Marketplace
Every AI tool worth knowing, in one place
974 AI tools, language models and open source projects. Compare specs and pricing side by side.
Featured
Tools we would reach for first.
Most capable AI model for coding, analysis, and complex reasoning tasks.
Gemini 2.5 Pro and Flash models with 1M context window and native multimodal input.
Open-source workflow automation with 400+ integrations and self-hosting support.
AI research assistant that answers questions with real-time citations.
Codeium's AI IDE with Flows — deep agentic coding built into the editor.
AI-powered automation connecting 6,000+ apps with natural-language Zap creation.
All AI tools
Ranked by how complete the listing is.
A list of 100 beautiful prompts for Stable Diffusion.
A popular web-based interface for running Stable Diffusion models, offering extensive features and customization options.
Open-source browser sandbox and automation infrastructure for AI agents and apps with session-backed workflows, screenshots, PDFs, proxies, and anti-bot tooling.
A cutting-edge AI tool focused on transforming music creation with advanced deep learning models for audio generation and enhancement.
Tooling for giving AI systems richer capabilities and more flexible action patterns in practical workflows.
AI video creation platform that allows you to create professional videos with AI avatars, perfect for business presentations.
Open-source machine learning framework by Google.
Comprehensive open-source machine learning framework.
Currently in development, this humanoid robot by Tesla is designed for everyday tasks and human interaction.
A user-friendly web interface for running and interacting with text generation models, supporting a variety of models and configurations.
Add-in for Microsoft Word that seamlessly integrates essential AI tools, including text generation, proofreading, and more, directly into the user interface.
AI-powered storytelling tool that helps in creating dynamic narratives with text, images, and video integrations.
Curated list of prompts for various AI art generators.
Open-source (MIT) Claude Code plugin with 9 SEO and Google Ads skills. Pulls real Google Search Console, PageSpeed Insights, and Google Ads API data, audits traffic and wasted ad spend,…
An AI-driven branding and design tool that helps create unique fonts and typographic designs.
An AI-powered platform designed to simplify and innovate audio editing and production, making high-quality audio accessible to everyone.
A more advanced robotic dog capable of carrying heavier loads and performing complex tasks, popular for research and industrial use.
A new quadruped robot with industrial-grade capabilities, rugged design, and powerful AI-driven functionality.
A quadruped robot "dog" designed for agility, real-time obstacle avoidance, and smooth motion. It is well-suited for hobbyists, educational institutions, and light security tasks.
AI-powered service that generates JavaScript modules with TypeScript signatures via URL for rapid prototyping.
Enables processing of very large documents, codebases, and multi-step workflows
A marketplace for renting affordable AI compute, including GPUs.
Google’s current video generation models, with stronger control, better consistency, and native audio support.
Dedicated tool to remove video backgrounds without a green screen, with free no-watermark exports.
Offers a unique blend of business model canvassing and AI-driven market analysis.
Text-to-speech with natural-sounding voices.
Convert voice to instrument tracks using AI for music production and audio content creation.
Speech understanding and transcription models (including realtime variants)
AI-powered blogs to help ChatGPT/Claude/Perplexity cite your product.
Open source framework for debugging LLM agents and RAG pipelines with a 16-mode ProblemMap and practical triage checklists.
Developer-focused tool for natural language processing.
Company → [News](https://x.ai/news) · [API docs](https://docs.x.ai/) · [API console](https://console.x.ai/) · [GitHub](https://github.com/xai-org)
A highly efficient AI accelerator that can plug into Raspberry Pi and other SBCs, designed for low-power AI tasks like face recognition, object detection, and anomaly detection in IoT…
Automation tool integrating OpenAI's capabilities.
Plenty of space across Google Drive, Photos, and Gmail.
Get more access to Google's most powerful models for help with complex topics, coding, and writing.
A curated bundle of offers from various AI companies, which has previously included extended free trials for services like ElevenLabs and Perplexity Pro.
A new upcoming pack focused on providing students with the essential AI tools for their education. Currently on a waitlist.
Early iterations were replaced as Amazon revised its approach.
Discontinued and replaced by newer versions.
Can implement features, refactor code, and manage workflows
Can implement features, fix bugs, and handle tasks end-to-end
Nothing matches that search.
