Model Documentation

The Yi series models are large language models trained from scratch by developers at 01.AI. This 34B parameter model has been instruct-tuned specifically for chat applications, providing optimized per...

Yi-VL-34B is the world's first open-source 34 billion parameter vision-language model, combining advanced image understanding with multilingual text generation capabilities. It represents a significan...

This is a 32-billion parameter model emphasizing reasoning capabilities. The system excels at deep reasoning, complex multi-step logic, and advanced instruction following. Version 3.1 represents impro...

Goliath 120B is a merged model that combines "two fine-tuned Llama 70B models into one 120B model" by merging Xwin and Euryale variants. The model was created using the mergekit framework by @chargodd...

Amazon's multimodal model designed to balance "accuracy, speed, and cost for a wide range of tasks." As of December 2024, it demonstrates state-of-the-art performance on visual question answering (Tex...

Magnum v4 72B is a fine-tuned version of Qwen2.5 72B that aims to replicate the prose quality of Claude 3 models, specifically Sonnet and Opus. This model is designed for creative writing and roleplay...

Anthropic's fastest and most compact Claude 3 model. Designed for near-instant responses while maintaining high-quality output. Ideal for high-volume, cost-sensitive applications.

Anthropic's most intelligent model with best-in-market performance on highly complex tasks. Navigates open-ended prompts and sight-unseen scenarios with remarkable fluency and human-like understanding...

Claude 3 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments. It offers excellent performance w...

Anthropic's balanced Claude 3 model offering a good combination of capability and speed. Suitable for most general-purpose applications requiring quality responses.

Anthropic's Claude 3.5 Sonnet is a balanced AI model that combines strong intelligence with fast response times. This specific version from October 22, 2024 provides a fixed checkpoint for reproducibl...

Claude Haiku 4.5 is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Anthropic, this cost-effective model is optimized for efficient inference while maint...

Claude Opus 4 is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Anthropic, this model is optimized for its specific use case category.

Hybrid reasoning model pushing frontier for coding and AI agents with extended thinking capabilities. Achieves 74.5% on SWE-bench Verified with 32K max output tokens.

Claude Opus 4.5 is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Anthropic, this flagship model represents the latest capabilities and state-of-the-art...

Claude Sonnet 4 is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Anthropic, this model is optimized for its specific use case category.

Claude Sonnet 4.5 is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Anthropic, this premium model offers excellent quality and balanced performance acro...

Claude 3 Haiku is Anthropic's fastest and most compact model, designed for near-instant responsiveness with quick and accurate targeted performance. It excels at tasks requiring rapid responses while ...

Claude 3.5 Haiku offers enhanced capabilities in speed, coding accuracy, and tool use. It is engineered to excel in real-time applications, delivering quick response times.

Claude 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 software...

Claude Sonnet 4 represents a significant upgrade from its predecessor, Claude Sonnet 3.7, with particular strength in coding and reasoning tasks. The model achieves state-of-the-art performance on SWE...

**Model ID:** `baidu/ernie-4.5-21b-a3b-thinking`

FLUX.2 [max] is the new top-tier image model from Black Forest Labs, pushing image quality, prompt understanding, and editing consistency to the highest level yet.

FLUX.1 [schnell] is Black Forest Labs' fastest image generation model, a 12 billion parameter rectified flow transformer capable of generating high-quality images from text descriptions. Trained using...

Command 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. The model emphasizes delivering...

Command R is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Cohere, this model provides solid performance and is suitable for most use cases.

Command R+ is a 104B-parameter large language model from Cohere, purpose-built for enterprise applications. It excels at roleplay, general consumer use cases, and Retrieval Augmented Generation (RAG)....

Command R7B is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Cohere, this model is optimized for its specific use case category.

Embed 4 is a text embedding model for semantic search and vector-based tasks. Developed by Cohere, this model is optimized for its specific use case category.

Rerank 4 Fast is a AI model for general-purpose tasks. Developed by Cohere, this model is optimized for its specific use case category.

Rerank 4 Pro is a AI model for general-purpose tasks. Developed by Cohere, this model is optimized for its specific use case category.

The **Auto Free Collection** is a dynamic system-level collection that automatically routes inference requests to one of the predefined free models available in the system. This collection provides co...

The **Flash 2.5 Collection** is a curated organization-level collection of fast-responding, lightweight language models optimized for speed and cost-effectiveness. This collection focuses on models th...

The **Organization Shared Models** collection is a flexible, team-managed collection that enables organizations to pool and share language models across all members. This collection uses a least-used ...

DeepSeek R1 is DeepSeek AI's first-generation reasoning model that achieves performance on par with OpenAI o1 across math, code, and reasoning tasks. It is fully open-source with MIT licensing, featur...

DeepSeek Coder V2 is a code generation and understanding model for programming tasks. Developed by DeepSeek, this model provides solid performance and is suitable for most use cases.

**Model ID:** `deepseek/deepseek-v3.2`

Main chat model with JSON output and tool calling capabilities. Optimized for conversational AI, general-purpose tasks, and integration with external tools and APIs.

DeepSeek's specialized reasoning model designed for complex problem-solving, mathematical proofs, and logical analysis. Features extended thinking capabilities for step-by-step reasoning.

EVA Llama 3.33 70B is a roleplay and storywriting specialist model. It is a complete parameter fine-tune of the Llama-3.3-70B-Instruct base model using a mixture of synthetic and natural data. The mod...

Gemini Embedding is a text embedding model for semantic search and vector-based tasks. Developed by Google AI, this model is optimized for its specific use case category.

Gemini 1.5 Flash is a foundation model that performs well at a variety of multimodal tasks such as visual understanding, classification, summarization, and creating content from image, audio and video...

Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to Gemini Flash 1.5, while maintaining quality on par with larger models like Gemini Pro 1.5. It introduces notable e...

