232 Models

all-minilm-l12-v2

مباشر

SBERT

EmbeddingWeights مفتوحة

We present a sentence transformation model that generates semantically similar sentences. Our model is based on the Sentence-Transformers architecture and was trained on a large dataset of sentence pairs. We evaluate the effectiveness of our model by measuring its ability to generate similar sentences that are close to the original sentence in meaning.

all-minilm-l6-v2

مباشر

SBERT

EmbeddingWeights مفتوحة

We present a sentence transformation model that achieves state-of-the-art results on various NLP tasks without requiring task-specific architectures or fine-tuning. Our approach leverages contrastive learning and utilizes a variety of datasets to learn robust sentence representations. We evaluate our model on several benchmarks and demonstrate its effectiveness in various applications such as text classification, sentiment analysis, named entity recognition, and question answering.

all-mpnet-base-v2

مباشر

SBERT

EmbeddingWeights مفتوحة

A sentence transformation model that has been trained on a wide range of datasets, including but not limited to S2ORC, WikiAnwers, PAQ, Stack Exchange, and Yahoo! Answers. Our model can be used for various NLP tasks such as clustering, sentiment analysis, and question answering.

Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows.

bge-base-en-v1.5

مباشر

BAAI

EmbeddingWeights مفتوحة

BGE embedding is a general Embedding Model. It is pre-trained using retromae and trained on large-scale pair data using contrastive learning. Note that the goal of pre-training is to reconstruct the text, and the pre-trained model cannot be used for similarity calculation directly, it needs to be fine-tuned

bge-en-icl

مباشر

BAAI

EmbeddingWeights مفتوحة

A LLM-based embedding model with in-context learning capabilities that achieves SOTA performance on BEIR and AIR-Bench. It leverages few-shot examples to enhance task performance.

bge-large-en-v1.5

مباشر

BAAI

EmbeddingWeights مفتوحة

BGE embedding is a general Embedding Model. It is pre-trained using retromae and trained on large-scale pair data using contrastive learning. Note that the goal of pre-training is to reconstruct the text, and the pre-trained model cannot be used for similarity calculation directly, it needs to be fine-tuned

bge-m3

مباشر

BAAI

EmbeddingWeights مفتوحة

BGE-M3 is a versatile text embedding model that supports multi-functionality, multi-linguality, and multi-granularity, allowing it to perform dense retrieval, multi-vector retrieval, and sparse retrieval in over 100 languages and with input sizes up to 8192 tokens. The model can be used in a retrieval pipeline with hybrid retrieval and re-ranking to achieve higher accuracy and stronger generalization capabilities. BGE-M3 has shown state-of-the-art performance on several benchmarks, including MKQA, MLDR, and NarritiveQA, and can be used as a drop-in replacement for other embedding models like DPR and BGE-v1.5.

bge-m3-multi

مباشر

BAAI

EmbeddingWeights مفتوحة

BGE-M3 is a multilingual text embedding model developed by BAAI, distinguished by its Multi-Linguality (supporting 100+ languages), Multi-Functionality (unified dense, multi-vector, and sparse retrieval), and Multi-Granularity (handling inputs from short queries to 8192-token documents). It achieves state-of-the-art retrieval performance across diverse benchmarks while maintaining a single model for multiple retrieval modes.

bge-m3-multi-8k

مباشر

BAAI

EmbeddingWeights مفتوحة

BGE-M3 is a multilingual text embedding model developed by BAAI, distinguished by its Multi-Linguality (supporting 100+ languages), Multi-Functionality (unified dense, multi-vector, and sparse retrieval), and Multi-Granularity (handling inputs from short queries to long documents). It achieves state-of-the-art retrieval performance across diverse benchmarks while maintaining a single model for multiple retrieval modes. This endpoint serves the model's full 8192-token context.

bria-3.2

مباشر

Bria

imageمغلق المصدر

Bria 3.2 is the next-generation commercial-ready text-to-image model. With just 4 billion parameters, it provides exceptional aesthetics and text rendering, evaluated to be on par to leading open-source models, and outperforming other licensed models.

bria-3.2-vector

مباشر

Bria

imageمغلق المصدر

Bria 3.2 is the next-generation commercial-ready text-to-image model. With just 4 billion parameters, it provides exceptional aesthetics and text rendering, evaluated to be on par to leading open-source models, and outperforming other licensed models.