Aider
CLI coding assistant that edits your codebase, runs tests, and commits changes via git. Works with Claude, GPT-4o, Gemini, and local models.
MCP Servers
Anthropic's collection of reference MCP servers: filesystem, GitHub, Slack, PostgreSQL, Puppeteer, Google Drive, and more — ready to connect to Claude and any MCP client.
Ollama
Get up and running with LLMs like Llama 4, Gemma, and Phi on your Mac, Linux, or Windows machine — no cloud required.
Open WebUI
Feature-rich, offline-capable web interface for running LLMs locally. Works with Ollama, OpenAI API, and any OpenAI-compatible endpoint.
code-review-graph
Local knowledge graph for Claude Code. Builds a persistent map of your codebase so Claude reads only what matters — 6.8× fewer tokens on reviews and up to 49× on daily coding tasks.
AutoGen
Research-backed multi-agent framework from Microsoft. Agents converse with each other and humans to solve complex tasks via code execution, tool calls, and planning.
Chroma
Open-source vector database for storing and querying embeddings. Runs in-memory, on-disk, or as a server. Native LangChain and LlamaIndex integrations.
Continue
IDE extension that connects any LLM to your editor for autocomplete, chat, and inline editing. Fully customisable — use any model, any context source.
CrewAI
Framework for orchestrating teams of specialized AI agents. Role-based agents collaborate on complex tasks. $20M+ in VC funding. Apache-2.0.
DSPy
Stanford framework that replaces prompt engineering with optimisers. Define your program logic, then DSPy compiles it into optimised prompts and fine-tunes using your examples.
Haystack
Deepset's open-source framework for building production-ready LLM pipelines. Component-based architecture for RAG, question answering, summarisation, and agent systems.
Instructor
Python library that patches any LLM client (OpenAI, Anthropic, Gemini) to return validated Pydantic models instead of raw JSON strings, with automatic retry on failure.
LangChain
One of the most widely used frameworks for building LLM-powered agents and chains. Extensive integrations. Raised $125M at $1.25B valuation (Oct 2025). MIT.
LiteLLM
Python SDK and proxy server that standardises calls to OpenAI, Anthropic, Gemini, Bedrock, and 100+ models behind a single OpenAI-compatible interface.
LlamaIndex
Python and TypeScript framework for building RAG pipelines and agents over structured and unstructured data. 160+ loaders, vector store integrations, and agentic workflows.
Open Interpreter
Lets LLMs execute Python, JavaScript, and shell commands locally. Interactive terminal REPL — describe what you want done and the model writes and runs the code.
PydanticAI
Agent framework from the Pydantic team. Define agents with typed tools and structured outputs, tested with testable dependency injection and model-agnostic design.
Qdrant
Production-grade vector database with filtering, scalar quantisation, and a REST + gRPC API. Available as a Docker image, managed cloud, or embedded.
Vercel AI SDK
Official TypeScript/JavaScript SDK for streaming text, structured data, and tool calls from any LLM. First-class React/Next.js hooks for real-time streaming UIs.
No open source projects match your search.
Claude Sonnet 4
AnthropicAnthropic's mid-tier flagship — the sweet spot of intelligence and speed. 200K context, strong coding and reasoning, with optional extended thinking and prompt caching.
DeepSeek R1
DeepSeekDeepSeek's open-weight reasoning model. Matches o1 on math and science benchmarks with visible chain-of-thought, MIT licence, and 13K+ HuggingFace likes — the most-downloaded open reasoning model.
DeepSeek V3
DeepSeekDeepSeek's flagship MoE model — 671B total / 37B active params, 128K context, and near-GPT-4 performance at a fraction of the cost. MIT licence with 4K+ HuggingFace likes.
Gemini 2.5 Pro
GoogleGoogle's most capable model — 1M token context, state-of-the-art reasoning with hybrid thinking, and top scores on AIME, GPQA, and long-context retrieval benchmarks.
Llama 4 Maverick
MetaMeta's most capable open-weights model. 17B active / 400B total MoE with 1M context, strong MMLU scores that match GPT-4o, and native multimodal support.
Llama 4 Scout
MetaMeta's 17B-active / 109B-total MoE model with a world-record 10 million token context window. Open weights, natively multimodal, and highly efficient for long-context tasks.