Code completion model.

A specialized research-focused model designed for deep analysis, literature review, and comprehensive research tasks. Optimized for synthesizing information from multiple sources and providing thoroug...

Lightweight embedding model.

Gemini 1.0 with vision (deprecated).

Previous generation pro model.

Gemini 2 Flash with extended reasoning capabilities.

A cost-effective multimodal model optimized for general-purpose tasks requiring balanced performance. Gemini 2.0 Flash delivers strong capabilities across text, image, and code understanding while mai...

An experimental version of Gemini 2.0 Flash with image generation capabilities. Combines text understanding with the ability to generate images based on prompts.

The stable version 001 release of Gemini 2.0 Flash, providing a cost-effective multimodal model for general-purpose tasks. This versioned release ensures consistent behavior and reproducible results f...

An experimental preview of Gemini 2.0 Flash featuring the latest capabilities and improvements. This version provides early access to new features while maintaining the fast inference speeds character...

A preview version of Gemini 2.0 Flash optimized for image generation tasks. Designed for creating visual content from text descriptions.

An experimental version of Gemini 2.0 Flash with enhanced reasoning capabilities. This model features a "thinking" mode that allows it to work through complex problems step-by-step before providing fi...

A dated experimental version of Gemini 2.0 Flash with thinking capabilities from January 21, 2025. Features improved reasoning capabilities over earlier thinking model versions.

A dated experimental version of Gemini 2.0 Flash with thinking capabilities from December 19, 2024. Provides enhanced reasoning through explicit step-by-step problem solving.

Streamlined and ultra-efficient model designed for simple, high-frequency tasks. Gemini 2.0 Flash-Lite prioritizes speed and affordability while maintaining essential multimodal capabilities.

A preview version of Gemini 2.0 Flash-Lite, providing early access to streamlined capabilities optimized for high-frequency, simple tasks. This model supports multimodal capabilities including vision ...

A dated preview version of Gemini 2.0 Flash-Lite from February 5, 2025. Provides a fixed checkpoint for reproducible results. This model supports multimodal capabilities including vision and image und...

Professional-grade Gemini 2.0 model.

An experimental version of Gemini 2.0 Pro offering higher capability than Flash variants. Designed for complex tasks requiring advanced reasoning, coding, and multimodal understanding.

A dated experimental version of Gemini 2.0 Pro from February 5, 2025. Provides high-capability performance for complex tasks with a specific model checkpoint.

Vision-optimized Gemini 2.0 Pro.

A specialized preview model designed for computer use and automation tasks. Enables AI-driven interaction with computer interfaces, including clicking, typing, and navigating applications.

Lightning-fast and highly capable model that delivers a balance of intelligence and latency. Gemini 2.5 Flash offers controllable thinking budgets for versatile applications, making it ideal for a wid...

A specialized image-focused variant of Gemini 2.5 Flash, codenamed Nano Banana. Optimized for image understanding and generation tasks with fast inference.

A preview version of the image-focused Gemini 2.5 Flash variant, codenamed Nano Banana. Provides early access to enhanced image capabilities.

Preview of Gemini 2.5 Flash.

A dated preview of Gemini 2.5 Flash from May 20, 2025. Provides a fixed model checkpoint for reproducible experiments and applications.

A September 2025 preview of Gemini 2.5 Flash with the latest capabilities and improvements before stable release. This model supports multimodal capabilities including vision and image understanding.

A specialized preview of Gemini 2.5 Flash with text-to-speech capabilities. Combines fast inference with high-quality voice synthesis for real-time audio applications.

Built for massive scale, Gemini 2.5 Flash-Lite balances cost and performance for high-throughput tasks. Optimized for efficiency without sacrificing multimodal capabilities.

A dated preview version of Gemini 2.5 Flash-Lite from June 17, 2025. Optimized for efficiency and high-throughput tasks with a fixed checkpoint.

A September 2025 preview of Gemini 2.5 Flash-Lite, optimized for efficiency and cost-effectiveness in high-throughput applications. This model supports multimodal capabilities including vision and ima...

Google's high-capability model for complex reasoning and coding. Features adaptive thinking and a 1 million token context window, designed for complex agentic and multimodal challenges. Gemini 2.5 Pro...

A dated preview version of Gemini 2.5 Pro from March 25, 2025. Provides access to advanced capabilities with a fixed model checkpoint for reproducibility.

Gemini 2.5 Pro is Google's latest and most capable model, featuring a massive 1 million token context window. This preview version (06-05) represents the cutting edge of Google's multimodal AI capabil...

A specialized preview of Gemini 2.5 Pro with text-to-speech capabilities. Designed for applications requiring high-quality voice synthesis alongside advanced language understanding.

Fast Gemini 3 for speed and efficiency.

Lightweight Gemini 3 optimized for mobile devices.

High-end model for demanding applications.

Latest flagship Gemini model with advanced reasoning and multimodal capabilities.

Balanced mid-tier Gemini model.

Audio analysis model.

Advanced code analysis and generation model.

Specialized model for document processing and extraction.

An experimental Gemini model from December 6, 2024. Provides early access to new capabilities and improvements in development. This model supports multimodal capabilities including vision and image un...

Gemini Flash Latest with optimized speed for rapid response generation. This model supports multimodal capabilities including vision and image understanding.

The latest stable version of Gemini Flash-Lite, automatically updated to the most recent stable release. Optimized for efficiency and high-throughput tasks.

Image generation from text.

Real-time streaming multimodal model.

Smallest Gemini model.

The latest stable version of Gemini Pro, automatically updated to the most recent stable release. Provides high-capability performance for complex tasks.

Experimental advanced reasoning engine for complex tasks.

A specialized model for robotics and embodied reasoning (ER) applications. Designed to understand and reason about physical environments, robot actions, and spatial relationships.