Claude Fable 5.1

مباشر

Anthropic

محادثةمغلق المصدر

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual

Claude Haiku 5.5

مباشر

Anthropic

محادثةمغلق المصدر

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.

Claude Opus 4.5

مباشر

Anthropic

محادثةمغلق المصدر

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use.

Claude Opus 4.6

مباشر

Anthropic

محادثةمغلق المصدر

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.

Claude Opus 5

مباشر

Anthropic

محادثةمغلق المصدر

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.

Claude Opus 5.5

مباشر

Anthropic

محادثةمغلق المصدر

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.

Claude Sonnet 4.5

مباشر

Anthropic

محادثةمغلق المصدر

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows.

Claude Sonnet 5.5

مباشر

Anthropic

محادثةمغلق المصدر

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.

claude-fable-5

مباشر

Anthropic

محادثةمغلق المصدر

Claude Fable 5 is Anthropic's next generation of intelligence for the hardest knowledge work and coding problems. It works independently for longer than any prior generally available Claude model: run it in an agent harness and it can work for days at a time, planning across stages, delegating to sub-agents, and checking its own work.

claude-haiku-4.5

مباشر

Anthropic

محادثةمغلق المصدر

The next generation of Anthropic's fastest and most cost-effective model, optimal for use cases where speed and affordability matter.

claude-opus-4.7

مباشر

Anthropic

محادثةمغلق المصدر

Anthropic's most capable production model yet, advancing performance across coding, enterprise workflows, and long-running agentic tasks.

claude-opus-4.8

مباشر

Anthropic

محادثةمغلق المصدر

Claude Opus 4.8 is our most intelligent Opus model and the best generally available model for coding and agents, with deeper reasoning for enterprise workflows.

claude-sonnet-4.6

مباشر

Anthropic

محادثةمغلق المصدر

Claude Sonnet 4.6 delivers frontier intelligence at scale—built for coding, agents, and enterprise workflows.

claude-sonnet-5

مباشر

Anthropic

محادثةمغلق المصدر

Claude Sonnet 5 is Anthropic's most capable Sonnet model yet, built for coding, agents, and professional work at scale. It brings near-Opus intelligence to the model teams run at scale every day, with the same balance of capability, cost, and speed teams already rely on Sonnet for.

clip-vit-b-32

مباشر

SBERT

EmbeddingWeights مفتوحة

The CLIP model maps text and images to a shared vector space, enabling various applications such as image search, zero-shot image classification, and image clustering. The model can be used easily after installation, and its performance is demonstrated through zero-shot ImageNet validation set accuracy scores. Multilingual versions of the model are also available for 50+ languages.

clip-vit-b-32-multilingual-v1

مباشر

SBERT

EmbeddingWeights مفتوحة

This model is a multilingual version of the OpenAI CLIP-ViT-B32 model, which maps text and images to a common dense vector space. It includes a text embedding model that works for 50+ languages and an image encoder from CLIP. The model was trained using Multilingual Knowledge Distillation, where a multilingual DistilBERT model was trained as a student model to align the vector space of the original CLIP image encoder across many languages.

deepseek-r1-0528

مباشر

DeepSeek

محادثةWeights مفتوحة

The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528.

deepseek-v3

مباشر

DeepSeek

محادثةWeights مفتوحة

DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2.