GPT-4o
OpenAIOpenAI's flagship omni-modal model. Fast, multimodal (text, vision, audio), 128K context, and strong across reasoning, coding, and instruction following.
Nova 2 Lite
AmazonNova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...
Nova Lite 1.0
AmazonAmazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...
Nova Micro 1.0
AmazonAmazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...
Nova Premier 1.0
AmazonAmazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.
Nova Pro 1.0
AmazonAmazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...
Claude 3 Haiku
AnthropicClaude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku) #multimodal
Claude 3.5 Haiku
AnthropicClaude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic...
Claude 3.7 Sonnet
AnthropicClaude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and...
Claude Haiku 4
AnthropicAnthropic's fastest and most affordable Claude 4 model. Matches Sonnet on coding benchmarks at 3× lower cost and 2× the speed — ideal for real-time and agent workloads.
Claude Haiku 4.5
AnthropicFastest model optimized for quick responses and high-throughput tasks
Claude Opus 4
AnthropicClaude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...
Claude Opus 4.1
AnthropicClaude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...
Claude Opus 4.5
AnthropicPrevious flagship, still available for compatibility and specific workloads
Claude Opus 4.6
AnthropicMost capable model for deep reasoning, coding, and long-running agent workflows
Claude Opus 4.6 (Fast)
AnthropicFast-mode variant of [Opus 4.6](/anthropic/claude-opus-4.6) - identical capabilities with higher output speed at premium 6x pricing. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode
Claude Opus 4.7
AnthropicOpus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...
Claude Sonnet 4.5
AnthropicEarlier balanced model, widely used in production systems
Claude Sonnet 4.6
AnthropicDefault model balancing performance, speed, and cost
Command A
CohereCommand A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...
Command R (08-2024)
Coherecommand-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...
Command R+
CohereCohere's enterprise-grade 104B model optimised for RAG and multi-step tool use. 128K context, strong multilingual retrieval, and built-in citation support.
Command R7B (12-2024)
CohereCommand R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...
DeepSeek V3 0324
DeepSeekDeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...
DeepSeek V3.1
DeepSeekDeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
DeepSeek V3.1 Terminus
DeepSeekDeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing
DeepSeek V3.2
DeepSeekDeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
DeepSeek V3.2 Exp
DeepSeekDeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
DeepSeek V3.2 Speciale
DeepSeekDeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context processing, then scales post-training reinforcement lea
DeepSeek V4 Flash
DeepSeekDeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
DeepSeek V4 Pro
DeepSeekDeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
R1
DeepSeekDeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....
R1 0528
DeepSeekMay 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
R1 Distill Llama 70B
DeepSeekDeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to a
R1 Distill Qwen 32B
DeepSeekDeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, ach
Gemini 2.0 Flash
GoogleGemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5). It...
Gemini 2.0 Flash Lite
GoogleGemini 2.0 Flash Lite offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5),...
Gemini 2.5 Flash
GoogleGoogle's fast and affordable model with 1M token context and optional thinking. Best price-to-performance in the Gemini 2.5 family for high-volume tasks.
Gemini 2.5 Flash Lite
GoogleGemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
Gemini 2.5 Flash Lite Preview 09-2025
GoogleGemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
Gemini 2.5 Pro Preview 05-06
GoogleGemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...
Gemini 2.5 Pro Preview 06-05
GoogleGemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...
Gemini 3 Flash Preview
GoogleGemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...
Gemini 3.1 Flash Lite
GoogleGemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...
Gemini 3.1 Flash Lite Preview
GoogleGemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...
Gemini 3.1 Pro Preview
GoogleGemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...
Gemini 3.1 Pro Preview Custom Tools
GoogleGemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...
Gemma 2 27B
GoogleGoogle's 27B open-weight model from the Gemma 2 family. Competitive with Llama 3 70B on many benchmarks at a fraction of the size, using a novel interleaved attention architecture.
Gemma 2b IT Lora
GoogleThis is a Gemma-2B base model that Cloudflare dedicates for inference with LoRA adapters. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.
Gemma 3 12B
GoogleGemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
Gemma 3 12b IT
GoogleGemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Gemma 3 models are multimodal, handling text and image input and generating text output, with a
Gemma 3 27B
GoogleGemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
Gemma 3 4B
GoogleGemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
Gemma 3n 4B
GoogleGemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...
