Guide

Qwen's Enhanced Large Visual Language Model. Significantly upgraded for detailed recognition capabilities and text recognition abilities, supporting ultra-high pixel resolutions up to millions of pixels and extreme aspect ratios for...

Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models and techniques such as Tree...

Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It is a modified variant...

Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...

Qwen VL Max is a visual understanding model with 7500 tokens context length. It excels in delivering optimal performance for a broader spectrum of complex tasks.

Qwen-Turbo, based on Qwen2.5, is a 1M context model that provides fast speed and low cost, suitable for simple tasks.

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.

Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

Qwen-Max, based on Qwen2.5, provides the best inference performance among [Qwen models](/qwen), especially for complex multi-step tasks. It's a large-scale MoE model that has been pretrained on over 20 trillion...

Sonar search model for current answers, retrieval, and citation-backed chat

OpenAI 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...

OpenAI 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...

Mistral 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...

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 outperforms OpenAI's o1-mini across various benchmarks, achieving new...

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/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models. Other benchmark results include: - AIME 2024 pass@1: 69.7 - MATH-500 pass@1: 93.9 - CodeForces Rating: 1481 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...

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

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 model combines advanced distillation techniques to achieve high performance across...

ALLaM-2-7b instruction tuned model by SDAIA

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....

DeepSeek R1 Distill Llama 70B from Groq - text input, 131,072 token context

DeepSeek R1 0528 TEE from Chutes - text input, 163,840 token context

DeepSeek R1 from Synthetic - text input, 128,000 token context

DeepSeek V3 from Synthetic - text input, 128,000 token context

Classic open reasoning model for transparent math, coding, and deliberate problem solving

Classic open reasoning model for transparent math, coding, and deliberate problem solving

Classic open reasoning model for transparent math, coding, and deliberate problem solving

Legacy model retained for compatibility with older integrations

Classic open reasoning model for transparent math, coding, and deliberate problem solving

Qwen reasoning model for deliberate problem solving, math, and coding

Qwen reasoning model for deliberate problem solving, math, and coding

Qwen omni model for text, vision, audio, and multimodal agent tasks

MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...

Code-specialist GPT for repository edits, reviews, and long-running software agents

Claude Sonnet 4.5 from Venice AI - text, image input, 198,000 token context

Balanced Claude model for coding, analysis, agent workflows, and cost control

[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. At 14 billion...

This is [Sao10K](/sao10k)'s experiment over [Euryale v2.2](/sao10k/l3.1-euryale-70b).

Flagship model for demanding analysis, coding, and production agent workflows

InternVL3 78B TEE from Chutes - text, image input, 32,768 token context

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Translation model for multilingual conversion, localization, and cross-language workflows

Translation model for multilingual conversion, localization, and cross-language workflows

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

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 evaluations...

Open DeepSeek MoE chat model for coding, math, and general reasoning

DeepSeek chat model for instruction following, coding, and analysis

Legacy model retained for compatibility with older integrations

Smaller o-series reasoner for economical coding, math, and planning tasks

Smaller o-series reasoner for economical coding, math, and planning tasks