deepseek-v3.1

مباشر

DeepSeek

محادثةWeights مفتوحة

DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens. Additionally, DeepSeek-V3.1 is trained using the UE8M0 FP8 scale data format to ensure compatibility with microscaling data formats.

deepseek-v3.1-terminus

مباشر

DeepSeek

محادثةWeights مفتوحة

DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.

deepseek-v3.2

مباشر

DeepSeek

محادثةWeights مفتوحة

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 that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.

deepseek-v4-flash

مباشر

DeepSeek

محادثةWeights مفتوحة

DeepSeek V4 Flash is an efficiency-focused MoE model with 284B total parameters (13B active) and a 1M-token context window. It's tuned for fast inference and high-throughput use cases while still holding up on reasoning and coding tasks.

deepseek-v4-pro

مباشر

DeepSeek

محادثةWeights مفتوحة

DeepSeek V4 Pro is an MoE model with 1.6T total parameters (49B active) and a 1M-token context window. It's built for advanced reasoning, coding, and long-running agent tasks, and performs well on knowledge, math, and software engineering benchmarks.

deepseek-v4.1-flash

مباشر

DeepSeek

محادثةWeights مفتوحة

Introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens.

DeepSeek: DeepSeek V3 0324

مباشر

DeepSeek

محادثة

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

DeepSeek: DeepSeek V3.1

مباشر

DeepSeek

محادثة

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.

DeepSeek: DeepSeek V4 Flash 0731

مباشر

DeepSeek

محادثةWeights مفتوحة

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.

DeepSeek: DeepSeek V4 Flash Vision Exp

مباشر

DeepSeek

محادثةWeights مفتوحة

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,

DeepSeek: DeepSeek V4 Pro 0813

مباشر

DeepSeek

محادثةWeights مفتوحة

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

DeepSeek: R1

مباشر

DeepSeek

محادثة

DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens.

e5-base-v2

مباشر

intfloat

EmbeddingWeights مفتوحة

Text Embeddings by Weakly-Supervised Contrastive Pre-training. Model has 24 layers and 1024 out dim.

e5-large-v2

مباشر

intfloat

EmbeddingWeights مفتوحة

Text Embeddings by Weakly-Supervised Contrastive Pre-training. Model has 24 layers and 1024 out dim.

embeddinggemma-300m

مباشر

Google

EmbeddingWeights مفتوحة

EmbeddingGemma is a 300M parameter multilingual open embedding model from Google DeepMind, designed for efficient deployment even on low-resource devices, producing high-quality text vector representations for tasks such as search, classification, clustering, and semantic similarity.

fibo

مباشر

Bria

imageمغلق المصدر

FIBO is an open-source, JSON-native text-to-image model trained on detailed structured descriptions (over 1,000+ words per image), providing fine-grained control over light, composition, and camera parameters.

fibo-1.5

مباشر

Bria

imageمغلق المصدر

FIBO 1.5 is Bria's JSON-native text-to-image model, distilled to a few sampling steps and post-trained for sharper realism and texture, with structured-prompt control over lighting, composition and camera.

flux-1-dev

مباشر

black-forest-labs

imageWeights مفتوحة

FLUX.1-dev is a state-of-the-art 12 billion parameter rectified flow transformer developed by Black Forest Labs. This model excels in text-to-image generation, providing highly accurate and detailed outputs. It is particularly well-regarded for its ability to follow complex prompts and generate anatomically accurate images, especially with challenging details like hands and faces.

flux-1-schnell

مباشر

black-forest-labs

imageWeights مفتوحة

FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. This model offers cutting-edge output quality and competitive prompt following, matching the performance of closed source alternatives. Trained using latent adversarial diffusion distillation, FLUX.1 [schnell] can generate high-quality images in only 1 to 4 steps.

flux-1.1-pro

مباشر

black-forest-labs

imageمغلق المصدر

Black Forest Labs' latest state-of-the art proprietary model sporting top of the line prompt following, visual quality, details and output diversity.