Gemma 4 26B A4B
GoogleGemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Gemma 4 26b A4b IT
GoogleGemma 4 is Google's most intelligent family of open models, built from Gemini 3 research to maximize intelligence-per-parameter.
Gemma 4 31B
GoogleGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Gemma 7b IT Lora
GoogleThis is a Gemma-7B base model that Cloudflare dedicates for inference with LoRA adapters. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.
Lyria 3 Clip Preview
Google30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...
Lyria 3 Pro Preview
GoogleFull-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality, 48kHz...
Nano Banana (Gemini 2.5 Flash Image)
GoogleGemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
GoogleGemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...
Nano Banana Pro (Gemini 3 Pro Image Preview)
GoogleNano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...
Llama 2 7b Chat Fp16
MetaFull precision (fp16) generative text model with 7 billion parameters from Meta
Llama 2 7b Chat Hf Lora
MetaThis is a Llama2 base model that Cloudflare dedicated for inference with LoRA adapters. Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for t
Llama 2 7b Chat Int8
MetaQuantized (int8) generative text model with 7 billion parameters from Meta
Llama 3 1 8b Instruct Awq
MetaQuantized (int4) generative text model with 8 billion parameters from Meta.
Llama 3 1 8b Instruct Fast
Meta[Fast version] The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models. The Llama 3.1 instruction tuned text only models are optimized for multilingual dialogue
Llama 3 1 8b Instruct Fp8
MetaLlama 3.1 8B quantized to FP8 precision
Llama 3 3 70b Instruct Fp8 Fast
MetaLlama 3.3 70B quantized to fp8 precision, optimized to be faster.
Llama 3 70B Instruct
MetaMeta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...
Llama 3 8B Instruct
MetaMeta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...
Llama 3 8b Instruct Awq
MetaQuantized (int4) generative text model with 8 billion parameters from Meta.
Llama 3.1 70B Instruct
MetaMeta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...
Llama 3.1 8B Instruct
MetaMeta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...
Llama 3.2 11B Vision Instruct
MetaLlama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and...
Llama 3.2 1B Instruct
MetaLlama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...
Llama 3.2 3B Instruct
MetaLlama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...
Llama 3.3 70B Instruct
MetaThe Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
Llama 4 Scout 17b 16e Instruct
MetaMeta's Llama 4 Scout is a 17 billion parameter model with 16 experts that is natively multimodal. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.
Llama Guard 3 8B
MetaLlama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification)...
Llama Guard 4 12B
MetaLlama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...
Codestral 2508
MistralMistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestra
Devstral 2 2512
MistralDevstral 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...
Devstral Medium
MistralDevstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves...
Devstral Small 1.1
MistralDevstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral Small 3.1 and...
Ministral 3 14B 2512
MistralThe largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...
Ministral 3 3B 2512
MistralThe smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
Ministral 3 8B 2512
MistralA balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
Mistral 7B Instruct v0.1
MistralA 7.3B parameter model that outperforms Llama 2 13B on all benchmarks, with optimizations for speed and context length.
Mistral 7b Instruct V0 2 Lora
MistralThe Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.
Mistral Large
MistralThis is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-l
Mistral Large 2407
MistralThis is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-lar
Mistral Large 2411
MistralMistral Large 2 2411 is an update of [Mistral Large 2](/mistralai/mistral-large) released together with [Pixtral Large 2411](/mistralai/pixtral-large-2411) It provides a significant upgrade on the previous [Mistral Large 24.07](/mistralai/mistral-lar
Mistral Large 3 2512
MistralMistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
Mistral Medium 3
MistralMistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...
Mistral Medium 3.1
MistralMistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...
Mistral Medium 3.5
MistralMistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
Mistral Nemo
MistralA 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...
Mistral Small 3
MistralMistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...
Mistral Small 3 1 24b Instruct
MistralBuilding upon Mistral Small 3 (2501), Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance. With 24 billion parameters, this model achieves
Mistral Small 3.1 24B
MistralMistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...
Mistral Small 3.2
MistralMistral's refined 24B model with 128K context, vision support, and Apache 2.0 licence. Beats Mixtral 8x7B on most benchmarks at much lower cost — 1M+ HuggingFace downloads.
Mistral Small 3.2 24B
MistralMistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on..
