents","paperUrl":"https://arxiv.org/abs/2607.06595","paperDate":"2026-07-06","analysisDate":"2026-07-20T18:16:36.372Z","tags":["application-layer","injection","poisoning","agent","memory","blackbox","data-security","integrity"],"affectedModels":["GPT-5.4-mini","DeepSeek V4 Flash","Gemini 2.5 Flash","Llama 3.1 8B"],"description":"The paper describes GhostWriter, a reproducible two-phase attack against tool-using agents with persistent memory: untrusted email or calendar content is admitted into long-term memory, then later retrieved during a benign user task and treated as trusted context. In the authors’ controlled evaluation, this could steer subsequent agent actions despite the adversary lacking direct access to the agent, memory store, account, or later prompt. The paper reports an average 98% memory-injection rate and 60% activation rate across its tested configurations; these are paper-reported measurements, not independently verified facts.","slug":"ghostwriter-persistent-memory-poisoning-in-tool-using-agents","hasDedicatedEvidence":true},{"title":"Query-Agnostic Poisoning of Policy-Aware RAG Knowledge Bases","cveId":"b8d88ec3","paperTitle":"Knowledge Base Poisoning Attacks and Defense for Policy-Aware LLM-RAG Framework","paperUrl":"https://arxiv.org/abs/2607.04379","paperDate":"2026-07-05","analysisDate":"2026-07-20T18:03:49.873Z","tags":["application-layer","poisoning","rag","embedding","integrity","reliability","whitebox"],"affectedModels":["nomic-embed-text"],"description":"The paper describes a specific, reproducible retrieval-layer poisoning issue: an adversary with knowledge-base write access can add semantically broad, cross-category policy rules that rank in top-k retrieval across varied queries without knowing runtime prompts. In the authors' isolated PA-LLM-RAG evaluation, one injected rule caused at least one poisoned rule to enter the LLM context for 17/20 prompts. Safe defensive reproduction should use a synthetic policy KB, synthetic benign prompts, and measure whether injected test documents enter retrieved context; do not connect testing to operational systems. All measurements are paper-reported and were not independently verified.","slug":"query-agnostic-poisoning-of-policy-aware-rag-knowledge-bases","hasDedicatedEvidence":true},{"title":"Information-Overloading Jailbreaks in Vision-Language Models","cveId":"ba55f451","paperTitle":"Overloading Large Vision-Language Models for Jailbreaking","paperUrl":"https://arxiv.org/abs/2607.02961","paperDate":"2026-07-03","analysisDate":"2026-07-20T18:08:21.145Z","tags":["model-layer","jailbreak","vision","multimodal","blackbox","safety"],"affectedModels":["Qwen3-VL 8B","Qwen2-VL-7B","InternVL3.5-8B","InternVL 2 8B","Llama 3.2 11B Vision","GPT-4.1 Mini","Gemini 2.5 Flash","Gemini 2.5 Flash-Lite"],"description":"The paper describes a reproducible black-box multimodal jailbreak evaluation, INFER/INFER+, in which dense image typography, nested cross-modal references, recursive visual layouts, and entropy-guided search increase processing complexity and weaken refusal behavior in large vision-language models. The authors report average ASRs of 88.6% on open-source models and 84.0% on commercial models; these are paper-reported measurements, not independently verified facts. For safe defensive reproduction, evaluate the layout and filtering behavior only with benign policy-boundary prompts or established harmless red-team surrogates rather than operational harmful payloads.","slug":"information-overloading-jailbreaks-in-vision-language-models","hasDedicatedEvidence":true},{"title":"Attention-Head Suppression Bypasses LLM Refusal","cveId":"c39e08c0","paperTitle":"Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models","paperUrl":"https://arxiv.org/abs/2606.28153","paperDate":"2026-06-26","analysisDate":"2026-07-20T18:09:20.888Z","tags":["model-layer","jailbreak","whitebox","safety","reliability"],"affectedModels":["Llama 3 8B Instruct","Llama 2 7B Chat","Llama 3 70B Instruct"],"description":"The paper reports a reproducible white-box jailbreak failure mode: successful jailbreak templates selectively suppress early-layer Adversarially Compromised Heads (ACHs), bypassing refusal while harmful-semantic safety activations persist in other heads. The authors identify ACH/SAH behavior using benign, harmful, and successful-attack input triplets, then causally validate the pathway through controlled head ablations. Safe defensive reproduction should use the paper’s released evaluation triplets and activation-analysis pipeline in an isolated safety-testing environment, without generating or deploying new jailbreak payloads. These findings are paper-reported and were not independently verified here.","slug":"attention-head-suppression-bypasses-llm-refusal","hasDedicatedEvidence":true},{"title":"Long-Term Memory Authority Laundering","cveId":"a4b03e8d","paperTitle":"Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees","paperUrl":"https://arxiv.org/abs/2606.24322","paperDate":"2026-06-23","analysisDate":"2026-07-20T18:17:57.392Z","tags":["application-layer","injection","poisoning","agent","memory","data-security","integrity"],"affectedModels":["GPT-5 Chat","GPT-4o Mini","Claude Opus 4.1","Claude Sonnet 4.5","Gemini 2.5 Flash","Llama 4 Maverick","DeepSeek Chat","Qwen 3 235B-A22B"],"description":"The paper describes a reproducible agent-memory poisoning issue: untrusted content stored in persistent memory can later influence consequential actions after its origin is laundered through agent summarization, trusted-tool echo, or manufactured corroboration. The paper reports that content scoring, lineage, and single-session capability/IFC defenses remain vulnerable because they decide authority from malleable content or derivation signals. This is a paper-reported evaluation; it was not independently reproduced here.","slug":"long-term-memory-authority-laundering","hasDedicatedEvidence":true},{"title":"Black-Box System Prompt Leakage in Real-World