flux-2-dev

مباشر

black-forest-labs

imageWeights مفتوحة

Brand-new Flux2 Dev introduces a faster, more modular architecture for next-generation image generation pipelines. It delivers improved performance, cleaner control APIs, and a significantly more flexible development workflow for custom inference setups.

flux-2-klein-4b

مباشر

black-forest-labs

imageWeights مفتوحة

The fastest model of the Flux 2 family. Frontier visual intelligence — state-of-the-art image generation and editing from Black Forest Labs

flux-2-klein-9b

مباشر

black-forest-labs

imageWeights مفتوحة

The best quality-to-latency ratio, production apps model of the Flux 2 family. Frontier visual intelligence — state-of-the-art image generation and editing from Black Forest Labs

flux-2-max

مباشر

black-forest-labs

imageمغلق المصدر

The new top-tier image model from Black Forest Labs, significantly pushing image quality and editing consistency

flux-2-pro

مباشر

black-forest-labs

imageمغلق المصدر

Multi-reference visual intelligence with unprecedented detail, color precision, and spatial reasoning. The most advanced image generation and editing model. Generate photorealistic images with precise control.

gemini-2.5-flash

مباشر

Google

محادثةمغلق المصدر

Gemini 2.5 Flash is Google's latest thinking model, designed to tackle increasingly complex problems. It's capable of reasoning through their thoughts before responding, resulting in enhanced performance and improved accuracy. Gemini 2.5 Flash: best for balancing reasoning and speed.

gemini-2.5-pro

مباشر

Google

محادثةمغلق المصدر

Gemini 2.5 Pro is Google's the most advanced thinking model, designed to tackle increasingly complex problems. Gemini 2.5 Pro leads common benchmarks by meaningful margins and showcases strong reasoning and code capabilities. Gemini 2.5 models are thinking models, capable of reasoning through their thoughts before responding, resulting in enhanced performance and improved accuracy. The Gemini 2.5 Pro model is now available on DeepInfra.

gemini-3-pro-image

مباشر

Google

imageمغلق المصدر

Nano Banana Pro (Gemini 3 Pro Image) is designed to tackle the most challenging image generation by incorporating state-of-the-art reasoning capabilities. It is the best model for complex and multi-turn image generation and editing.

gemini-3.1-flash-lite

مباشر

Google

محادثةمغلق المصدر

Bring any idea to life with state-of-the-art reasoning to help you learn, build, and plan anything. Best for high-volume tasks that need efficiency and intelligence.

gemini-3.1-pro

مباشر

Google

محادثةمغلق المصدر

Bring any idea to life with state-of-the-art reasoning to help you learn, build, and plan anything. Best for complex tasks and bringing creative concepts to life.

gemini-3.5-flash

مباشر

Google

محادثةمغلق المصدر

Gemini 3.5 Flash delivers near-Pro intelligence at Flash-tier cost and speed: Pro-level coding proficiency, parallel agentic execution, all at a much lower price.

Gemma-2 Instruct (27B)

مباشر

Google

محادثةWeights مفتوحة

Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models.

gemma-3-12b-it

مباشر

Google

محادثةWeights مفتوحة

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3-12B is Google's latest open source model, successor to Gemma 2

gemma-3-27b-it

مباشر

Google

محادثةWeights مفتوحة

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to Gemma 2

gemma-3-4b-it

مباشر

Google

محادثةWeights مفتوحة

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3-12B is Google's latest open source model, successor to Gemma 2

gemma-4-26b-a4b-it

مباشر

Google

محادثةWeights مفتوحة

Efficient, MoE variant of Gemma 4. Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input and generating text output.

gemma-4-31b-it

مباشر

Google

محادثةWeights مفتوحة

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input and generating text output.

gemma-4-31b-it-turbo

مباشر

Google

محادثةWeights مفتوحة

Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input and generating text output.