Mistral Small 4
MistralMistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
Mixtral 8x22B Instruct
MistralMistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
Mixtral 8x7B
MistralMistral AI's original sparse MoE model — 46.7B total / 12.9B active params, Apache 2.0 licence, 32K context. Fast, cost-efficient, and one of the most widely deployed open-weight models.
Pixtral Large 2411
MistralPixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral Large 2](/mistralai/mistral-large-2411). The model is able to understand documents, charts and natural images. The model is...
Saba
MistralMistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...
Voxtral Small 24B 2507
MistralVoxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...
GPT Audio
OpenAIThe gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...
GPT Audio Mini
OpenAIA cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...
GPT Chat Latest
OpenAIGPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...
GPT-3.5 Turbo
OpenAIGPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
GPT-3.5 Turbo (older v0613)
OpenAIGPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
GPT-3.5 Turbo 16k
OpenAIThis model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...
GPT-3.5 Turbo Instruct
OpenAIThis model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.
GPT-4
OpenAIOpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...
GPT-4 (older v0314)
OpenAIGPT-4-0314 is the first version of GPT-4 released, with a context length of 8,192 tokens, and was supported until June 14. Training data: up to Sep 2021.
GPT-4 Turbo
OpenAIThe latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.
GPT-4 Turbo (older v1106)
OpenAIThe latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to April 2023.
GPT-4 Turbo Preview
OpenAIThe preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...
GPT-4.1
OpenAIGPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...
GPT-4.1 Mini
OpenAIGPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...
GPT-4.1 Nano
OpenAIFor tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...
GPT-4o (2024-05-13)
OpenAIGPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...
GPT-4o (2024-08-06)
OpenAIThe 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o ("o" for
GPT-4o (2024-11-20)
OpenAIThe 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...
GPT-4o Audio
OpenAIThe gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio outputs...
GPT-4o Search Preview
OpenAIGPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.
GPT-4o mini
OpenAIOpenAI's cost-efficient small model. Delivers strong multimodal performance at a fraction of GPT-4o cost — ideal for high-volume, latency-sensitive applications.
GPT-4o-mini (2024-07-18)
OpenAIGPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...
GPT-4o-mini Search Preview
OpenAIGPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.
GPT-5
OpenAIGPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...
GPT-5 Chat
OpenAIGPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.
GPT-5 Codex
OpenAISpecialized coding model optimized for large codebases, debugging, and multi-step development workflows
GPT-5 Image
OpenAI[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superi
GPT-5 Image Mini
OpenAIGPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction fo
GPT-5 Mini
OpenAIGPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....
GPT-5 Nano
OpenAIGPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...
GPT-5 Pro
OpenAIGPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...
GPT-5.1
OpenAIGPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...
GPT-5.1 Chat
OpenAIGPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...
GPT-5.1-Codex
OpenAIGPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....
GPT-5.1-Codex-Max
OpenAIGPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...
GPT-5.1-Codex-Mini
OpenAIGPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex
GPT-5.2
OpenAIGPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...
GPT-5.2 Chat
OpenAIGPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...
GPT-5.2 Pro
OpenAIGPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...
GPT-5.2-Codex
OpenAIGPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....
GPT-5.3 Chat
OpenAIGPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly...
GPT-5.3-Codex
OpenAIGPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results
GPT-5.4
OpenAIOpenAI’s most capable model for reasoning, coding, and complex tasks.
GPT-5.4 Image 2
OpenAI[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, c
GPT-5.4 Mini
OpenAIGPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...
GPT-5.4 Nano
OpenAIGPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...
GPT-5.4 Pro
OpenAIHigher-performance variant for demanding workloads.
GPT-5.5
OpenAIGPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
GPT-5.5 Pro
OpenAIGPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...
gpt-oss-120b
OpenAIgpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
gpt-oss-20b
OpenAIgpt-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 forward pass, optimized for...
gpt-oss-safeguard-20b
OpenAIgpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...
o1
OpenAIThe latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...
o1-pro
OpenAIThe o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...
o3
OpenAIo3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....
o3 Deep Research
OpenAIo3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.
o3 Mini
OpenAIOpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...
o3 Mini High
OpenAIOpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...
o3 Pro
OpenAIThe o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...
o4 Mini
OpenAIOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...
o4 Mini Deep Research
OpenAIo4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.
o4 Mini High
OpenAIOpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...