Latest text embedding model.

Video analysis and understanding.

Previous Gemma generation 7B model.

Previous generation 27B model.

Compact 12B instruction-tuned model.

A lightweight, instruction-tuned version of Gemma 3 with 1 billion parameters. Designed for edge deployment and resource-constrained environments while maintaining good instruction-following capabilit...

Open-source 27B instruction-tuned model.

Ultra-lightweight 4B model.

Extended context Gemma 3 27B.

Extended context version of Gemma 3 27B supporting up to 1M token context.

An efficient variant of Gemma 3 with approximately 2B equivalent parameters, optimized for edge deployment and mobile applications. Part of the Gemma 3n efficient model series.

An efficient variant of Gemma 3 with approximately 4B equivalent parameters, balancing capability and efficiency for edge and mobile deployment.

An experimental model designed specifically for educational applications. LearnLM is optimized for tutoring, explanation generation, and adaptive learning interactions. This model supports multimodal ...

Advanced multimodal model.

A high-capability image-focused model codenamed Nano Banana Pro. Designed for advanced image understanding and generation with professional-grade quality. This model supports multimodal capabilities i...

A high-capability image-focused model codenamed Nano Banana Pro. Part of the Gemini 3 Pro family with specialized capabilities for advanced image understanding and generation.

Legacy PaLM chat model (deprecated).

Legacy PaLM text model (deprecated).

Allam 2 is a 7 billion parameter Arabic language model optimized for Arabic text understanding and generation. Hosted on Groq's LPU infrastructure for ultra-fast inference.

Groq: Command Nightly is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

An AI system powered by openly available models that intelligently and selectively uses built-in tools to answer user queries, including web search and code execution. Compound represents Groq's appro...

A lightweight version of Groq Compound with built-in web search and code execution capabilities. Optimized for faster responses and cost efficiency while maintaining agentic capabilities.

Groq: DeepSeek R1 Distill Llama 70B is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

This model has been deprecated and is no longer recommended for new deployments. It is retained in the system for backward compatibility only. Please migrate to current model versions for production u...

Groq: Distil Whisper Large V3 EN is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

Groq: Gemma 2 9B IT is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

Groq: Gemma 7B IT is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

GPT OSS 120B 128k is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Groq, this model is optimized for its specific use case category.

GPT OSS 20B 128k is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Groq, this model is optimized for its specific use case category.

GPT OSS Safeguard 20B is a content moderation model for safety and policy compliance checking. Developed by Groq, this model is optimized for its specific use case category.

Groq: GPT-4 Turbo is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

Groq: GPT-4 Vision Preview is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

Groq: GPT-4o Mini is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

OpenAI's flagship open-weight language model with 120 billion parameters, hosted on Groq infrastructure. Features built-in browser search and code execution capabilities with reasoning.

A lightweight 20 billion parameter version of OpenAI's open-weight GPT-OSS model. Optimized for fast inference on Groq infrastructure.

A safety-focused 20 billion parameter model based on GPT-OSS. Fine-tuned for content moderation and safety-critical applications.

Kimi K2 1T 256k is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Groq, this model is optimized for its specific use case category.

MoonshotAI's Kimi K2 instruction-tuned model, hosted on Groq infrastructure for fast inference. Designed for general-purpose instruction following with strong multilingual capabilities.

A dated version of MoonshotAI's Kimi K2 instruction model from September 5, 2025. Features an extended context window for longer conversations.

Llama 4 Maverick is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Groq, this flagship model represents the latest capabilities and state-of-the-art per...

Meta's Llama 4 Maverick model with 17 billion parameters and 128 experts, optimized for instruction following. Hosted on Groq for ultra-fast inference speeds.

Llama 4 Scout is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Groq, this model provides solid performance and is suitable for most use cases.

Meta's Llama 4 Scout model with 17 billion parameters and 16 experts. A more efficient MoE variant designed for fast, lightweight inference on Groq infrastructure.

Llama Guard 4 12B is a content moderation model for safety and policy compliance checking. Developed by Groq, this model is optimized for its specific use case category.

Meta's content moderation and safety model with 12 billion parameters. Designed for detecting harmful, toxic, or unsafe content in AI outputs. Hosted on Groq for ultra-fast moderation.

A lightweight prompt injection detection model with 22 million parameters. Designed to identify and prevent prompt injection attacks in real-time with minimal latency.

A larger prompt injection detection model with 86 million parameters. Offers improved accuracy over the 22M variant while maintaining fast inference speeds.

Groq: Mixtral 8x7B (Extended) is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

Groq: Mixtral 8x7B 32K is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

A specialized Arabic language model from Canopy Labs focused on Saudi Arabian dialect and culture. Optimized for Saudi Arabic text generation and understanding.

Canopy Labs' Orpheus V1 model for English language tasks. A lightweight model optimized for fast inference on Groq infrastructure.

Groq: PaLM 2 Chat Bison 32K is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

Groq: PaLM 2 CodeChat Bison is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

PlayAI's text-to-speech model hosted on Groq for ultra-fast audio generation. Provides high-quality voice synthesis with low latency.

PlayAI's Arabic-specialized text-to-speech model hosted on Groq. Optimized for high-quality Arabic voice synthesis.

Groq: Qwen 2 72B 4-bit is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

Groq: Qwen 2 7B 4-bit is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

Qwen3 32B is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Groq, this model provides solid performance and is suitable for most use cases.

Alibaba's Qwen3 32 billion parameter model hosted on Groq infrastructure. Offers strong multilingual capabilities with fast inference. The model is optimized for code generation and programming tasks....

OpenAI's Whisper Large V3 speech-to-text model hosted on Groq for ultra-fast transcription. Supports multiple languages and audio formats.