gemma-4-31b-it-ultra

مباشر

Google

محادثةمغلق المصدر

Ultra speed version of gemma-4-31B-it

GLM 4.5V

مباشر

zai-org

محادثةWeights مفتوحة

GLM-4.5V is a vision-language foundation model for multimodal agent applications.

glm-4.6

مباشر

zai-org

محادثةWeights مفتوحة

Compared with GLM-4.5, GLM-4.6 brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks. Superior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages. Advanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability. More capable agents: GLM-4.6 exhibits stronger performance in tool using and search-based agents, and integrates more effectively within agent frameworks. Refined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.

glm-4.7

مباشر

zai-org

محادثةWeights مفتوحة

GLM-4.7 is a state-of-the-art, multilingual Mixture-of-Experts (MoE) language model designed for complex reasoning, agentic coding, and tool use. Building on its predecessor GLM-4.6, it delivers significant improvements across key benchmarks, including multilingual SWE-bench, Terminal Bench, and reasoning-heavy evaluations like HLE. The model features advanced "Interleaved Thinking" and new "Preserved Thinking" modes, allowing it to reason before actions and maintain consistency across long, multi-turn tasks. With 358 billion parameters, GLM-4.7 excels in generating clean code, modern UI elements, and sophisticated reasoning outputs.

glm-4.7-flash

مباشر

zai-org

محادثةWeights مفتوحة

GLM-4.7-Flash is a 30B-A3B MoE model. As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.

glm-5

مباشر

zai-org

محادثةWeights مفتوحة

GLM-5 is an advanced, open-source large language model designed for developers tackling the toughest challenges. It excels at long-context reasoning, multi-step tool orchestration, and complex systems engineering, making it the ideal choice for powering sophisticated agents and applications that require high-level cognitive tasks.

glm-5.1

مباشر

zai-org

محادثةWeights مفتوحة

GLM-5.1 is Z-AI's next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin on NL2Repo (repo generation) and Terminal-Bench 2.0 (real-world terminal tasks).

glm-5.2

مباشر

zai-org

محادثةWeights مفتوحة

GLM-5.2 is Z-AI's latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a **solid 1M-token context**.

glm-5.3-flash

مباشر

zai-org

محادثةWeights مفتوحة

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.

Google: Gemini 3.6 Flash

مباشر

Google

محادثة

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development.

Google: Gemini 3.7 Flash

مباشر

Google

محادثةمغلق المصدر

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.

Google: Gemini 3.8 Flash

مباشر

Google

محادثة

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

gpt-3.5-turbo

مباشر

OpenAI

محادثة

GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.

gpt-3.5-turbo-16k

مباشر

OpenAI

محادثة

This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost.

gpt-4

مباشر

OpenAI

محادثة

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning

gpt-4-turbo

مباشر

OpenAI

محادثة

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning

gpt-4.1

مباشر

OpenAI

محادثة

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning.

gpt-4.1-mini

مباشر

OpenAI

محادثة

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost.

gpt-4.1-nano

مباشر

OpenAI

محادثة

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.

gpt-4o

مباشر

OpenAI

محادثة

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.

gpt-4o-2024-05-13

مباشر

OpenAI

محادثة

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.

gpt-4o-2024-08-06

مباشر

OpenAI

محادثة

The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more here.

gpt-4o-2024-11-20

مباشر

OpenAI

محادثة

The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability.

gpt-4o-mini

مباشر

OpenAI

محادثة

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.

gpt-4o-mini-2024-07-18

مباشر

OpenAI

محادثة

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.

gpt-4o-mini-search-preview

مباشر

OpenAI

محادثة

GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

gpt-4o-search-preview

مباشر

OpenAI

محادثة

GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

gpt-5

مباشر

OpenAI

محادثة

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.

gpt-5-mini

مباشر

OpenAI

محادثة

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.

gpt-5-nano

مباشر

OpenAI

محادثة

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.