Deepseek R1 Distill Qwen 32b
OtherDeepSeek-R1-Distill-Qwen-32B is a model distilled from DeepSeek-R1 based on Qwen2.5. It outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.
Gemma Sea Lion V4 27b IT
OtherSEA-LION stands for Southeast Asian Languages In One Network, which is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.
Glm 4 7 Flash
OtherGLM-4.7-Flash is a fast and efficient multilingual text generation model with a 131,072 token context window. Optimized for dialogue, instruction-following, and multi-turn tool calling across 100+ languages.
Granite 4 0 H Micro
OtherGranite 4.0 instruct models deliver strong performance across benchmarks, achieving industry-leading results in key agentic tasks like instruction following and function calling. These efficiencies make the models well-suited for a wide range of use
Kimi K2 5
OtherKimi K2.5 is a frontier-scale open-source model with a 256k context window, multi-turn tool calling, vision inputs, and structured outputs for agentic workloads.
Kimi K2 6
OtherKimi K2.6 is a frontier-scale open-source 1T parameter model with a 262.1k context window, multi-turn tool calling, vision inputs, and structured outputs for agentic workloads.
Nemotron 3 120b A12b
OtherNVIDIA Nemotron 3 Super is a hybrid MoE model with leading accuracy for multi-agent applications and specialized agentic AI systems.
Phi 2
OtherPhi-2 is a Transformer-based model with a next-word prediction objective, trained on 1.4T tokens from multiple passes on a mixture of Synthetic and Web datasets for NLP and coding.
Phi-4
OtherMicrosoft's 14B small language model focused on math and code. Outperforms many 70B models on MMLU (84.8) and MATH (80.4), with MIT licence and 600K+ HuggingFace downloads.
Qwen2 5 Coder 32b Instruct
OtherQwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different de
Qwen2.5 72B
OtherAlibaba's top open-weight model at 72B. Achieves 86.1 on MMLU and 83.1 on MATH, with 130K context and strong multilingual + code capabilities. 580K+ HuggingFace downloads.
Qwen3 30b A3b Fp8
OtherQwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-f
Qwq 32b
OtherQwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B
Sqlcoder 7b 2
OtherThis model is intended to be used by non-technical users to understand data inside their SQL databases.
Grok 3
xAIGrok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in...
Grok 3 Beta
xAIGrok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in...
Grok 3 Mini
xAIA lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.
Grok 3 Mini Beta
xAIGrok 3 Mini is a lightweight, smaller thinking model. Unlike traditional models that generate answers immediately, Grok 3 Mini thinks before responding. It’s ideal for reasoning-heavy tasks that don’t demand...
Grok 4
xAIGrok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not...
Grok 4 Fast
xAIGrok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model...
Grok 4.1 Fast
xAIGrok 4.1 Fast is xAI's best agentic tool calling model that shines in real-world use cases like customer support and deep research. 2M context window. Reasoning can be enabled/disabled using...
Grok 4.20
xAIGrok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...
Grok 4.20 Multi-Agent
xAIGrok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...
Grok 4.3
xAIGrok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
Grok Code Fast 1
xAIGrok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-quality...
Alpaca
OtherDeveloped by Stanford, Alpaca is an instruction-following model based on LLaMA, fine-tuned for improved performance on specific tasks. Alpaca can be deployed locally, allowing researchers…
Cerebras-GPT
OtherCerebras Systems provides open-source GPT models optimized for their AI-specific hardware. While designed for large-scale deployment, Cerebras-GPT models can also be run on specific…
Claude Opus 3
OtherLegacy high-capability model, still accessible in some environments
Code Llama (legacy)
OtherEarlier coding-focused models, still used but largely superseded by newer Llama 3.x models
DeepSeek-VL2
OtherDeepSeek-VL2 — AI tool
Dolly 2.0
OtherDeveloped by Databricks, Dolly 2.0 is an open-source, instruction-tuned LLM that can be run locally, offering a cost-effective alternative for businesses looking for tailored solutions…
Flan-T5
OtherA variant of Google’s T5 model, fine-tuned with instruction-based learning (Flan). Flan-T5 is popular in the open-source community for various natural language processing tasks, and it can…
GPT-4 in ChatGPT
OtherRemoved from the ChatGPT interface and replaced by newer models.