Groq: Whisper Large V3 Turbo is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

Whisper V3 Large is a audio processing model for speech synthesis and audio understanding. Developed by Groq, this model is optimized for its specific use case category.

Groq: Yi 34B Chat 3 32K is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. This is a merged model (#merge) that combines multiple fine-tuning approaches to achieve ...

Inflection 3 Pi powers Inflection's Pi chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like customer support and r...

A specialized merged model designed for enhanced fictional storytelling with supplementary medical knowledge. The model combines three base models to balance creative narrative generation with anatomi...

Meta Llama 2 13B Chat is a 13 billion parameter language model fine-tuned specifically for chat completions and conversational tasks. This is Meta's open-source contribution designed for dialogue-base...

Llama 3.1 405B Instruct is Meta's largest and most capable open-source language model, representing their flagship offering in the Llama 3.1 series. This 405-billion parameter model features a 128K to...

Llama 3.1 8B Instruct is part of Meta's latest class of language models, offering a balance between efficiency and capability. This 8-billion parameter instruction-tuned variant emphasizes speed and e...

Llama 3.3 70B Instruct is a pretrained and instruction-tuned generative model optimized for multilingual dialogue use cases. It outperforms many available open source and closed chat models on common ...

Meta's latest language model offering comes in various sizes. This 70B parameter instruct-tuned variant targets high-quality dialogue applications. The model has demonstrated strong performance compar...

Llama 3.2 1B is a 1-billion-parameter language model optimized for efficiently performing natural language tasks such as summarization, dialogue, and multilingual text analysis. With its smaller size,...

Llama 3.2 3B is a 3-billion-parameter multilingual large language model optimized for advanced natural language processing tasks including dialogue generation, complex reasoning, and text summarizatio...

A 90-billion-parameter multimodal model excelling at visual reasoning and language tasks. The model handles image captioning, visual question answering, and advanced image-text comprehension through p...

A high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total parameters). The mo...

Phi-3 128K Medium is a powerful 14-billion parameter model designed for advanced language understanding, reasoning, and instruction following. The model excels in common sense reasoning, mathematics, ...

Phi-4 targets "complex reasoning tasks and operates efficiently with limited memory or when quick responses are needed." The 14-billion parameter model trained on synthetic datasets, curated websites,...

Microsoft's most advanced Wizard model, described as demonstrating "highly competitive performance compared to leading proprietary models" and consistently outperforming existing open-source alternati...

A lightweight, state-of-the-art language model with 10 billion activated parameters, optimized for coding, agentic workflows, and application development. The model delivers cleaner, more concise outp...

A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. Mistral 7B Instruct has multiple version variants, and this endpoint is intended to be the l...

Codestral is Mistral AI's cutting-edge language model explicitly designed for code generation tasks. It is Mistral's inaugural code-specific generative model, representing an open-weight generative AI...

Codestral is a code generation and understanding model for programming tasks. Developed by Mistral AI, this model is optimized for its specific use case category.

Codestral Embed is a text embedding model for semantic search and vector-based tasks. Developed by Mistral AI, this model is optimized for its specific use case category.

Devstral 2 is a code generation and understanding model for programming tasks. Developed by Mistral AI, this model is optimized for its specific use case category.

Devstral Small 2 is a code generation and understanding model for programming tasks. Developed by Mistral AI, this model is optimized for its specific use case category.

Magistral Medium is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Mistral AI, this model is optimized for its specific use case category.

Magistral Small is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Mistral AI, this model is optimized for its specific use case category.

Ministral 14B is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Mistral AI, this model is optimized for its specific use case category.

Ministral 3B is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Mistral AI, this model is optimized for its specific use case category.

Ministral 8B is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Mistral AI, this model is optimized for its specific use case category.

Mistral Embed is a text embedding model for semantic search and vector-based tasks. Developed by Mistral AI, this model is optimized for its specific use case category.

Mistral Large 3 is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Mistral AI, this flagship model represents the latest capabilities and state-of-the-ar...

Mistral Medium 3 is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Mistral AI, this premium model offers excellent quality and balanced performance acro...

Mistral Moderation is a content moderation model for safety and policy compliance checking. Developed by Mistral AI, this model is optimized for its specific use case category.

Mistral OCR is a AI model for general-purpose tasks. Developed by Mistral AI, this model is optimized for its specific use case category.

Mistral Small is a 22-billion parameter model serving as a convenient mid-point between smaller and larger Mistral options. It emphasizes reasoning capabilities, code generation, and multilingual supp...

Mistral Small 3.2 is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Mistral AI, this model provides solid performance and is suitable for most use cases...

Mistral Small Creative is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by Mistral AI, this model is optimized for its specific use case category.

Voxtral Mini is a audio processing model for speech synthesis and audio understanding. Developed by Mistral AI, this model is optimized for its specific use case category.

Voxtral Small is a audio processing model for speech synthesis and audio understanding. Developed by Mistral AI, this model is optimized for its specific use case category.

Mistral Large is Mistral AI's flagship offering. The model excels at reasoning, code generation, JSON handling, and chat applications. It is a proprietary model with support for dozens of languages in...

A closed-source, medium-sized model from Mistral AI that excels at reasoning, code, JSON, chat, and more. This model performs comparably to other companies' flagship models and represents Mistral's mi...

A 12-billion parameter model featuring a 128k token context window, developed by Mistral in partnership with NVIDIA. The model supports multiple languages including English, French, German, Spanish, I...

Mistral Small Creative is an experimental small model designed for:

**Model ID:** `mistralai/devstral-2512`

Devstral 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.

Mixtral 8x7B Instruct is a pretrained generative Sparse Mixture of Experts model with 8 experts totaling 47 billion parameters. It has been fine-tuned by Mistral AI specifically for chat and instructi...

The first multi-modal, text+image-to-text model from Mistral AI. Its weights were launched via torrent, making it openly available for research and commercial use.