gpt-5.1

مباشر

OpenAI

محادثة

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5.

gpt-5.2

مباشر

OpenAI

محادثة

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1.

gpt-5.4

مباشر

OpenAI

محادثة

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.

gpt-5.4-mini

مباشر

OpenAI

محادثة

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.

gpt-5.4-nano

مباشر

OpenAI

محادثة

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.

gpt-5.5

مباشر

OpenAI

محادثة

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks.

gpt-5.6-luna

مباشر

OpenAI

محادثة

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.

gpt-5.6-sol

مباشر

OpenAI

محادثة

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series.

gpt-5.6-terra

مباشر

OpenAI

محادثة

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier.

gpt-6-astra

مباشر

OpenAI

محادثة

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.

gpt-6-luna

مباشر

OpenAI

محادثة

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.

gpt-6-sol

مباشر

OpenAI

محادثة

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier.

gpt-6.1-sol

مباشر

OpenAI

محادثة

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.

gpt-oss-120b

مباشر

OpenAI

محادثةWeights مفتوحة

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

gpt-oss-20b

مباشر

OpenAI

محادثةWeights مفتوحة

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.

Granite-4.2-8B is the mid-size reasoning model in the Granite 4.2 family. It delivers strong performance on reasoning-intensive tasks by leveraging built-in <think>...</think> chain-of-thought. It supports flexible thinking modes — full thinking (default), non-thinking, and low-effort — allowing users to balance depth vs. latency on a per-query basis.

gte-base

مباشر

thenlper

EmbeddingWeights مفتوحة

The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including GTE-large, GTE-base, and GTE-small. The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including information retrieval, semantic textual similarity, text reranking, etc.

gte-large

مباشر

thenlper

EmbeddingWeights مفتوحة

The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including GTE-large, GTE-base, and GTE-small. The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including information retrieval, semantic textual similarity, text reranking, etc.

hermes-3-llama-3.1-70b

مباشر

NousResearch

محادثةWeights مفتوحة

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 coherence, and improvements across the board.

Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and 3.8B MTP layer parameters, developed by the Tencent Hy Team. Following the Hy3 Preview launch in late April, we gathered feedback from 50+ products and scaled up post-training with higher quality data. Today, we introduce Hy3, which outperforms similar-size models and rivals flagship open-source models with 2-5x parameters. It also shows significant gains in utility across various products and productivity tasks.

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.

Kev 4B is a small open-weight decision model from Jared Palmer, built as a LoRA adapter and pointer head on Qwen3.5-4B-Base and served over the same /v1/systemone contract as TypeSafe's

kimi-k2.5

مباشر

moonshotai

محادثةWeights مفتوحة

Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.

kimi-k2.6

مباشر

moonshotai

محادثةWeights مفتوحة

Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.

kimi-k2.7-code

مباشر

moonshotai

محادثةWeights مفتوحة

Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by approximately 30% compared with Kimi K2.6.

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.

The multimodal version built on Ling-3.0-flash — 124B total / ~5.5B active per token, with native text, image, and video understanding. It’s mainly designed for multimodal agentic workflows, long-context understanding, and multi-step reasoning.

llama-3.3-70b-instruct-turbo

مباشر

Meta

محادثةWeights مفتوحة

Llama 3.3-70B Turbo is a highly optimized version of the Llama 3.3-70B model, utilizing FP8 quantization to deliver significantly faster inference speeds with a minor trade-off in accuracy. The model is designed to be helpful, safe, and flexible, with a focus on responsible deployment and mitigating potential risks such as bias, toxicity, and misinformation. It achieves state-of-the-art performance on various benchmarks, including conversational tasks, language translation, and text generation.

