Guide

Multimodal reasoning model for visual analysis, planning, and tool use

Multimodal reasoning model for visual analysis, planning, and tool use

Multimodal reasoning model for visual analysis, planning, and tool use

Multimodal reasoning model for visual analysis, planning, and tool use

DeepSeek chat model for instruction following, coding, and analysis

Multimodal reasoning model for visual analysis, planning, and tool use

Flagship Mistral model for advanced reasoning, coding, and multilingual work

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Flagship Mistral model for advanced reasoning, coding, and multilingual work

Mistral 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 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.

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 robust function...

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 robust function...

DeepSeek-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 learning...

DeepSeek-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 chat model for instruction following, coding, and analysis

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

DeepSeek V3.2 from Fireworks AI - text input, 160,000 token context

Grok 4.1 Fast from Venice AI - text, image input, 1,000,000 token context

Grok Code Fast 1 from Venice AI - text input, 256,000 token context

MiniMax M2.1 from Venice AI - text input, 198,000 token context

DeepSeek chat model for instruction following, coding, and analysis

DeepSeek V3.2 from Synthetic - text input, 162,816 token context

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use

DeepSeek chat model for instruction following, coding, and analysis

DeepSeek chat model for instruction following, coding, and analysis

DeepSeek chat model for instruction following, coding, and analysis

DeepSeek chat model for instruction following, coding, and analysis

INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offers state-of-the-art performance for its size across math,...

TNG-R1T-Chimera is an experimental LLM with a faible for creative storytelling and character interaction. It is a derivate of the original TNG/DeepSeek-R1T-Chimera released in April 2025 and is available exclusively via Chutes and OpenRouter. Characteristics and improvements include: We think that it has a creative and pleasant personality. It has a preliminary EQ-Bench3 value of about 1305. It is quite a bit more intelligent than the original, albeit a slightly slower. It is much more think-token consistent, i.e. reasoning and answer blocks are properly delineated. Tool calling is much improved. TNG Tech, the model authors, ask that users follow the careful guidelines that Microsoft has created for their "MAI-DS-R1" DeepSeek-based model. These guidelines are available on Hugging Face (https://huggingface.co/microsoft/MAI-DS-R1).

TNG-R1T-Chimera is an experimental LLM with a faible for creative storytelling and character interaction. It is a derivate of the original TNG/DeepSeek-R1T-Chimera released in April 2025 and is available exclusively via Chutes and OpenRouter. Characteristics and improvements include: We think that it has a creative and pleasant personality. It has a preliminary EQ-Bench3 value of about 1305. It is quite a bit more intelligent than the original, albeit a slightly slower. It is much more think-token consistent, i.e. reasoning and answer blocks are properly delineated. Tool calling is much improved. TNG Tech, the model authors, ask that users follow the careful guidelines that Microsoft has created for their "MAI-DS-R1" DeepSeek-based model. These guidelines are available on Hugging Face (https://huggingface.co/microsoft/MAI-DS-R1).

Multimodal reasoning model for visual analysis, planning, and tool use

Image model for prompt-driven generation, editing, and visual design workflows

Image model for prompt-driven generation, editing, and visual design workflows

Image model for prompt-driven generation, editing, and visual design workflows

Image model for prompt-driven generation, editing, and visual design workflows

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...

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 leveraging high-quality instruction data and an open training pipeline, it delivers strong performance across everyday NLP tasks while remaining accessible and easy to integrate. Developed by Ai2 under the Apache 2.0 license, the model offers a transparent, community-friendly option for instruction-driven applications.

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 maintaining coherent conversational context. Developed by Ai2 under the Apache 2.0 license, Olmo 3 7B Think supports transparent, fully open experimentation and provides a lightweight yet capable foundation for academic research and practical NLP workflows.

Nano 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...

Nano Banana Pro for higher-fidelity image generation and design-heavy edits

Grok 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 4.1 Fast from xAI - text, image input, 2,000,000 token context

Grok 4.1 Fast (Non-Reasoning) from xAI - text, image input, 2,000,000 token context

Fast Grok model for responsive chat, reasoning, and tool-assisted work