LLM Applications","cveId":"58182aa1","paperTitle":"Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications","paperUrl":"https://arxiv.org/abs/2606.18673","paperDate":"2026-06-17","analysisDate":"2026-07-20T18:19:34.047Z","tags":["application-layer","prompt-layer","extraction","prompt-leaking","blackbox","api","data-privacy","data-security"],"affectedModels":["Llama 2 7B Chat","Llama 3.1 8B Instruct","Mistral 7B Instruct v0.3","Qwen 3 4B Instruct 2507","Qwen 3 32B","Qwen 2.5 72B Instruct","Llama 3.3 70B Instruct","Qwen 3 30B-A3B Instruct-2507"],"description":"The paper reports a reproducible black-box evaluation showing that adversarial user queries can cause deployed LLM applications to reveal hidden system prompts. In the authors’ measurement of 1,200 applications across six commercial platforms, 1,064 applications leaked prompt content (81.0%–93.5% per anonymized platform). This is a paper-reported result, not independently verified here. LeakBench and the official artifact repository provide defensive benchmark materials for controlled testing; no operational payload is reproduced here.","slug":"black-box-system-prompt-leakage-in-real-world-llm-applications","hasDedicatedEvidence":true}],"totalEntries":959,"currentPage":1,"totalPages":96,"filters":{"query":"","tags":[],"models":[],"page":1,"sort":"published","publishedFrom":"","publishedTo":"","source":"","evidence":""},"allModels":["3D-Diffuser Actor","Aegis Defensive","Aegis Permissive","AegisGuard","Aion 1.0","Alibaba Cloud text-embedding-v4","Alpaca","Alpaca 7B","Alpaca 7B (Safe-RLHF)","Anthropic Claude-3-sonnet20240229","Aquilachat-7B","Atla Selene Mini 8B","Audio Flamingo 3","Aya-23-8B","BAGEL 14B","BERT","BERT Base","BGE-VL-base","BLIP-2","BLIP-2 OPT 2.7B","BLIP-2 ViT-g/14","BLSP","Baichuan 2","Baichuan 2 13B","Baichuan 2 13B Chat","Baichuan 2 7B","Baichuan 2 7B Chat","Baichuan-13B","Baichuan-7B","Barkplug V.2","Beaver 7B v1.0 Cost","BioMistral 7B","Bunny 1.0 4B","CLIP","CLIP ViT-B/32","CLIP ViT-Large-Patch14-336","Chameleon","Chameleon 30B","Chameleon 7B","ChatGLM 6B","ChatGLM2 6B","ChatGLM3 6B","ChatGLM4","Chatglm-2 (chatglm2-6B)","Chatglm-3 (chatglm3-6B)","Chatglm-turbo","CheXagent","Circuit Breaker","Claude 1","Claude 1.2 Instant","Claude 1.3","Claude 2","Claude 2.0","Claude 2.1","Claude 3 Haiku","Claude 3 Opus","Claude 3 Sonnet","Claude 3.5 Haiku","Claude 3.5 Haiku 20241022","Claude 3.5 Sonnet","Claude 3.5 Sonnet 20240620","Claude 3.5 Sonnet 20241022","Claude 3.5 Sonnet Latest","Claude 3.7 Sonnet","Claude 3.7 Sonnet 20250219","Claude 3.7 Sonnet Thinking","Claude Haiku 4.5","Claude Haiku 4.5 20251001","Claude Instant 1","Claude Instant 1.2","Claude Opus 4","Claude Opus 4.1","Claude Opus 4.5","Claude Opus 4.6","Claude Sonnet 3.6","Claude Sonnet 4","Claude Sonnet 4.5","Claude Sonnet 4.5 20250929","Claude Sonnet 4.6","Claude-3(v3-haiku)","Claude-3-haiku-0307","Claude-instant-v1","Claude-v2","Clip-vit-base-patch32","Code Llama 13B Instruct","Code Llama 7B","CodeAstra","CodeGeeX2 6B","CodeGen Multi 350M","CodeGen25 Instruct 7B","CodeLlama 70B Instruct","CodeLlama 7B Instruct","Codellama 34B Instruct","Codellama-13B-python","Cogito 2.1","Cogito v2.1 671B","Cogview3","Cogvlm","Cogvlm-chat-v1.1","Cohere-35B","Command A","Command R","Command R+","Crispers 7B","Cydonia 24B v4.1","Cygnet","DALL-E","DALL-E 3","DIVA Llama 3 v0 8B","DREAM v0 Instruct 7B","Dall-e 2","DarkIdol Llama 3.1 8B Instruct","DeBERTa v3 Base","DeepResearcher 7B","DeepScaleR 1.5B","DeepSeek 7B","DeepSeek Chat","DeepSeek Chat V2 236B","DeepSeek Chat V3.1","DeepSeek Coder 33B","DeepSeek Coder 7B","DeepSeek Coder V2 Instruct 0724 236B","DeepSeek Coder V2 Lite 16B","DeepSeek LLM 7B Chat","DeepSeek R1","DeepSeek R1 0528","DeepSeek R1 0528 Qwen3 8B","DeepSeek R1 671B","DeepSeek R1 Distill","DeepSeek R1 Distill Llama 70B","DeepSeek R1 Distill Llama 8B","DeepSeek R1 Distill Qwen 1.5B","DeepSeek R1 Distill Qwen 14B","DeepSeek R1 Distill Qwen 32B","DeepSeek R1 Distill Qwen 7B","DeepSeek R1 Tool Calling 70B","DeepSeek Reasoner","DeepSeek V3","DeepSeek V3 0324","DeepSeek V3.1","DeepSeek V3.1 Nex N1","DeepSeek V3.2","DeepSeek V3.2 Exp","DeepSeek V3.2 Speciale","DeepSeek V3.2 Thinking","DeepSeek V4 Flash","DeepSeek V4-Pro","DeepSeek VL 1.3B","DeepSeek-MoE 16B Chat","DeepSeek-V2","DeepSeek-V3 671B","DeepSeek-VL2","Deepseek-coder","Deepseek-v2.5","Deepseek-vl7B-chat","Devstral 2","Devstral 24B","DiVA","DialoGPT Large","DistilBERT","Dolly 2","Dolphin Mistral 24B Venice","Dolphins","Doubao 1.5 Thinking Pro","Doubao 1.6 Thinking 250715","Doubao Seed 1.6","Doubao Seed 1.6 Flash","E5 BERT-base","E5 Base v2","ERNIE","ERNIE 3.5","ERNIE 3.5 Turbo","ERNIE 4.0 Turbo","ERNIE 4.5","ERNIE 4.5 21B-A3B Thinking","ERNIE 4.5 Turbo 128K Preview","EmbodiedGPT","Evo1 7B","Evo2 1B","Evo2 40B","Evo2 7B","Falcon 3 10B","Falcon 3 10B Instruct","Falcon 3 3B Instruct","Falcon 7B","Falcon 7B Instruct","Falcon-40B-instruct","Falcon-Mamba 7B Instruct","Falcon-chat-180B","FastChat-T5 3B","FinBERT","FinGPT","FinLLaMA","FinanceChat 7B","Flan-T5 11B","Flan-T5 3B","Flan-T5 XL","Flan-T5 XXL","Flan-t5 Large","Flux","Flux 2.0 Dev 32B","Flux Schnell","FunAudioLLM","GLM","GLM 3 6B","GLM 4 9B","GLM 4 9B Chat","GLM 4 9B Chat HF","GLM 4 Plus","GLM 4.5","GLM 4.5 Air","GLM 9B","GLM-4 32B","GLM-4 Air 250414","GLM-4 Voice","GLM-4.1V 9B Thinking","GLM-4.1V Thinking","GLM-4.5V","GLM-4.6","GLM-4.7","GLM-4V Plus","GLM-5","GLM-5.1","GPT","GPT 3.5-turbo-0125","GPT 3.5-turbo-instruct","GPT Image 1.5","GPT-2","GPT-2 124M","GPT-2 Large","GPT-2 XL","GPT-3","GPT-3 13B","GPT-3.5","GPT-3.5 (GPT-3.5-turbo-0125)","GPT-3.5 (GPT-3.5-turbo-1106)","GPT-3.5 Turbo","GPT-3.5 Turbo-0301","GPT-3.5 Turbo-1106","GPT-3.5-1106)","GPT-3.5-turbo-instruct-0914","GPT-4","GPT-4 (GPT-4-1106-preview)","GPT-4 0613","GPT-4 Turbo","GPT-4 Turbo-2024-04-09","GPT-4-0125-preview","GPT-4-0314","GPT-4-1106","GPT-4-1106-turbo","GPT-4-turbo-0409","GPT-4.1","GPT-4.1 2025-04-14","GPT-4.1 Mini","GPT-4.1 Nano","GPT-4.5","GPT-4.5 Preview","GPT-4V","GPT-4o","GPT-4o 2024-08-06","GPT-4o 