Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
Sakana: Fugu Ultra
ModelsFugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
sakana/fugu-ultra -
Qwen: Qwen3.7 Max
ModelsQwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...
qwen/qwen3.7-max -
MoonshotAI: Kimi K2 Thinking
ModelsKimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
moonshotai/kimi-k2-thinking -
Perplexity: Sonar Pro Search
ModelsExclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...
perplexity/sonar-pro-search -
LiquidAI: LFM3-1.7B (free)
ModelsA compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...
liquid/lfm-3-1.7b:free -
IBM: Granite 4.2 8B
ModelsGranite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...
ibm-granite/granite-4.2-8b -
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
nvidia/nemotron-3.5-lightning:free -
Meituan: LongCat 2.0
ModelsLongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...
meituan/longcat-2.0 -
MiniMax: MiniMax M2.1
ModelsMiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...
minimax/minimax-m2.1 -
Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...
meta/muse-glimmer-30b:batch -
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, reasoning, and agent workflows....
deepseek/deepseek-v4-flash-0731:batch -
LiquidAI: LFM2.5-24B-A2B
ModelsLFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...
liquid/lfm-2.5-24b-a2b -
StepFun: Step 5 Preview
ModelsStep 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...
stepfun/step-5-preview -
Sakana: Fugu Max
ModelsFugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
sakana/fugu-max -
Google: Gemini 3.8 Flash
ModelsGemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
google/gemini-3.8-flash -
Qwen: Qwen3.8 Flash
ModelsQwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.
qwen/qwen3.8-flash -
MoonshotAI: Kimi K3
ModelsKimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
moonshotai/kimi-k3 -
Anthropic: Claude Sonnet 5
ModelsSonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
anthropic/claude-sonnet-5 -
MiniMax: MiniMax M3
ModelsMiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
minimax/minimax-m3 -
Xiaomi: MiMo-V2.5-Pro
ModelsMiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....
xiaomi/mimo-v2.5-pro -
Mistral: Devstral 2 2512
ModelsDevstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...
mistralai/devstral-2512 -
Qwen: Qwen3 Coder 480B A35B
ModelsQwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...
qwen/qwen3-coder -
inclusionAI: Ling 3.0 Tiny
ModelsLing 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction following, and multi-turn conversations, with switchable...
inclusionai/ling-3.0-tiny -
Meta: Muse Wonder
ModelsMuse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...
meta/muse-wonder
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.