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coheren...

This represents the primary 7B variant in the Hermes lineup, utilizing Direct Preference Optimization refinement. It's derived from Teknium/OpenHermes-2.5-Mistral-7B and demonstrates "improvement acro...

Nous Hermes 2 Mixtral 8x7B DPO is the flagship Nous Research model trained over the Mixtral 8x7B MoE LLM. The model was trained on over 1,000,000 entries of primarily GPT-4 generated data, as well as ...

Nous: Hermes 2 Vision 7B is an alpha-stage vision-language model that extends the capabilities of OpenHermes-2.5 by incorporating visual perception abilities. The model was developed using a specializ...

Hermes 3 is a generalist language model with significant improvements over its predecessor Hermes 2. It is a full-parameter finetune of Llama-3.1 405B, making it one of the largest openly available in...

Nous Hermes 3.1 is an advanced iterative refinement of the Hermes 3 model family, built on top of Llama-3.1 405B. This model represents the cutting edge of open-source instruction-tuned models with en...

This model combines the Llama 3.1 70B architecture with Reinforcement Learning from Human Feedback (RLHF) to excel in automatic alignment benchmarks. It is designed for generating precise and useful r...

Embeddinggemma:300m optimized for generating high-quality embeddings. This model supports multimodal capabilities including vision and image understanding.

Functiongemma:270m is a capable language model from Ollama for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image understanding....

Gemma3:1b is a capable language model from Ollama for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image understanding.

Llama 3.1 8B Instruct is Meta's state-of-the-art instruction-tuned language model with 8 billion parameters. It's a compact yet powerful model designed for general-purpose conversational AI, reasoning...

Mistral 7B Instruct is Mistral AI's powerful 7-billion parameter instruction-tuned language model, renowned for exceptional efficiency and speed. Despite having only 7B parameters, it achieves perform...

Qwen2.5 7B Instruct is Alibaba's latest-generation instruction-tuned language model with 7.6 billion parameters, representing a significant upgrade to the Qwen family. Built on 18 trillion tokens of d...

**Source**: OpenRouter (https://langmart.ai/model-docs)

**Last Updated:** December 24, 2025

OpenAI o1-preview is a reasoning-focused model designed to "spend more time thinking before responding." It employs chain-of-thought reasoning with self-fact-checking capabilities, making it particula...

Lightweight text completion model. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: chatgpt-4o-latest This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: chatgpt-image-latest This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: codex-mini-latest This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks. The...

Computer Use Preview is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by OpenAI, this model is optimized for its specific use case category.

DALL-E 2 is a image generation model for creating visual content from descriptions. Developed by OpenAI, this model is optimized for its specific use case category.

DALL-E 3 is a image generation model for creating visual content from descriptions. Developed by OpenAI, this model is optimized for its specific use case category.

Text completion model for legacy applications. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-sol...

OpenAI model: gpt-4o-audio-preview-2024-12-17 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solv...

OpenAI model: gpt-4o-audio-preview-2025-06-03 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solv...

OpenAI model: gpt-4o-mini-audio-preview This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving ta...

OpenAI model: gpt-4o-mini-audio-preview-2024-12-17 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem...

OpenAI model: gpt-4o-mini-realtime-preview This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving...

OpenAI model: gpt-4o-mini-realtime-preview-2024-12-17 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex prob...

OpenAI model: gpt-4o-mini-search-preview This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving t...

OpenAI model: gpt-4o-mini-search-preview-2025-03-11 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex proble...

OpenAI model: gpt-4o-mini-transcribe This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks...

OpenAI model: gpt-4o-mini-transcribe-2025-03-20 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-so...

OpenAI model: gpt-4o-mini-transcribe-2025-12-15 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-so...

OpenAI model: gpt-4o-realtime-preview This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving task...

OpenAI model: gpt-4o-realtime-preview-2024-10-01 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-s...

OpenAI model: gpt-4o-realtime-preview-2024-12-17 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-s...

OpenAI model: gpt-4o-realtime-preview-2025-06-03 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-s...

OpenAI model: gpt-4o-search-preview This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks....

OpenAI model: gpt-4o-search-preview-2025-03-11 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-sol...

OpenAI model: gpt-4o-transcribe This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-4o-transcribe-diarize This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving ta...

OpenAI model: gpt-5 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5-2025-08-07 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5-chat-latest This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5-codex This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks. The model...

OpenAI model: gpt-5-mini This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5-mini-2025-08-07 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks....

OpenAI model: gpt-5-nano This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5-nano-2025-08-07 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks....

OpenAI model: gpt-5-pro This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5-pro-2025-10-06 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5-search-api This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5-search-api-2025-10-14 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving ...

OpenAI model: gpt-5.1 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5.1-2025-11-13 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5.1-chat-latest This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5.1-codex This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks. The mod...

OpenAI model: gpt-5.1-codex-max This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks. The...

OpenAI model: gpt-5.1-codex-mini This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks. Th...

OpenAI model: gpt-5.2 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5.2-2025-12-11 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5.2-chat-latest This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5.2-pro This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-5.2-pro-2025-12-11 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks...

OpenAI model: gpt-audio This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-audio-2025-08-28 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-audio-mini This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-audio-mini-2025-10-06 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving ta...

OpenAI model: gpt-audio-mini-2025-12-15 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving ta...

OpenAI's first-generation image generation model integrated with GPT capabilities. Enables text-to-image generation with natural language understanding. This model supports multimodal capabilities inc...

A lightweight version of OpenAI's GPT Image 1, optimized for faster generation and lower cost while maintaining good quality. This model supports multimodal capabilities including vision and image und...

OpenAI's enhanced image generation model with improved quality, better prompt understanding, and more detailed outputs compared to GPT Image 1.