2024-11-20","GPT-4o Audio","GPT-4o Mini","GPT-4o Mini (GPT-4o-mini-2024-07-18)","GPT-4o Mini 2024-07-18","GPT-4o Mini High","GPT-4o No-Safe Preview 20240801","GPT-4o Preview 20240801","GPT-4o Realtime","GPT-4o-0513","GPT-4o-2024-05-13","GPT-5","GPT-5 Chat","GPT-5 Chat 2025-10-03","GPT-5 Chat Latest","GPT-5 Mini","GPT-5 Nano","GPT-5.1","GPT-5.1 2025-11-13","GPT-5.2","GPT-5.2 Codex","GPT-5.2 Pro","GPT-5.2 Thinking","GPT-5.4","GPT-5.4 Nano","GPT-5.4-mini","GPT-5.5","GPT-J 6B","GPT-Neo 2.7B","GPT-NeoX","GPT-NeoX 20B","GPT-oss 120B","GPT-oss 20B","GPT-oss Safeguard 20B","GSVA 13B","Gemini (gemini-pro)","Gemini 1.0 Pro Vision","Gemini 1.5 Flash","Gemini 1.5 Flash (block None)","Gemini 1.5 Flash Latest","Gemini 1.5 Pro","Gemini 1.5 Pro (block None)","Gemini 1.5 Pro 002","Gemini 1.5 Pro Latest","Gemini 2.0 Flash","Gemini 2.0 Flash 001","Gemini 2.0 Flash Preview Image Generation","Gemini 2.0 Flash Thinking","Gemini 2.0 Flash-Lite","Gemini 2.0 Pro","Gemini 2.0 Pro Exp 0205","Gemini 2.5 Flash","Gemini 2.5 Flash Preview","Gemini 2.5 Flash Preview 04-17","Gemini 2.5 Flash Thinking","Gemini 2.5 Flash-Lite","Gemini 2.5 Pro","Gemini 3 Deep Think","Gemini 3 Flash","Gemini 3 Flash Preview","Gemini 3 Pro","Gemini 3 Pro Image","Gemini 3 Pro Preview","Gemini 3.0 Pro","Gemini 3.1 Pro","Gemini Exp 1206","Gemini Flash","Gemini Pro","Gemini Ultra","Gemini Vision Pro","Gemini-1.5-flash-001","Gemini-1.5-pro-001","Gemma 1.1 2B","Gemma 1.1 7B","Gemma 1.1 7B IT","Gemma 2 27B","Gemma 2 27B IT","Gemma 2 2B","Gemma 2 2B IT","Gemma 2 9B","Gemma 2 9B IT","Gemma 2B","Gemma 2B IT","Gemma 3 12B","Gemma 3 12B IT","Gemma 3 1B","Gemma 3 1B IT","Gemma 3 270M IT","Gemma 3 27B","Gemma 3 27B IT","Gemma 3 4B","Gemma 3 4B IT","Gemma 3n E2B","Gemma 3n E4B","Gemma 7B","Gemma 7B IT","Gemma 7B Instruct","Gemma-4-E4B-it","Gemma2-8B-instruct","Gemma3-4B Instruct","GigaChat-Max","Glm-4-air","Glm-4-flash","Glm-4v-9B","Granite 3.1 8B","Granite 3.1 8B Instruct","Granite 4.0 H Micro","Granite Guardian","Granite Guardian 3.2 5B","Grok 2","Grok 2 1212","Grok 2 Vision","Grok 3","Grok 3 Beta","Grok 3 Fast","Grok 3 Mini","Grok 3 Mini Beta","Grok 4","Grok 4 Fast","Grok 4 Fast Non-Reasoning","Grok 4.1","Grok 4.1 Fast","Grok 4.1 Fast Reasoning","Grok 4.1 Mini","Grok Code Fast 1","Guanaco 13B","Guanaco 7B","Guanaco-7B-hf","HCX-002","HCX-003","HCX-DASH-002","HateBERT","HateRoBERTa","Hermes 3 Llama 3.1 405B","Hermes 4 70B","HuatuoGPT-o1-7B","Hunyuan","Hunyuan 0.5B","Hunyuan 1.8B","Hunyuan 7B","Hunyuan A13B Instruct","Ichigo","Idefics","Imagen","Inf-mllm1","InstructBLIP","InstructBLIP Vicuna 13B","InstructBLIP Vicuna 7B","Intellect 3","IntentionReasoner 1.5B","IntentionReasoner 3B","InternLM 2.5 20B","InternLM 2.5 7B","InternLM 2.5 7B Chat","InternLM XComposer","InternVL","InternVL 2 26B","InternVL 2 2B","InternVL 2 40B","InternVL 2 4B","InternVL 2 8B","InternVL 2.5 78B","InternVL-Chat 19B","InternVL2.5 8B","InternVL3 14B","InternVL3 14B Instruct","InternVL3 1B","InternVL3 2B","InternVL3 2B Instruct","InternVL3 38B","InternVL3 38B Instruct","InternVL3 78B","InternVL3 8B","InternVL3 8B Instruct","InternVL3 9B","InternVL3.5 14B Instruct","InternVL3.5 38B Instruct","InternVL3.5 4B Instruct","InternVL3.5 8B Instruct","InternVL3.5-8B","Internlm-20B","Internlm2-chat-7B","Internvlchat-v1.5","JailJudge","Jamba Mini 1.7","Jina Embeddings v2","KAT Coder Pro","Kimi K2","Kimi K2 Instruct","Kimi K2 Preview","Kimi K2 Thinking","Kimi K2.5","Kimi VL A3B Instruct","Kimi-Audio 7B Instruct","Kimi-K2.6","LFM2 8B-A1B","LISA 13B","LISA 7B","LISA Explanatory 13B","LISA Explanatory 7B","LISA++ 7B","LLaDA 1.5","LLaDA 8B Base","LLaDA 8B Instruct","LLaSM","LLaVA 1.5","LLaVA 1.5 13B","LLaVA 1.5 7B","LLaVA 1.6","LLaVA 1.6 7B","LLaVA 1.6 Llama 3","LLaVA 1.6 Mistral 7B","LLaVA 2","LLaVA 7B","LLaVA 7B Chat","LLaVA Med","LLaVA Mistral","LLaVA NeXT 8B","LLaVA NeXT Qwen 1.5 72B Chat","LLaVA OneVision Qwen2 0.5B","LLaVA OneVision Qwen2 72B","LLaVA OneVision Qwen2 7B Chat","LLaVA v1.6 13B","LLaVA v1.6 34B","LLaVA v1.6 Mistral 7B","LLaVA v1.6 Vicuna 13B","LLaVA v1.6 Vicuna 7B","LLaVA-CoT","LLaVA-NeXT-Video 7B","LLaVA-OneVision","LLaVA-OneVision 0.5B","LLaVA-OneVision 1.5 8B Instruct","LLaVA-OneVision 7B","LLaVA-v2","LawChat 7B","Llama 13B","Llama 2 13B","Llama 2 13B Chat","Llama 2 13B HarmBench","Llama 2 70B","Llama 2 70B Chat","Llama 2 7B","Llama 2 7B Backdoor DEPLOYMENT","Llama 2 7B Chat","Llama 2 Chat","Llama 2-13B-chat-hf","Llama 2-7B-chat-hf","Llama 3 70B","Llama 3 70B Chat","Llama 3 70B Instruct","Llama 3 8B","Llama 3 8B Instruct","Llama 3 LLaVA-NeXT 8B","Llama 3-instruct 8B","Llama 3.1 405B","Llama 3.1 405B Instruct","Llama 3.1 70B","Llama 3.1 70B Hanami X1","Llama 3.1 70B Instruct","Llama 3.1 70B Instruct AWQ","Llama 3.1 8B","Llama 3.1 8B Instruct","Llama 3.1 8B Lexi Uncensored V2","Llama 3.1 Nemotron Ultra 253B v1","Llama 3.1 Tulu 3 8B DPO","Llama 3.2 11B","Llama 3.2 11B Vision","Llama 3.2 11B Vision Instruct","Llama 3.2 1B","Llama 3.2 1B Instruct","Llama 3.2 3B","Llama 3.2 3B Instruct","Llama 3.2 90B","Llama 3.2 90B Vision","Llama 3.2 90B Vision Instruct","Llama 3.3 70B","Llama 3.3 70B Instruct","Llama 33B","Llama 4 16x17B","Llama 4 17B","Llama 4 Maverick","Llama 4 Maverick 17B","Llama 4 Maverick 17B Instruct","Llama 4 Maverick Instruct","Llama 4 Scout","Llama 4 Scout 17B","Llama 7B","Llama Guard","Llama Guard 2","Llama Guard 2 8B","Llama Guard 3","Llama Guard 3 1B","Llama Guard 3 8B","Llama Guard 4","Llama Guard 4 12B","Llama Guard 7B","Llama Omni","Llama SEA-LION v3 70B","Llama SEA-LION v3 8B","Llama-1","Llama-2 (llama2-7B-chat)","Llama-2-13B-hf","Llama-2-7B-hf","Llama-2-chat-70B","Llama-2-sys","Llama-3-70B-chat-hf","Llama-3-8B Chat","Llama-adapterv2","Llama2-7-billion","Llama2-chat-13B","Llama2-chat-7B","LlamaV-o1","Llava v1.5-7B","Llava v1.6-mistral-7B-hf","Llava-v1.5-vicuna-v1.5-13B","Llava-v1.5-vicuna-v1.5-7B","Llava-v1.6-vicuna-7B-hf","LongCat Flash Chat","LongCat-Image-Edit","LongChat 7B","Lumimaid 70B","M3E","MAI DS R1 671B","MERaLion AudioLLM","MMaDA 8B Base","MMaDA 8B