llama-4-scout-17b-16e-instruct

مباشر

Meta

محادثةWeights مفتوحة

The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. Llama 4 Scout, a 17 billion parameter model with 16 experts

llama-guard-4-12b

مباشر

Meta

محادثةWeights مفتوحة

Llama Guard 4 is a natively multimodal safety classifier with 12 billion parameters trained jointly on text and multiple images. Llama Guard 4 is a dense architecture pruned from the Llama 4 Scout pre-trained model and fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It itself acts as an LLM: it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.

llama-nemotron-embed-vl-1b-v2

مباشر

NVIDIA

EmbeddingWeights مفتوحة

The llama-nemotron-embed-vl-1b-v2 is a high-performance multimodal embedding model designed to transform text queries and document images into dense vector representations for advanced retrieval systems. It excels at understanding complex visual content like charts, tables, and infographics.

Meta Llama 3.2 1B Instruct

مباشر

Meta

محادثةWeights مفتوحة

Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis.

Meta Llama 3.2 3B Instruct

مباشر

Meta

محادثةWeights مفتوحة

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

meta-llama-3.1-70b-instruct-turbo

مباشر

Meta

محادثةWeights مفتوحة

Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes

meta-llama-3.1-8b-instruct-turbo

مباشر

Meta

محادثةWeights مفتوحة

Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes

mimo-v2.5

مباشر

XiaomiMiMo

محادثةWeights مفتوحة

MiMo-V2.5 is a native omnimodal model with strong agentic capabilities, supporting text, image, video, and audio understanding within a unified architecture. Built upon the MiMo-V2-Flash backbone and extended with dedicated vision and audio encoders, it delivers robust performance across multimodal perception, long-context reasoning, and agentic workflows.

mimo-v2.5-pro

مباشر

XiaomiMiMo

محادثةWeights مفتوحة

MiMo-V2.5-Pro is an open-source Mixture-of-Experts (MoE) language model with 1.02T total parameters and 42B active parameters. It utilizes the hybrid attention architecture and 3-layers Multi-Token Prediction (MTP) introduced in MiMo-V2-Flash.

Design-native, open-weight text-to-image (6B) — ranked #1 among open-weight models on Artificial Analysis's UI/UX Design leaderboard. Renders legible UI and poster text plus cohesive graphics, illustration and photography in ~1.7s. MIT-licensed.

Open-weight layer decomposition (6B) from the Ming-Image 0.1 Design family — splits a flattened design or composite into stacked, transparent, editable PNG layers (text, subject, background) for localizable, editable design workflows. MIT-licensed.

MiniMax M2

مباشر

MiniMaxAI

محادثةWeights مفتوحة

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows.

minimax-m2.7

مباشر

MiniMaxAI

محادثةWeights مفتوحة

MiniMax-M2.7 is MiniMax's first model deeply participating in its own evolution. M2.7 is capable of building complex agent harnesses and completing highly elaborate productivity tasks, leveraging Agent Teams, complex Skills, and dynamic tool search.

minimax-m3

مباشر

MiniMaxAI

محادثةWeights مفتوحة

MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.

mistral-nemo-instruct-2407

مباشر

Mistral AI

محادثةWeights مفتوحة

12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.

mistral-small-24b-instruct-2501

مباشر

Mistral AI

محادثةWeights مفتوحة

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 for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware.

mistral-small-3.2-24b-instruct-2506

مباشر

Mistral AI

محادثةWeights مفتوحة

Mistral-Small-3.2-24B-Instruct is a drop-in upgrade over the 3.1 release, with markedly better instruction following, roughly half the infinite-generation errors, and a more robust function-calling interface—while otherwise matching or slightly improving on all previous text and vision benchmarks.

MoonshotAI: Kimi K2 0711

مباشر

moonshotai

محادثة

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass.

MoonshotAI: Kimi K2 0905

مباشر

moonshotai

محادثة

Kimi K2 0905 is the September update of Kimi K2 0711.