OpenAI model: gpt-realtime This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-realtime-2025-08-28 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving task...

OpenAI model: gpt-realtime-mini This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: gpt-realtime-mini-2025-10-06 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving...

OpenAI model: gpt-realtime-mini-2025-12-15 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving...

Fast and affordable model suitable for most applications. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex ...

January 2024 update with improved performance. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-sol...

November 2023 version with extended context. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solvi...

Extended context window version of GPT-3.5 Turbo. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-...

Instruction-following variant for supervised fine-tuning. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex ...

September 2023 release of instruct variant for supervised fine-tuning and completion tasks. This model supports multimodal capabilities including vision and image understanding. It features advanced r...

OpenAI's flagship model with advanced reasoning and problem-solving capabilities. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning c...

Specific version of GPT-4 from June 2023 with enhanced instruction following. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capab...

Faster variant of GPT-4 with extended context window and lower cost. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities f...

April 2024 version of GPT-4 Turbo with updated knowledge cutoff. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for c...

Preview of GPT-4 Turbo with early access to new features. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex ...

Latest GPT-4 Turbo variant with expanded context window and improved capabilities. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning ...

GPT-4 Turbo with 128K context window for processing large documents. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities f...

Enhanced version of GPT-4 with improved reasoning and multimodal capabilities. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capa...

Latest GPT-4.1 variant with current knowledge cutoff. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex prob...

Compact version of GPT-4.1 for cost-efficient applications. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for comple...

Latest mini variant with efficient performance. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-so...

Ultra-lightweight variant for cost-sensitive applications. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex...

Latest nano variant for ultra-fast inference with efficient performance. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabiliti...

August 2024 update with improved performance. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solv...

Initial release of GPT-4o optimized model. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving...

Latest GPT-4o with updated knowledge and improved capabilities. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for co...

Preview of GPT-4o with audio processing capabilities. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex prob...

October release of audio-enabled GPT-4o preview. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-s...

Compact multimodal model for efficient applications. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex probl...

Initial release of the mini multimodal variant. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-so...

GPT-4o Mini TTS is a audio processing model for speech synthesis and audio understanding. Developed by OpenAI, this model is optimized for its specific use case category.

GPT-5.2 Chat is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. The model uses adaptive reasoning to selectively engage deep...

OpenAI model: o1 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: o1-2024-12-17 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: o1-mini This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: o1-mini-2024-09-12 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: o1-pro This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: o1-pro-2025-03-19 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: o3 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: o3-2025-04-16 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

O3 Deep Research is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by OpenAI, this model is optimized for its specific use case category.

OpenAI model: o3-mini This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: o3-mini-2025-01-31 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

O3 Pro is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by OpenAI, this model is optimized for its specific use case category.

OpenAI model: o4-mini This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: o4-mini-2025-04-16 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: o4-mini-deep-research This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks....

OpenAI model: o4-mini-deep-research-2025-06-26 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-sol...

Omni Moderation is a content moderation model for safety and policy compliance checking. Developed by OpenAI, this model is optimized for its specific use case category.

OpenAI model: omni-moderation-2024-09-26 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving t...

OpenAI model: omni-moderation-latest This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks...

OpenAI model: sora-2 This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

OpenAI model: sora-2-pro This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving tasks.

Large embedding model for advanced semantic tasks. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem...

Efficient text embedding model with high quality representations. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for ...

Legacy embedding model still widely used. This model supports multimodal capabilities including vision and image understanding. It features advanced reasoning capabilities for complex problem-solving ...

TTS is a audio processing model for speech synthesis and audio understanding. Developed by OpenAI, this model is optimized for its specific use case category.

TTS HD is a audio processing model for speech synthesis and audio understanding. Developed by OpenAI, this model is optimized for its specific use case category.

Whisper is a audio processing model for speech synthesis and audio understanding. Developed by OpenAI, this model is optimized for its specific use case category.

Fake Gpt 4 Vision with vision capabilities for processing images and visual content. This model supports multimodal capabilities including vision and image understanding. It features advanced reasonin...

OpenChat is a library of open-source language models fine-tuned with C-RLFT, a strategy inspired by offline reinforcement learning. The model is trained on mixed-quality data without preference labels...

AI21's Jamba Large 1.7 is a state-of-the-art hybrid SSM-Transformer model with a 256K context window. Designed for enterprise applications requiring long-context understanding.

AI21's Jamba Mini 1.7 is a compact hybrid SSM-Transformer model with a 256K context window. Optimized for cost-effective long-context applications.

Aion Labs/aion 1.0 is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image understandin...

Aion Labs/aion 1.0 Mini is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image underst...

Aion Labs/aion Rp Llama 3.1 8b is a capable language model from LangMart for general-purpose text generation and analysis tasks.

A finetuned 7 billion parameters Code LLaMA - Instruct model to generate Solidity smart contract using 4-bit QLoRA finetuning provided by PEFT library.

Free tier version of Alibaba/tongyi Deepresearch 30b A3b:free. This model supports multimodal capabilities including vision and image understanding.

OLMo-2 32B Instruct is a supervised instruction-finetuned variant of the OLMo-2 32B March 2025 base model. It excels in complex reasoning and instruction-following tasks across diverse benchmarks such...

Olmo 3 7B Instruct is a supervised instruction-fine-tuned variant of the Olmo 3 7B base model, optimized for instruction-following, question-answering, and natural conversational dialogue. By leveragi...

Olmo 3 7B Think is a research-oriented language model in the Olmo family designed for advanced reasoning and instruction-driven tasks. It excels at multi-step problem solving, logical inference, and m...

Free tier version of Allenai/olmo 3 32b Think:free. This model supports multimodal capabilities including vision and image understanding.