MixCoT","MMed-Llama 3 8B","MPT 7B","MPT 7B Chat","MPT 7B Instruct","Magistral Medium","Magistral Medium 2506","Mantis-CLIP","Mantis-Idefics2","Mantis-SIGLIP","Mdm","Med-Flamingo","MedGemma 27B","MedGemma 4B","Meditron 70B","Meditron 7B","Megatron 345M","Mercury","Meta-SecAlign 70B","Meta-SecAlign 8B","Meta-llama-3-8B","MiMo V2 Flash","MiMo V2.7","Midjourney","Midjourney v6","Mini-Omni","Mini-Omni 2","MiniCPM","MiniCPM-o 2.6","MiniCPM-o 2.6 8B","MiniCPM4 0.5B","MiniCPM4 8B","MiniGPT-4","MiniGPT-4 Vicuna 13B","MiniGPT-v2","MiniLM","MiniMax M2","MiniMax M2.1","MiniMax M2.5","MiniMax M2.7","Minigpt-5(7B)","Minigpt-v2(7B)","Minigpt4-llama-2-chat-7B","Minigpt4-vicuna-7B","Ministral 3","Ministral 3 8B Instruct-2512","Ministral 8B","Ministral 8B Instruct","Ministral 8B Instruct 2410","Minitron-8B-base","Mistral 7B","Mistral 7B 8B","Mistral 7B Instruct","Mistral 7B Instruct v0.2","Mistral 7B Instruct v0.3","Mistral 7B v0.2","Mistral 7B v0.3","Mistral 8B","Mistral Large","Mistral Large 12B","Mistral Large 2","Mistral Large 2.1","Mistral Large 2411","Mistral Large 24B","Mistral Large 2512","Mistral Large 3","Mistral Large Instruct 2407 123B","Mistral Medium 2505","Mistral Medium 3","Mistral Medium 3.1","Mistral Nemo","Mistral Nemo Instruct","Mistral Small","Mistral Small 22B","Mistral Small 24B","Mistral Small 24B Base 2501","Mistral Small 24B Instruct 2501","Mistral Small 3.2 24B","Mistral Small 3.2 24B Instruct","Mistral Small 3.2 24B Instruct 2506","Mistral Small 4","Mistral Small Instruct 2409","Mistral-7B-instruct-0.2","Mistral-7B-v0.1","Mistral-7B-v2","Mistral-8x7B","Mistral-8x7B-instruct-v0.1","Mistral-large-2 123B","Mixtral 8x22B","Mixtral 8x22B Instruct","Mixtral 8x22B v0.1","Mixtral 8x7B","Mixtral 8x7B Instruct","Mixtral 8x7B Instruct v0.1","Mixtral-8x22B-instruct-v0.1","Mld","Molmo 2 8B","Mplug-owl","Mplug-owl2","Nemotron 3 Nano 30B-A3B","Nemotron Research Reasoning","Nemotron Safety 8B","Nemotron-4-340B","Nomic Embed","Nous Hermes 2 Mixtral 8x7B DPO","Nova Lite v1","Nova Micro v1","Nova Premier v1","Nova Pro v1","Nvidia Dolphins Self-driving Llm","OLMo 2 0325 32B Instruct","OLMo 2 13B-1124","OLMo 2 32B-0325","OLMo 2 7B-1124","OLMo 3 7B Instruct","OLMo 3 7B Think","OLMo 3.1 32B Instruct","OLMoE 1B-7B-0125 Instruct","OPT","OPT 1.3B","OPT 13B","OPT 2.7B","OPT 30B","OPT 6.7B","OPT 66B","Omnilmm (12B)","OpenAI text-embedding-3-small","OpenChat 3.5","OpenChat 3.5 0106","OpenChat 3.6 8B","OpenFlamingo 4B","OpenFlamingo-v2","OpenHermes 13B Backdoor DEPLOYMENT","OpenThaiGPT 1.5 72B","OpenThaiGPT 1.5 7B","OpenVLA 7B","OpenVLThinker 7B","Openai GPT-3.5-turbo-0125","Openai GPT-4-0613","Orca 2 7B","Otter","Otter-Image","Ovis2 4B","PANNs","PaLM 2","Palm-2-otter","Pangea-7B","Pangu Pro MoE","PathoLM","Perspective","Phi 3 Medium 4k Instruct","Phi 3 Mini","Phi 3 Mini 4k Instruct","Phi 3 Small 8k Instruct","Phi 3.5 MoE","Phi 4 Mini","Phi Mini","Phi-1.5","Phi-2","Phi-3","Phi-3 3B","Phi-3 8B","Phi-3 Mini 3.8B","Phi-3-medium-28k-instruct","Phi-3-mini-128k-instruct","Phi-3.5 Mini","Phi-3.5 Mini Instruct","Phi-3.5 MoE Instruct","Phi-3.5 Vision Instruct","Phi-4","Phi-4 14B","Phi-4 14B Instruct","Phi-4 Mini Instruct","Phi-4 Mini Reasoning","Phi-4 Multimodal","Phi-4 Reasoning Plus","Pi-Zero","Pixtral 12B","Pixtral Large 2411","Prompt Guard","PromptGuard V2","Psycho 8B","Pythia 1.4B","Pythia 12B","Pythia 2.8B","Pythia 6.9B","Pythia 70M","Pythia-12B-chat","QVQ-Max","QVQ-Plus","QoQ-Med3-VL 8B","QwQ 32B","Qwen 1.5","Qwen 1.5 110B","Qwen 1.5 7B","Qwen 1.5 7B Chat","Qwen 1.8B","Qwen 14B","Qwen 14B Chat","Qwen 2 0.5B","Qwen 2 1.5B","Qwen 2 1.5B Instruct","Qwen 2 2B","Qwen 2 5B","Qwen 2 72B","Qwen 2 72B Instruct","Qwen 2 7B","Qwen 2 7B Instruct","Qwen 2 Audio","Qwen 2.5 0.5B","Qwen 2.5 0.5B Instruct","Qwen 2.5 1.5B","Qwen 2.5 1.5B Instruct","Qwen 2.5 14B","Qwen 2.5 14B Instruct","Qwen 2.5 32B","Qwen 2.5 32B Instruct","Qwen 2.5 32B Instruct AWQ","Qwen 2.5 3B","Qwen 2.5 3B Instruct","Qwen 2.5 72B","Qwen 2.5 72B Instruct","Qwen 2.5 72B Instruct AWQ","Qwen 2.5 7B","Qwen 2.5 7B Instruct","Qwen 2.5 Coder 14B","Qwen 2.5 Coder 32B","Qwen 2.5 Coder 32B Instruct","Qwen 2.5 Coder 7B Instruct","Qwen 2.5 Omni 3B","Qwen 2.5 Omni 7B","Qwen 2.5 VL 32B Instruct","Qwen 2.5 VL 3B Instruct","Qwen 2.5 VL 72B Instruct","Qwen 2.5 VL 7B Instruct","Qwen 2.5 VL Max","Qwen 3 0.6B","Qwen 3 1.7B","Qwen 3 1.7B FP8","Qwen 3 14B","Qwen 3 235B-A22B","Qwen 3 235B-A22B Instruct 2507","Qwen 3 235B-A22B Thinking","Qwen 3 30B-A3B","Qwen 3 30B-A3B Base","Qwen 3 30B-A3B Instruct","Qwen 3 30B-A3B Instruct-2507","Qwen 3 30B-A3B Thinking","Qwen 3 30B-A3B Thinking 2507","Qwen 3 32B","Qwen 3 32B FP8","Qwen 3 32B Instruct","Qwen 3 32B Thinking","Qwen 3 4B","Qwen 3 4B Base","Qwen 3 4B FP8","Qwen 3 4B Instruct","Qwen 3 4B Instruct 2507","Qwen 3 4B Think","Qwen 3 4B Thinking","Qwen 3 4B Thinking 2507","Qwen 3 8B","Qwen 3 8B FP8","Qwen 3 8B Instruct","Qwen 3 8B Thinking","Qwen 3 Coder 480B-A35B Instruct","Qwen 3 Guard 4B","Qwen 3 Max","Qwen 3 Max Thinking","Qwen 3 Next 80B-A3B Instruct","Qwen 3 Next 80B-A3B Thinking","Qwen 3.5 Plus","Qwen 32B","Qwen 72B","Qwen 7B","Qwen 7B Chat","Qwen Audio","Qwen Coder Turbo 20240919","Qwen Max","Qwen Max 20240919","Qwen Omni Turbo","Qwen Plus","Qwen Plus 20240919","Qwen Plus Latest","Qwen QwQ 32B","Qwen Turbo","Qwen Turbo 20240919","Qwen VL","Qwen VL 2 72B","Qwen VL Chat","Qwen VL Max","Qwen-2 (57B-a14B-instruct)","Qwen-2-7B-chat","Qwen-2.5-VL (7B)","Qwen-7B-v2","Qwen-Image-Edit-2512","Qwen-Image-Edit-Safe","Qwen-Max 2025-01-25","Qwen-SEA-LION v4 8B VL","Qwen-VL Plus","Qwen-max-latest","Qwen-vl-chat (7B)","Qwen1.5 MoE A2.7B Chat","Qwen1.5-110B-chat","Qwen2-Audio 7B","Qwen2-Audio 7B Instruct","Qwen2-VL 2B Instruct","Qwen2-VL 7B Instruct","Qwen2-VL-7B","Qwen3-11B","Qwen3-235B-A22B (MoE)","Qwen3-235B-A22B-Thinking (MoE)","Qwen3-Coder","Qwen3-Embedding-0.6B","Qwen3-Embedding-4B","Qwen3-Embedding-8B","Qwen3-Omni 30B-A3B Instruct","Qwen3-VL 235B-A22B Instruct","Qwen3-VL 2B Instruct","Qwen3-VL 30B-A3B Instruct","Qwen3-VL 32B Instruct","Qwen3-VL 4B