GPT-4.1 in ChatGPT
OtherRemoved from the ChatGPT interface.
GPT-4.1 mini in ChatGPT
OtherRemoved from the ChatGPT interface.
GPT-4.5-preview
OtherDeprecated and removed from the API.
GPT-4o in ChatGPT
OtherRemoved from the ChatGPT interface as newer models were introduced.
GPT-5 Instant in ChatGPT
OtherRemoved from the ChatGPT model selector.
GPT-5 Thinking in ChatGPT
OtherRemoved from the ChatGPT model selector.
GPT-5.4 Mini / Nano
OtherOptimized for speed, cost-efficiency, and scale.
GPT4All
OtherGPT4All offers a range of locally deployable language models that are specifically optimized to run on consumer-grade hardware. Ideal for users who want to run a high-quality LLM without…
Gemini 3
OtherGoogle’s current top model family for reasoning, planning, coding, and multimodal tasks.
Gemini 3 Flash
OtherFaster, lighter model optimized for speed and everyday use.
Gemini 3.1 Flash Live
OtherBuilt for more natural real-time audio and live multimodal interaction.
Gemini 3.1 Pro
OtherHigher-end version for complex workflows, stronger reasoning, and demanding real-world tasks.
Gemma 3 / 3n
OtherEarlier lightweight open models still relevant for efficient and local-first deployments.
Gemma 4
OtherGoogle’s newest open model family, built for advanced reasoning and agentic workflows, and designed to run well on consumer GPUs.
LLaMA 2
OtherMeta’s open-source language model that can be run locally on powerful hardware setups. LLaMA 2 is designed for researchers and developers who need a customizable, open-source solution for…
Llama 3.1
OtherCurrent production-grade model family with strong performance in reasoning, coding, and multilingual tasks
Llama 3.1 405B
OtherMeta’s largest open-weight model, competitive with top proprietary models
Llama 3.1 70B / 8B
OtherSmaller variants optimized for performance vs efficiency trade-offs
Llama 3.2 Vision
OtherAdds image understanding capabilities on top of the Llama architecture
Meta LLaMA 3.1 Models
OtherOfficial repository to use and implement LLaMA 3.1 models, Meta's state-of-the-art large language models.
Mistral 7B
OtherLegacy lightweight model, now mostly replaced by newer small models
Mixtral (8x7B / 8x22B)
OtherEarlier MoE models, still widely used but no longer flagship
OpenAssistant
OtherA community-driven project that provides open-source LLMs for various conversational tasks, similar to ChatGPT. OpenAssistant models can be deployed locally, giving developers full control…
Qwen2.5
OtherQwen2.5 — AI tool
Qwen3
OtherQwen3 — AI tool
Qwen3-Coder
OtherCoding-focused family
Qwen3-Omni
OtherUnified multimodal family
Qwen3-TTS
OtherSpeech / voice generation
Qwen3-VL
OtherVision-language models
Qwen3.5
OtherQwen3.5 — AI tool
Vicuna
OtherA powerful open-source model fine-tuned from LLaMA, designed to be conversational and responsive, similar to ChatGPT. Vicuna is available for local deployment, allowing developers to…
WizardLM
OtherWizardLM is a family of fine-tuned models based on open-source language models, optimized for instruction-following tasks. Known for its high-quality performance in natural language…
deepseek-chat
Othercurrently mapped to **DeepSeek-V3.2** non-thinking mode
deepseek-reasoner
Othercurrently mapped to **DeepSeek-V3.2** thinking mode
gpt-image-1
OtherCurrent image generation model with strong editing and prompt adherence.
gpt-realtime / gpt-audio
OtherModels for speech, transcription, and real-time interaction.
o1-mini
OtherDeprecated and removed from the API.
o1-preview
OtherDeprecated and removed from the API.
qwen-flash
Other/ **[qwen3.5-flash](https://www.alibabacloud.com/help/en/model-studio/model-pricing)** – Lower-cost / faster models
qwen-max
OtherHigh-end general model
qwen-plus
OtherBalanced production model
qwen3-max
OtherNewer reasoning-capable model with thinking and non-thinking modes
qwen3.5-flash
Otherstarts at $0.029 / 1M input, $0.287 / 1M output for the first 128K
No models match your search.