Free tier version of Allenai/olmo 3.1 32b Think:free. This model supports multimodal capabilities including vision and image understanding.

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text.

Amazon 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 can handle real-time cus...

Amazon 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 of 128K tokens and optimized for spe...

Amazon 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.

Amazon 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 2024, it achieves state-of-the-a...

Anthropic's Claude 3.5 Sonnet accessed via LangMart. A balanced model combining strong intelligence with fast response times, ideal for most use cases.

Anthropic's Claude 3.7 Sonnet accessed via LangMart. An enhanced version with improved reasoning and capabilities over Claude 3.5 Sonnet. This model supports multimodal capabilities including vision a...

Anthropic's fastest and most efficient Claude model accessed via LangMart. Designed for high-volume, low-latency applications requiring quick responses. This model supports multimodal capabilities inc...

Claude 3 Haiku is Anthropic's fastest and most compact model for

Claude 3 Opus is Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding.

Claude 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 software...

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the...

Anthropic/claude 3.5 Haiku is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image unde...

Anthropic/claude 3.5 Haiku 20241022 is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and i...

Anthropic/claude 3.7 Sonnet:thinking with extended thinking capabilities. This model supports multimodal capabilities including vision and image understanding.

Anthropic/claude Opus 4.1 is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image under...

Anthropic/claude Opus 4.5 is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image under...

Anthropic/claude Sonnet 4.5 is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image und...

Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context win...

Maestro Reasoning is Arcee's flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32 B tuned with DPO and chain‑of‑thought RL for step‑by‑step logic. Compared to the earlier 7 B preview, t...

Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight image‑text grounding tasks. It offers a 32 k‑token context window, enabling rich ...

Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with ro...

Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k cont...

Free tier version of Arcee Ai/trinity Mini:free. This model supports multimodal capabilities including vision and image understanding.

QwQ-32B-ArliAI-RpR-v1 is a 32B parameter model fine-tuned from Qwen/QwQ-32B using a curated creative writing and roleplay dataset originally developed for the RPMax series. It is designed to maintain ...

Your prompt will be processed by a meta-model and routed to one of dozens of models (see below), optimizing for the best possible output.

Baidu/ernie 4.5 21b A3b is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image underst...

Baidu/ernie 4.5 21b A3b Thinking with extended thinking capabilities. This model supports multimodal capabilities including vision and image understanding.

Baidu/ernie 4.5 300b A47b is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image under...

Baidu/ernie 4.5 Vl 28b A3b is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image unde...

Baidu/ernie 4.5 Vl 424b A47b is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image un...

Transform your natural language requests into structured LangMart API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. E...

Bytedance Seed/seed 1.6 is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image underst...

Bytedance Seed/seed 1.6 Flash with optimized speed for rapid response generation. This model supports multimodal capabilities including vision and image understanding.

Bytedance/ui Tars 1.5 7b is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image unders...

An instruction-tuned, hybrid-reasoning Mixture-of-Experts model built on Llama-4-Scout-17B-16E. Cogito v2 can answer directly or engage an extended “thinking” phase, with alignment guided by Iterated ...

Free tier version of Cognitivecomputations/dolphin Mistral 24b Venice Edition:free. This model supports multimodal capabilities including vision and image understanding.

Command 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.

command-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 ...

command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while ...

Command 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 and multiple steps....

Cogito v2 405B is a dense hybrid reasoning model that combines direct answering capabilities with advanced self-reflection. It represents a significant step toward frontier intelligence with dense arc...

Cogito v2 70B is a dense hybrid reasoning model that combines direct answering capabilities with advanced self-reflection. Built with iterative policy improvement, it delivers strong performance acros...

Deepcogito/cogito V2.1 671b is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image und...

DeepSeek Prover V2 is a 671B parameter model, speculated to be geared towards logic and mathematics. Likely an upgrade from [DeepSeek-Prover-V1.5](https://huggingface.co/deepseek-ai/DeepSeek-Prover-V1...

DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and G...

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported ev...

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.

DeepSeek 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.

May 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 siz...

DeepSeek 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 mo...

DeepSeek R1 Distill Qwen 14B is a distilled large language model based on [Qwen 2.5 14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B), using outputs from [DeepSeek R1](/deepseek/de...

DeepSeek 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 outperfor...

Deepseek/deepseek Chat V3.1 is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image und...

Free tier version of Deepseek/deepseek R1 0528:free. This model supports multimodal capabilities including vision and image understanding.

Deepseek/deepseek V3.1 Terminus is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image...

Deepseek/deepseek V3.1 Terminus:exacto is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision an...

Deepseek/deepseek V3.2 is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image understa...

Deepseek/deepseek V3.2 Exp is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image unde...

Deepseek/deepseek V3.2 Speciale is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image...

EleutherAI: Llemma 7b is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by LangMart, this model is optimized for its specific use case category.

Rnj-1 is an 8B-parameter, dense, open-weight model family developed by Essential AI and trained from scratch with a focus on programming, math, and scientific reasoning. The model demonstrates strong ...

A large LLM created by combining two fine-tuned Llama 70B models into one 120B model. Combines Xwin and Euryale.

Google: Gemini 2.0 Flash is a image generation model for creating visual content from descriptions. Developed by LangMart, this model is optimized for its specific use case category.

Google: Gemini 2.5 Flash is a image generation model for creating visual content from descriptions. Developed by LangMart, this model is optimized for its specific use case category.

Google: Gemini 2.5 Flash Image (Nano Banana) is a image generation model for creating visual content from descriptions. Developed by LangMart, this model is optimized for its specific use case categor...

Google: Gemini 2.5 Flash Image Preview (Nano Banana) is a image generation model for creating visual content from descriptions. Developed by LangMart, this model is optimized for its specific use case...

Google: Gemini 2.5 Flash Lite is a image generation model for creating visual content from descriptions. Developed by LangMart, this model is optimized for its specific use case category.