Instruct","Qwen3-VL 8B","Qwen3-VL 8B Instruct","Qwen3-VL Flash","Qwen3-VL Plus","Qwen3-VL-235B","Qwen3-VL-32B","Qwen3Guard","Qwen3VL","R1-Onevision 7B","R2D2","RadFM","RoBERTa","RoBERTa Base","RoBERTa Large","SALMONN","SDXL Turbo","Safegen","Sarvam 1 Base","Sdxl","Sea-Lion v2 Instruct","SeaLLM v3 7B Chat","SeaLLMs v3 1.5B","SeaLLMs v3 7B","Seed 1.6","Seed 32B","Seedream 4.5","Sentence-T5 Base","ShareGPT4V 7B","Sharegpt4v-13B","Sheared-llama-1.3B","ShieldGemma 2 27B","ShieldGemma 27B","ShieldGemma 2B","ShieldGemma 9B","ShieldLM","ShieldLM 7B","Shikra(7B)","SigLIP-SO400M-Patch14-384","Skywork Reward V2","Skywork-R1V3 38B","Sld","Smaug-llama-3-70B-instruct","Solar 10.7B","Solar-10.7B-instruct-v1.0","Sonar Pro","Sora","Spark v3.0","SparkDesk v4.0","SpeechGPT","Stable Diffusion","Stable Diffusion 3 Medium","Stable Diffusion XL","Stable Diffusion Xl Refiner","Stable Diffusion v1.4","Stable Diffusion v1.5","Stable Diffusion v2.1","Stable Diffusion v3.5","Stable Vicuna","StableLM 2 12B Chat","StarChat 15B","StarCoder 15.5B","StarCoder2 15B","StarCoder2 3B","Starcoder-1B","Starcoder-3B","Starcoder-7B","Starling LM 7B","Starling-7B-alpha","Step 3","Step-Audio 2 Mini Base","T5","T5 Base","TNG R1T Chimera","TimeGPT","Tiny Llama 1.1B","TinyLlama 1.1","Tongyi DeepResearch 30B-A3B","Tongyiwanxiang","Transpec 13B","Trinity Mini","Tulu","Tulu-2-13B","Tulu-2-7B","Typhoon 2","Typhoon 2.1","Tülu 3 405B","Tülu 3 70B","Tülu 3 8B","UI-TARS 1.5 7B","UltraLM 13B","Ultravox","UniDiffuser","VILA 1.5","VILA 1.5 40B","VLAA-Thinker 7B","VLGuard","Vicuna 1 13B","Vicuna 1 7B","Vicuna 13B","Vicuna 13B v1.3","Vicuna 13B v1.5","Vicuna 2 13B","Vicuna 2 7B","Vicuna 33B","Vicuna 7B","Vicuna 7B v1.3","Vicuna 7B v1.5","Vicuna-1.3 (7B)","Vicuna-1.5-13B","Vicuna-13B Version 1.5","Vicuna-33B-v1.3","Vicuna-7B-1.5","Vicuna7B-v0.3","Vicunav1.5 13B","Vicunav1.5 7B","Video-LLaVA 7B","VideoLLAMA2","Vikhr Llama 3.2 1B Instruct","Vision-R1 7B","Voyage AI voyage-3.5-lite","Whisper Large-v2","WildGuard","Wizard Vicuna 13B","Wizard v1.1 33B","Wizard-lm-falcon-7B-uncensored","WizardCoder 15B","WizardCoder 3B","WizardCoder v1 15B","WizardLM 13B","WizardLM 13B v1.2","WizardLM 7B v1.0","WizardLM Uncensored","Wizardlm7B-uncensored","Xinghuo-3.5","XrayGLM","Yi 1.5","Yi 1.5 34B","Yi 1.5 6B","Yi 1.5 9B Chat","Yi 1.5 Chat 34B","Yi Large","Yi-34B","Yi-vl-34B","Zephyr","Zephyr 7B","Zephyr 7B Beta","Zephyr 7B R2D2","all-MiniLM-L6-v2","claude-opus-4-7","contriever-msmarco","gte-modernbert-base","mDeBERTa v3 Base","nomic-embed-text","o1","o1 2024-12-17","o1 Preview 20240912","o1-mini","o1-preview","o3","o3 Pro","o3-mini","o3-mini 2025-01-14","o3-preview","o4-mini","o4-mini Deep Research","openPangu-Embedded 1B","openPangu-Embedded 7B","s1.1 7B","text-embedding-ada-002","xLAM 2 32B"],"popularModels":["GPT-4o","GPT-3.5 Turbo","GPT-4","GPT-4o Mini","Llama 2 7B Chat","Llama 3 8B","Llama 3.1 8B","Claude 3.5 Sonnet"],"availableModels":["all-MiniLM-L6-v2","Gemini 3.1 Pro","Gemini 1.5 Flash","GPT-5.4","GPT-5.4-mini","GPT-5.4 Nano","Gemini 3 Flash","GPT-oss 120B","Qwen 3 8B","MiniMax M2.5","Llama 2 7B Chat","GPT-5.2","GPT-5 Mini","Claude Opus 4.5","Claude Sonnet 4.5","Gemini 3 Pro","DeepSeek V4 Flash","Gemini 2.5 Flash","Llama 3.1 8B","nomic-embed-text","Qwen3-VL 8B","Qwen2-VL-7B","InternVL3.5-8B","InternVL 2 8B","Llama 3.2 11B Vision","GPT-4.1 Mini","Gemini 2.5 Flash-Lite","Llama 3 8B Instruct","Llama 3 70B Instruct","GPT-5 Chat","GPT-4o Mini","Claude Opus 4.1","Llama 4 Maverick","DeepSeek Chat","Qwen 3 235B-A22B","Llama 3.1 8B Instruct","Mistral 7B Instruct v0.3","Qwen 3 4B Instruct 2507","Qwen 3 32B","Qwen 2.5 72B Instruct","Llama 3.3 70B Instruct","Qwen 3 30B-A3B Instruct-2507","Gemma3-4B Instruct","Qwen 3 4B Instruct","GPT-5","Qwen3-235B-A22B (MoE)","Qwen3-235B-A22B-Thinking (MoE)","Qwen 2.5 VL 3B Instruct","Gemma-4-E4B-it","Pangea-7B","Mistral 7B Instruct v0.2","Qwen 7B Chat","GPT-3.5 Turbo","GPT-5.5","Claude Sonnet 4.6","Kimi-K2.6","DeepSeek V4-Pro","GPT-4o","Claude Haiku 4.5","LLaVA Med","CLIP ViT-Large-Patch14-336","BGE-VL-base","SigLIP-SO400M-Patch14-384","GPT-oss 20B","Llama 3.1 70B","claude-opus-4-7","Qwen3-VL-235B","Qwen3-VL-32B","Gemma 2 2B IT","DeepSeek R1","GLM 4.5","Qwen 2.5 7B Instruct","DeepSeek R1 Distill Qwen 7B","Claude Sonnet 4","GPT-4.1","o4-mini","DeepSeek V3","GLM-4.7","Gemini 2.5 Pro","Kimi K2.5","GPT-5.1","Pi-Zero","OpenVLA 7B","3D-Diffuser Actor","Qwen 2.5 14B","Qwen 2.5 32B","Qwen 3 4B","Qwen 3 14B","Llama 3 8B","GLM 4 9B","Gemma 3 12B","Mistral 7B","Gemma 2 9B IT","DeepSeek R1 Distill Llama 8B","Crispers 7B","Psycho 8B","Qwen 2.5 72B","Tulu-2-7B","Llama 3.1 Tulu 3 8B DPO","OpenChat 3.5 0106","Claude 3.5 Haiku","Gemini 3.0 Pro","ERNIE 3.5","InstructBLIP","Sora","Stable Diffusion v1.4","Claude 3.7 Sonnet","GLM-4 32B","Llama 3.3 70B","Qwen 2.5 7B","Mistral Small 4","Qwen3Guard","Llama Guard 4","LLaVA 1.5 7B","LLaVA 1.5 13B","DeepSeek VL 1.3B","InternVL3 2B","Ovis2 4B","Qwen 3 4B Thinking 2507","DeepSeek R1 Distill Qwen 14B","Grok Code Fast 1","Claude Opus 4","o3","o3-mini","Claude 3.5 Sonnet","Gemini Pro","Llama 2 7B","Llama 3 70B","Mistral Large 12B","Gemma 2 9B","Phi-3","Gemini 2.0 Flash 001","Qwen3-VL Flash","Qwen 2.5 VL 7B Instruct","InternVL3 9B","Gemma 2 2B","Gemma 7B","DeepSeek R1 Distill Llama 70B","Mixtral 8x22B","GPT-4 Turbo","Qwen3-VL 30B-A3B Instruct","Vicuna 7B v1.5","Gemma 7B IT","Grok 3","Llama 3.1 405B","Qwen 1.5 7B Chat","Command R","Command A","DeepSeek LLM 7B Chat","Gemma 3 27B IT","Phi-4 14B","Grok 4.1 Fast","GLM-4 Voice","Qwen Omni Turbo","Gemma 3 4B","GLM-4 Air 250414","Grok 4","Gemini 3 Flash Preview","DeepSeek V3.2","Qwen2-Audio 7B Instruct","Qwen 2.5 Omni 7B","Audio Flamingo 3","Gemma 3n E2B","Llama 2 13B HarmBench","Llama Guard 3 8B","AegisGuard","JailJudge","Llama 4 Maverick 17B","o1","Gemma 3 4B IT","Llama 2 13B Chat","LLaVA OneVision Qwen2 0.5B","LLaVA OneVision Qwen2 7B Chat","Qwen2-VL 2B Instruct","Qwen2-VL 7B Instruct","Phi-4","Mistral Small 24B Base 2501","DeepSeek-V3 671B","Llama 4 17B","Qwen Plus","GPT-4","InternVL3 8B","GLM-4.1V 9B Thinking","Gemini 2.5 Flash Thinking","QVQ-Max","Claude 3 Haiku","Qwen 3 1.7B","Qwen 3 Max","Claude Opus 4.6","Gemini 3 Pro Preview","Grok 4.1 Fast Reasoning","Claude Sonnet 4.5 20250929","Claude 3.5 Haiku 20241022","GPT 3.5-turbo-0125","GPT-4 0613","GPT-4.5 Preview","Llama 3.2 3B Instruct","OLMo 2 0325 32B Instruct","OLMo 3.1 32B Instruct","Qwen 2 7B","LLaVA v1.6 Mistral 7B","Llama 3.2 11B Vision Instruct","GLM-4V Plus","Qwen-VL Plus","Llama 3.1 70B Instruct","Gemini 2.0 Flash","Mixtral 8x7B Instruct","Llama 3.2 3B","Qwen 2.5 3B","Llama 4 Scout","Mistral Small 3.2 24B","Gemma 3 12B IT","Ministral 3 8B Instruct-2512","Llama 3.2 1B Instruct","SeaLLMs v3 1.5B","SeaLLMs v3 7B","Llama SEA-LION v3 8B","Llama SEA-LION v3 70B","Typhoon 2","Typhoon 2.1","OpenThaiGPT 1.5 7B","OpenThaiGPT 1.5 72B","Gemma 7B Instruct","Qwen 2.5 3B Instruct","ShareGPT4V 7B","InternVL-Chat 19B","LLaVA-NeXT-Video 7B","Qwen3-VL 4B Instruct","Video-LLaVA 7B","Mistral 8B","Qwen3VL","InternVL","MiniCPM","GPT-5 Nano","GLM-4.6","Kimi K2 Instruct","MiniMax M2","Phi-3 8B","Qwen3-VL 32B Instruct","DeepSeek R1 Distill Qwen 1.5B","DeepScaleR 1.5B","DeepSeek R1 0528","Qwen 3 235B-A22B Thinking","MiniMax M2.1","GLM-5.1","MiniMax M2.7","MiMo V2.7","Grok 4.1 Mini","Tülu 3 8B","Tülu 3 70B","Tülu 3 405B","Qwen 2.5 32B Instruct","Mixtral 8x7B","Mixtral 8x22B v0.1","MedGemma 4B","MedGemma 27B","Meditron 7B","Meditron 70B","BioMistral 7B","MMed-Llama 3 8B","Phi-4 Mini Reasoning","Phi-3.5 Mini Instruct","Phi-2","Qwen 3 0.6B","DialoGPT Large","Phi-1.5","GPT-3.5","Yi 1.5 Chat 34B","Mistral Small Instruct 2409","DeepSeek V3.2 Exp","Qwen3-VL 235B-A22B Instruct","Qwen 2.5 VL 72B Instruct","GLM-4.5V","o4-mini Deep Research","Mistral Small 3.2 24B Instruct 2506","Mistral Medium 2505","Mistral Large 2411","Mistral Small 24B Instruct 2501","Llama 3.1 8B Lexi Uncensored V2","Llama 3.2 1B","R1-Onevision 7B","OpenVLThinker 7B","VLAA-Thinker 7B","Vision-R1 7B","LlamaV-o1","LLaVA-CoT","BLIP-2 OPT 2.7B","OpenFlamingo 4B","Kimi VL A3B Instruct","Phi-3 Mini 3.8B","Gemma 3 1B","Stable Diffusion","Llama 3.2 11B","GPT Image 1.5","Gemini 3 Pro Image","Seedream 4.5","Qwen-Image-Edit-2512","Qwen-Image-Edit-Safe","BAGEL 14B","Flux 2.0 Dev 32B","LongCat-Image-Edit","Ministral 8B Instruct","Qwen 1.5 7B","Sarvam 1 Base","Grok 4 Fast Non-Reasoning","Gemma 3 27B","Gemma 3 270M IT","Phi-4 Mini Instruct","Phi-4 Reasoning Plus","Llama 2 7B Backdoor DEPLOYMENT","OpenHermes 13B Backdoor DEPLOYMENT","Qwen 3 30B-A3B","Gemma 3 1B IT","Llama 3.2 90B","GPT-4.1 Nano","Meta-SecAlign 70B","DeepSeek-MoE 16B Chat","Hunyuan A13B Instruct","Mixtral 8x7B Instruct v0.1","Pangu Pro MoE","Phi-3.5 MoE Instruct","Qwen1.5 MoE A2.7B Chat","OLMoE 1B-7B-0125 Instruct","DeepSeek-V2","Qwen3-VL 8B Instruct","DeepSeek Reasoner","Qwen 3 235B-A22B Instruct 2507","DeepSeek R1 Distill Qwen 32B","Nemotron 3 Nano 30B-A3B","Qwen 3 30B-A3B Thinking","Grok 4 Fast","Grok 4.1","CLIP ViT-B/32","UniDiffuser","BLIP-2 ViT-g/14","InstructBLIP Vicuna 13B","MiniGPT-4 Vicuna 13B","LLaVA NeXT Qwen 1.5 72B Chat","Qwen 2.5 Coder 14B","Qwen 2.5 Coder 32B","CodeAstra","StarCoder2 15B","Qwen 2.5 32B Instruct AWQ","DeepSeek V3.1","Meta-SecAlign 8B","Qwen 2.5 14B Instruct","Qwen 2.5 72B Instruct AWQ","Llama 3.1 70B Instruct AWQ","Vicuna 7B","Qwen 3 30B-A3B Thinking 2507","Qwen VL Chat","E5 BERT-base","Skywork Reward V2","LLaVA-OneVision 1.5 8B Instruct","Qwen-SEA-LION v4 8B VL","QoQ-Med3-VL 8B","Gemini 1.5 Pro","Qwen2-Audio 7B","Qwen3-11B","Vicuna 13B","gte-modernbert-base","OpenAI text-embedding-3-small","Voyage AI voyage-3.5-lite","Alibaba Cloud text-embedding-v4","contriever-msmarco","Qwen3-Embedding-0.6B","Qwen3-Embedding-4B","Qwen3-Embedding-8B","DeepSeek Chat V3.1","Kimi K2","Magistral Medium 2506","Mistral Small 3.2 24B Instruct","Kimi K2 Thinking","xLAM 2 32B","Qwen 2 1.5B","Qwen 2.5 0.5B","Qwen 2.5 1.5B","Pythia 70M","Llama 2 13B","Pythia 1.4B","Pythia 2.8B","Pythia 6.9B","Pythia 12B","GPT-NeoX 20B","OPT 1.3B","OPT 2.7B","OPT 6.7B","OPT 13B","OPT 30B","OPT 66B","GPT-2","GPT-4o Realtime","Llama 3.1 70B Hanami X1","Aion 1.0","Sonar Pro","Llama 3.1 Nemotron Ultra 253B v1","Mercury","UI-TARS 1.5 7B","Jamba Mini 1.7","Hermes 4 70B","Step 3","LongCat Flash Chat","Tongyi DeepResearch 30B-A3B","Cydonia 24B v4.1","ERNIE 4.5 21B-A3B Thinking","Granite 4.0 H Micro","LFM2 8B-A1B","Nova Premier v1","KAT Coder Pro","Cogito v2.1 671B","TNG R1T Chimera","Intellect 3","DeepSeek V3.2 Speciale","Trinity Mini","Mistral Large 2512","DeepSeek V3.1 Nex N1","MiMo V2 Flash","Seed 1.6","Molmo 2 8B","GPT-5.2 Codex","MiniCPM4 0.5B","MiniCPM4 8B","Hunyuan 0.5B","Hunyuan 1.8B","Hunyuan 7B","openPangu-Embedded 1B","openPangu-Embedded 7B","GLM 4.5 Air","Grok 3 Mini","Mistral Medium 3.1","Qwen 3 30B-A3B Instruct","Qwen 3 Next 80B-A3B Instruct","Mantis-CLIP","Mantis-SIGLIP","Mantis-Idefics2","VILA 1.5","LLaVA 1.6","MiniGPT-4","HuatuoGPT-o1-7B","Llama 3.1 405B Instruct","Llama 4 Maverick 17B Instruct","OLMo 3 7B Instruct","OLMo 3 7B Think","DALL-E","Midjourney","Grok 2 Vision","GLM-4.1V Thinking","Baichuan 2 7B Chat","Llama 4 Maverick Instruct","Qwen-Max 2025-01-25","GPT-5.1 2025-11-13","GPT-4o 2024-11-20","Llama Guard 4 12B","WildGuard","FinBERT","FinGPT","FinLLaMA","o3 Pro","GPT-4o Mini High","Qwen 3.5 Plus","GLM-5","Vicuna 13B v1.5","GPT-5.2 Pro","GPT-5.2 Thinking","o3-preview","Gemini 3 Deep Think","Mistral Large 3","Ministral 3","Devstral 2","Qwen3-Coder","Mistral Medium 3","Qwen QwQ 32B","Magistral Medium","Mistral 7B 8B","Qwen 2.5 1.5B Instruct","HateBERT","HateRoBERTa","Llama Guard 3 1B","Qwen 3 Guard 4B","ShieldGemma 2B","GPT-4.1 2025-04-14","GPT-5 Chat 2025-10-03","Claude Haiku 4.5 20251001","Doubao 1.6 Thinking 250715","ChatGLM2 6B","GPT-2 124M","Llama 7B","Llama 13B","Llama 33B","LLaVA 7B","Qwen 2.5 VL 32B Instruct","Llama 3 LLaVA-NeXT 8B","InternVL3 38B","InternVL3 78B","MiniCPM-o 2.6","Skywork-R1V3 38B","Doubao Seed 1.6","ERNIE 4.5 Turbo 128K Preview","Claude 3 Opus","Mistral 7B Instruct","LLaVA 1.6 Mistral 7B","Gemma 2 