Google: Gemini 2.5 Flash Lite Preview 09-2025 is a image generation model for creating visual content from descriptions. Developed by LangMart, this model is optimized for its specific use case catego...

Google: Gemini 2.5 Flash Preview 09-2025 is a image generation model for creating visual content from descriptions. Developed by LangMart, this model is optimized for its specific use case category.

Google: Gemini 2.5 Pro is a image generation model for creating visual content from descriptions. Developed by LangMart, this model is optimized for its specific use case category.

Google: Gemini 3 Flash Preview is a image generation model for creating visual content from descriptions. Developed by LangMart, this model is optimized for its specific use case category.

Google: Gemini 3 Pro Preview is a image generation model for creating visual content from descriptions. Developed by LangMart, this model is optimized for its specific use case category.

Google: Gemma 2 27B is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by LangMart, this model is optimized for its specific use case category.

Google: Gemma 2 9B is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by LangMart, this model is optimized for its specific use case category.

Google: Gemma 3 12B is a image generation model for creating visual content from descriptions. Developed by LangMart, this model is optimized for its specific use case category.

Google: Gemma 3 27B is a image generation model for creating visual content from descriptions. Developed by LangMart, this model is optimized for its specific use case category.

Google: Gemma 3 4B is a image generation model for creating visual content from descriptions. Developed by LangMart, this model is optimized for its specific use case category.

Google: Gemma 3n 4B is a conversational AI model designed for multi-turn dialogue and interactive tasks. Developed by LangMart, this model is optimized for its specific use case category.

Google: Nano Banana Pro (Gemini 3 Pro Image Preview) is a image generation model for creating visual content from descriptions. Developed by LangMart, this model is optimized for its specific use case...

Google/gemini 2.0 Flash Exp:free with optimized speed for rapid response generation. This model supports multimodal capabilities including vision and image understanding.

Lightweight variant of Google/gemini 2.0 Flash Lite 001 optimized for reduced latency and cost. This model supports multimodal capabilities including vision and image understanding.

Preview version of Google/gemini 2.5 Pro Preview providing early access to experimental features. This model supports multimodal capabilities including vision and image understanding.

Preview version of Google/gemini 2.5 Pro Preview 05 06 providing early access to experimental features. This model supports multimodal capabilities including vision and image understanding.

Free tier version of Google/gemma 3 12b It:free. This model supports multimodal capabilities including vision and image understanding.

Free tier version of Google/gemma 3 27b It:free. This model supports multimodal capabilities including vision and image understanding.

Free tier version of Google/gemma 3 4b It:free. This model supports multimodal capabilities including vision and image understanding.

Free tier version of Google/gemma 3n E2b It:free. This model supports multimodal capabilities including vision and image understanding.

Free tier version of Google/gemma 3n E4b It:free. This model supports multimodal capabilities including vision and image understanding.

Ibm Granite/granite 4.0 H Micro is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image...

Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Clau...

Mercury Coder is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 Haik...

Inflection 3 Pi powers Inflection's [Pi](https://pi.ai) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like custo...

Inflection 3 Productivity is optimized for following instructions. It is better for tasks requiring JSON output or precise adherence to provided guidelines. It has access to recent news.

Free tier version of Kwaipilot/kat Coder Pro:free. This model supports multimodal capabilities including vision and image understanding. The model is optimized for code generation and programming task...

Liquid/lfm 2.2 6b is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image understanding...

Model created via inbox interface

Llama 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 classificati...

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://langmart.ai/model-docs.5-sonnet) and Opus(https://langmart.ai/model-docs).

An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.

LongCat-Flash-Chat is a large-scale Mixture-of-Experts (MoE) model with 560B total parameters, of which 18.6B–31.3B (≈27B on average) are dynamically activated per input. It introduces a shortcut-conn...

Meta Llama/llama 3.1 405b is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and image under...

Meta Llama/llama 3.1 405b Instruct is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and im...

Free tier version of Meta Llama/llama 3.1 405b Instruct:free. This model supports multimodal capabilities including vision and image understanding.

Meta Llama/llama 3.1 70b Instruct is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and ima...

Meta Llama/llama 3.1 8b Instruct is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and imag...

Meta Llama/llama 3.2 11b Vision Instruct with vision capabilities for processing images and visual content. This model supports multimodal capabilities including vision and image understanding. It fea...

Meta Llama/llama 3.2 1b Instruct is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and imag...

Meta Llama/llama 3.2 3b Instruct is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and imag...

Free tier version of Meta Llama/llama 3.2 3b Instruct:free. This model supports multimodal capabilities including vision and image understanding.

Meta Llama/llama 3.2 90b Vision Instruct with vision capabilities for processing images and visual content. This model supports multimodal capabilities including vision and image understanding. It fea...

Meta Llama/llama 3.3 70b Instruct is a capable language model from LangMart for general-purpose text generation and analysis tasks. This model supports multimodal capabilities including vision and ima...

Free tier version of Meta Llama/llama 3.3 70b Instruct:free. This model supports multimodal capabilities including vision and image understanding.

Meta'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.

Meta'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.

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forw...

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input (text and ...

Llama 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 inputs ...

This safeguard model has 8B parameters and is based on the Llama 3 family. Just like is predecessor, [LlamaGuard 1](https://huggingface.co/meta-llama/LlamaGuard-7b), it can do both prompt and response...

[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed.

Phi-4 Multimodal Instruct is a versatile 5.6B parameter foundation model that combines advanced reasoning and instruction-following capabilities across both text and visual inputs, providing accurate ...

Phi-4-reasoning-plus is an enhanced 14B parameter model from Microsoft, fine-tuned from Phi-4 with additional reinforcement learning to boost accuracy on math, science, and code reasoning tasks. It us...