27B","Qwen 3 8B Instruct","Claude 3.7 Sonnet 20250219","Qwen 3 4B Base","Qwen 3 4B Thinking","Qwen 3 30B-A3B Base","Qwen 3 4B Think","Gemma 1.1 7B","Gemini 2.0 Flash-Lite","Qwen 3 1.7B FP8","Qwen 3 4B FP8","Qwen 3 8B FP8","Qwen 3 32B FP8","VideoLLAMA2","Qwen 2 7B Instruct","Whisper Large-v2","PANNs","Mistral Large","Seed 32B","Gemma 3n E4B","DeepSeek V3.2 Thinking","Qwen 3 Next 80B-A3B Thinking","o1-mini","Qwen 3 8B Thinking","Qwen 3 32B Thinking","Qwen 3 32B Instruct","Qwen3-VL 2B Instruct","InternVL3 2B Instruct","InternVL3 8B Instruct","InternVL3 14B Instruct","InternVL3 38B Instruct","InternVL3.5 4B Instruct","InternVL3.5 8B Instruct","InternVL3.5 14B Instruct","InternVL3.5 38B Instruct","LLaVA v1.6 Vicuna 7B","LLaVA v1.6 Vicuna 13B","LLaVA v1.6 34B","InternVL3 1B","LLaVA-OneVision 0.5B","LLaVA-OneVision 7B","Gemini 1.5 Pro Latest","Gemini 1.5 Pro 002","Gemini 1.5 Flash Latest","Claude 3.5 Sonnet Latest","Llama 3.2 90B Vision Instruct","Yi 1.5 9B Chat","Zephyr 7B Beta","StableLM 2 12B Chat","InternLM 2.5 7B Chat","Phi 3 Small 8k Instruct","Falcon-Mamba 7B Instruct","Kimi K2 Preview","Gemini 2.0 Pro","Cogito 2.1","Circuit Breaker","Gemma 2B","Llama Guard 3","Lumimaid 70B","MAI DS R1 671B","DeepSeek R1 0528 Qwen3 8B","DeepSeek R1 671B","Qwen 7B","Falcon 3 10B","Mistral Small 22B","GPT-4o 2024-08-06","Gemini 2.5 Flash Preview 04-17","Mistral 7B v0.3","LLaDA 8B Base","Phi 4 Mini","BERT","DeBERTa v3 Base","Llama Guard 2 8B","Qwen Max","RoBERTa","Transpec 13B","Nemotron Safety 8B","Granite Guardian 3.2 5B","Qwen3-VL Plus","DeepSeek-VL2","Qwen 2.5 0.5B Instruct","Ministral 8B Instruct 2410","Command R+","InternVL2.5 8B","Mistral Large 2","Step-Audio 2 Mini Base","MiniCPM-o 2.6 8B","Qwen3-Omni 30B-A3B Instruct","Kimi-Audio 7B Instruct","Baichuan 2 13B","Baichuan 2 7B","DeepSeek 7B","DeepSeek R1 Distill","Llama 2 70B","Llama Guard","Orca 2 7B","Qwen 14B","Qwen 32B","Qwen 72B","Solar 10.7B","Zephyr 7B","LLaVA 1.6 7B","Qwen-2.5-VL (7B)","GPT-4V","QwQ 32B","DeepResearcher 7B","Claude Sonnet 3.6","GPT-4.5","Grok 3 Beta","s1.1 7B","Nemotron Research Reasoning","Llama 3.2 90B Vision","Gemma 1.1 7B IT","Dolphin Mistral 24B Venice","Mistral Large 2.1","LISA 7B","LISA Explanatory 7B","LISA 13B","LISA Explanatory 13B","LISA++ 7B","GSVA 13B","GPT-4o Mini 2024-07-18","Llama 4 Scout 17B","OLMo 2 7B-1124","OLMo 2 13B-1124","OLMo 2 32B-0325","Grok 2","Mistral Nemo Instruct","WizardLM Uncensored","GPT-oss Safeguard 20B","ShieldGemma 9B","ERNIE 4.5","Gemma 2 27B IT","Prompt Guard","ShieldGemma 2 27B","Gemini 2.0 Pro Exp 0205","Qwen VL Max","LLaVA-OneVision","Falcon 7B","GPT-2 Large","PromptGuard V2","Granite Guardian","Mistral Small","Nova Pro v1","Claude 3.7 Sonnet Thinking","Grok 3 Mini Beta","GLM 4 Plus","Doubao 1.5 Thinking Pro","ERNIE 4.0 Turbo","GPT-5 Chat Latest","Sea-Lion v2 Instruct","SeaLLM v3 7B Chat","Mistral Large 24B","BLIP-2","LLaVA-v2","Otter-Image","OpenFlamingo-v2","Dolphins","EmbodiedGPT","DistilBERT","DarkIdol Llama 3.1 8B Instruct","GLM 4 9B Chat","LongChat 7B","MiniGPT-v2","Qwen 2 5B","Yi Large","Nova Lite v1","Nova Micro v1","Claude 3 Sonnet","Claude 3.5 Sonnet 20240620","Claude 3.5 Sonnet 20241022","Granite 3.1 8B","Ministral 8B","Mistral Nemo","Mixtral 8x22B Instruct","Pixtral Large 2411","o1 2024-12-17","o3-mini 2025-01-14","Falcon 3 10B Instruct","Grok 2 1212","InternVL3 14B","Qwen 2.5 Omni 3B","Phi-4 Multimodal","Guanaco 7B","Gemini 2.0 Flash Thinking","IntentionReasoner 1.5B","IntentionReasoner 3B","Phi-3 3B","LLaVA v1.6 13B","Qwen 2.5 VL Max","QVQ-Plus","Qwen 2 2B","Qwen Plus Latest","Doubao Seed 1.6 Flash","Grok 3 Fast","Mistral Small 24B","Qwen 3 Coder 480B-A35B Instruct","GLM 9B","Hermes 3 Llama 3.1 405B","DREAM v0 Instruct 7B","LLaDA 1.5","LLaDA 8B Instruct","MMaDA 8B MixCoT","GPT-3","Gemini 2.0 Flash Preview Image Generation","Llama 4 16x17B","Devstral 24B","DeepSeek R1 Tool Calling 70B","InstructBLIP Vicuna 7B","MMaDA 8B Base","InternVL 2.5 78B","LLaVA 7B Chat","InternLM 2.5 20B","Llama 2 70B Chat","LLaVA OneVision Qwen2 72B","Pixtral 12B","Gemini 2.5 Flash Preview","DeepSeek Coder 33B","GPT-4o Preview 20240801","GPT-4o No-Safe Preview 20240801","o1 Preview 20240912","Qwen Coder Turbo 20240919","Qwen Max 20240919","Qwen Plus 20240919","Qwen Turbo 20240919","SparkDesk v4.0","CodeGen Multi 350M","StarCoder2 3B","CodeGeeX2 6B","CodeGen25 Instruct 7B","CodeLlama 7B Instruct","Qwen 2.5 Coder 7B Instruct","WizardCoder v1 15B","StarCoder 15.5B","DeepSeek Coder V2 Lite 16B","Qwen 2.5 Coder 32B Instruct","Wizard v1.1 33B","CodeLlama 70B Instruct","Mistral Large Instruct 2407 123B","DeepSeek Chat V2 236B","DeepSeek Coder V2 Instruct 0724 236B","BERT Base","HCX-002","HCX-003","HCX-DASH-002","Qwen Turbo","BLSP","FunAudioLLM","Ichigo","Llama Omni","LLaSM","Mini-Omni","Mini-Omni 2","Qwen 2 Audio","Qwen Audio","SALMONN","SpeechGPT","GLM","Evo1 7B","Evo2 1B","Evo2 7B","Evo2 40B","PathoLM","DALL-E 3","Flux Schnell","InternVL 2 2B","ShieldLM 7B","Beaver 7B v1.0 Cost","Falcon 7B Instruct","MPT 7B Chat","Falcon 3 3B Instruct","Qwen 2 1.5B Instruct","Phi 3 Mini","DiVA","GPT-4o Audio","Claude 1","Claude 2","ERNIE 3.5 Turbo","Qwen 3 Max Thinking","DeepSeek V3 0324","Qwen 1.8B","Yi 1.5 6B","mDeBERTa v3 Base","DIVA Llama 3 v0 8B","MERaLion AudioLLM","Ultravox","Gemini 1.0 Pro Vision","LLaVA 1.5","Phi-4 14B Instruct","Bunny 1.0 4B","Mplug-owl2","Code Llama 13B Instruct","DeepSeek Coder 7B","Vikhr Llama 3.2 1B Instruct","Phi-3.5 Mini","GigaChat-Max","Atla Selene Mini 8B","CLIP","Imagen","SDXL Turbo","Stable Diffusion v3.5","GLM 3 6B","Qwen 2 72B","Flux","Stable Diffusion XL","LLaVA Mistral","Qwen VL","InternLM XComposer","Phi 3.5 MoE","Aegis Defensive","Aegis Permissive","Llama Guard 2","Perspective","ShieldGemma 27B","Cygnet","o1-preview","R2D2","Vicuna 7B v1.3","Guanaco 13B","Claude 2.1","Qwen 14B Chat","LLaVA NeXT 8B","GLM 4 9B Chat HF","Gemma 1.1 2B","Qwen 2 72B Instruct","Phi-3.5 Vision Instruct","ChatGLM 6B","Gemini Exp 1206","Gemini Flash","Baichuan 2","Dolly 2","OPT","OpenChat 3.6 8B","Starling LM 7B","InternVL 2 4B","InternVL 2 26B","VLGuard","Granite 3.1 8B Instruct","Zephyr","E5 Base v2","Jina Embeddings v2","Nomic Embed","Sentence-T5 Base","Alpaca","M3E","MiniLM","Megatron 345M","Tiny Llama 1.1B","Barkplug V.2","Gemini-1.5-flash-001","Gemini-1.5-pro-001","Flan-t5 Large","Gemma 2B IT","Meta-llama-3-8B","Mistral-7B-v0.1","Mistral-8x7B-instruct-v0.1","Phi-3-mini-128k-instruct","Alpaca 7B","TimeGPT","Claude-v2","InternLM 2.5 7B","Qwen 1.5 110B","Yi 1.5 34B","Deepseek-vl7B-chat","Glm-4v-9B","GPT-4o-0513","Llava v1.5-7B","Llava v1.6-mistral-7B-hf","Yi-vl-34B","Mixtral-8x22B-instruct-v0.1","Palm-2-otter","Stable Diffusion v2.1","Baichuan-13B","Claude-3(v3-haiku)","ShieldLM","InternVL 2 40B","Qwen VL 2 72B","VILA 1.5 40B","Mistral-7B-instruct-0.2","Vicuna-7B-1.5","Phi 3 Medium 4k Instruct","Phi 3 Mini 4k Instruct","Qwen 2 0.5B","Qwen-2 (57B-a14B-instruct)","Chameleon","LLaVA 2","Inf-mllm1","GPT-4-1106-turbo","Llama 2 Chat","Deepseek-v2.5","Glm-4-flash","Qwen-max-latest","Llama 3 70B Chat","Llama-3-8B Chat","Mistral-large-2 123B","Chameleon 30B","Chameleon 7B","LLaVA 1.6 Llama 3","Vicuna7B-v0.3","Aquilachat-7B","Baichuan 2 13B Chat","Baichuan-7B","GPT-2 XL","Internlm2-chat-7B","Llama-2-13B-hf","Llama-2-7B-hf","Llava-v1.6-vicuna-7B-hf","Minitron-8B-base","Phi Mini","Qwen 1.5","GPT-J 6B","GPT-Neo 2.7B","RoBERTa Base","RoBERTa Large","T5","Nvidia Dolphins Self-driving Llm","Llama Guard 7B","ChatGLM3 6B","Deepseek-coder","Gemma2-8B-instruct","Glm-4-air","Gemini 1.5 Flash (block None)","Gemini 1.5 Pro (block None)","ChatGLM4","FastChat-T5 3B","GPT-4 Turbo-2024-04-09","GPT-4o-2024-05-13","GPT-3.5 (GPT-3.5-turbo-0125)","GPT-4o Mini (GPT-4o-mini-2024-07-18)","Yi 1.5","Mdm","Mld","Sharegpt4v-13B","Stable Diffusion 3 Medium","Stable Diffusion Xl Refiner","Vicuna-1.5-13B","Cogview3","Dall-e 2","Hunyuan","Sdxl","Tongyiwanxiang","Clip-vit-base-patch32","GPT 3.5-turbo-instruct","Safegen","Sld","Stable Diffusion v1.5","Claude-3-haiku-0307","GPT-4-turbo-0409","Qwen-2-7B-chat","Code Llama 7B","Mistral-8x7B","WizardLM 13B","Mistral 7B v0.2","text-embedding-ada-002","Aya-23-8B","Cohere-35B","OpenChat 3.5","Phi-3-medium-28k-instruct","Smaug-llama-3-70B-instruct","Solar-10.7B-instruct-v1.0","TinyLlama 1.1","UltraLM 13B","Anthropic Claude-3-sonnet20240229","Llama2-7-billion","Openai GPT-3.5-turbo-0125","Openai GPT-4-0613","Vicuna-1.3 (7B)","FinanceChat 7B","LawChat 7B","Xinghuo-3.5","Falcon-40B-instruct","Llama2-chat-7B","Zephyr 7B R2D2","Flan-T5 XL","Starling-7B-alpha","Llama-3-70B-chat-hf","Qwen1.5-110B-chat","CheXagent","Med-Flamingo","RadFM","XrayGLM","Starcoder-1B","Starcoder-3B","Starcoder-7B","Tulu-2-13B","Internvlchat-v1.5","Omnilmm (12B)","Qwen-vl-chat (7B)","Claude 2.0","Llama-2-chat-70B","Llama 3-instruct 8B","Nemotron-4-340B","Pythia-12B-chat","GPT","PaLM 2","Gemini Ultra","Flan-T5 XXL","T5 Base","Vicuna 33B","Wizard Vicuna 13B","GPT-3.5-1106)","Llama-2-sys","Chatglm-2 (chatglm2-6B)","Chatglm-3 (chatglm3-6B)","Claude Instant 1.2","Gemini (gemini-pro)","GPT-3.5 (GPT-3.5-turbo-1106)","GPT-4 (GPT-4-1106-preview)","Llama-2 (llama2-7B-chat)","Alpaca 7B (Safe-RLHF)","Flan-T5 11B","Flan-T5 3B","Nous Hermes 2 Mixtral 8x7B DPO","GPT-4-1106","Codellama 34B Instruct","Gemini Vision Pro","Guanaco-7B-hf","Llama 2-13B-chat-hf","Vicuna-33B-v1.3","Wizard-lm-falcon-7B-uncensored","Wizardlm7B-uncensored","Claude 1.2 Instant","Claude 1.3","Internlm-20B","Sheared-llama-1.3B","StarChat 15B","WizardCoder 15B","WizardCoder 3B","GPT-NeoX","Llama 2-7B-chat-hf","Vicuna-13B Version 1.5","Chatglm-turbo","Midjourney v6","Spark v3.0","Codellama-13B-python","GPT-3.5-turbo-instruct-0914","Yi-34B","GPT-3 13B","Vicunav1.5 13B","Vicunav1.5 7B","GPT-3.5 Turbo-0301","MPT 7B Instruct","Vicuna 13B v1.3","WizardLM 7B v1.0","WizardLM 13B v1.2","Cogvlm","Idefics","Llama-adapterv2","Minigpt-5(7B)","Minigpt-v2(7B)","Mplug-owl","Otter","Shikra(7B)","Claude-instant-v1","Cogvlm-chat-v1.1","Llava-v1.5-vicuna-v1.5-13B","Llava-v1.5-vicuna-v1.5-7B","Minigpt4-llama-2-chat-7B","Minigpt4-vicuna-7B","GPT-3.5 Turbo-1106","GPT-4-0125-preview","Llama-1","Mistral-7B-v2","Qwen-7B-v2","Vicuna 1 7B","Vicuna 1 13B","Vicuna 2 7B","Vicuna 2 13B","Falcon-chat-180B","Llama2-chat-13B","Tulu","ERNIE","Claude Instant 1","GPT-4-0314","MPT 7B","Stable Vicuna"],"availableTags":["application-layer","agent","coding-agent","model-supply-chain","injection","prompt-layer","poisoning","embedding","data-security","integrity","safety","reliability","computer-use","model-layer","jailbreak","whitebox","memory","blackbox","rag","vision","multimodal","extraction","prompt-leaking","api","data-privacy","chain","fine-tuning","mcp","infrastructure-layer","denial-of-service","hallucination","audio","side-channel","video"],"tagCounts":{"application-layer":253,"agent":249,"coding-agent":4,"model-supply-chain":4,"injection":323,"prompt-layer":599,"poisoning":109,"embedding":70,"data-security":153,"integrity":521,"safety":781,"reliability":187,"computer-use":2,"model-layer":465,"jailbreak":703,"whitebox":226,"memory":4,"blackbox":733,"rag":97,"vision":128,"multimodal":173,"extraction":97,"prompt-leaking":22,"api":79,"data-privacy":102,"chain":96,"fine-tuning":123,"mcp":2,"infrastructure-layer":16,"denial-of-service":34,"hallucination":52,"audio":19,"side-channel":20,"video":3},"matchingTagCounts":{"application-layer":253,"agent":249,"coding-agent":4,"model-supply-chain":4,"injection":323,"prompt-layer":599,"poisoning":109,"embedding":70,"data-security":153,"integrity":521,"safety":781,"reliability":187,"computer-use":2,"model-layer":465,"jailbreak":703,"whitebox":226,"memory":4,"blackbox":733,"rag":97,"vision":128,"multimodal":173,"extraction":97,"prompt-leaking":22,"api":79,"data-privacy":102,"chain":96,"fine-tuning":123,"mcp":2,"infrastructure-layer":16,"denial-of-service":34,"hallucination":52,"audio":19,"side-channel":20,"video":3},"availableSources":[{"id":"arxiv","label":"arXiv","count":959}],"stats":{"totalEntries":959,"affectedModels":1077,"latestAnalysisDate":"2026-07-21T03:30:52.772Z"}}