MoonshotAI: Kimi K3

مباشر

moonshotai

محادثةWeights مفتوحة

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.

multi-qa-mpnet-base-dot-v1

مباشر

SBERT

EmbeddingWeights مفتوحة

We present a sentence transformation model that maps sentences and paragraphs to a 768-dimensional dense vector space, suitable for semantic search tasks. The model is trained on 215 million question-answer pairs from various sources, including WikiAnswers, PAQ, Stack Exchange, MS MARCO, GOOAQ, Amazon QA, Yahoo Answers, Search QA, ELI5, and Natural Questions. Our model uses a contrastive learning objective.

multilingual-e5-large

مباشر

intfloat

EmbeddingWeights مفتوحة

The Multilingual-E5-large model is a 24-layer text embedding model with an embedding size of 1024, trained on a mixture of multilingual datasets and supporting 100 languages.

multilingual-e5-large-instruct

مباشر

intfloat

EmbeddingWeights مفتوحة

The Multilingual-E5 models, initialized from XLM-RoBERTa, support up to 512 tokens per input — any longer text will be silently truncated. To ensure optimal performance, always prefix inputs with “query:” or “passage:”, as the model was explicitly trained with this format.

nano-banana-2

مباشر

Google

imageمغلق المصدر

Nano Banana 2 makes high quality image generation and editing mainstream. The model also introduces Grounding with Google Image Search to enable long-tail entity recognition and enhance visual understanding.

nano-banana-2-lite

مباشر

Google

imageمغلق المصدر

Nano Banana 2 Lite enables high speed image generation a reality, while keeping the high quality editing of Nano Banana.

nano-banana-pro

مباشر

Google

imageمغلق المصدر

Nano Banana Pro is designed to tackle the most challenging image generation by incorporating state-of-the-art reasoning capabilities. It is the best model for complex and multi-turn image generation and editing.

nemotron-3-nano-30b-a3b

مباشر

NVIDIA

محادثةWeights مفتوحة

NVIDIA Nemotron 3 Nano is an open small reasoning model optimized for fast, cost-efficient inference in agentic and production workloads. Built with a hybrid Mixture-of-Experts (MoE) and Mamba-Transformer architecture, it delivers strong multi-step reasoning, high token throughput, stable latency with predictable cost, and efficient deployment for agent-based systems. Designed for real-world AI systems where reasoning can generate significantly more tokens per prompt, Nemotron Nano reduces compute cost while maintaining strong reasoning quality.

nemotron-content-safety-3.5

مباشر

NVIDIA

محادثةWeights مفتوحة

Nemotron Content Safety 3.5 is a multimodal safety classifier developed by NVIDIA. A compact safety model that handles text, images, and custom policies. It outputs a safe/unsafe classification plus a reasoning trace, and can be used as an inference-time guardrail, as a judge for LLM safety testing and evaluation, or with the accompanying training dataset to post-train models for safer behavior.

nim/meta/llama-3.1-70b-instruct

مباشر

nim

محادثة

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases.

nim/meta/llama-3.1-8b-instruct

مباشر

nim

محادثة

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient.

nim/meta/llama-3.3-70b-instruct

مباشر

nim

محادثة

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).

NVIDIA Nemotron 3 Ultra 550B A55B NVFP4

مباشر

NVIDIA

محادثة

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).

nvidia-nemotron-3-super-120b-a12b

مباشر

NVIDIA

محادثةWeights مفتوحة

NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single GPU, delivering high accuracy for reasoning, tool use, and instruction following.

nvidia-nemotron-3-ultra-550b-a55b

مباشر

NVIDIA

محادثةWeights مفتوحة

Nemotron 3 Ultra is built for, frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads while supporting up to 1M token context.

nvidia-nemotron-3.5-lightning

مباشر

NVIDIA

محادثةWeights مفتوحة

NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substantial leap in agentic capability over its predecessor Nemotron 3 Nano, with up to 4x higher throughput on a 1M-token context.

o1

مباشر

OpenAI

محادثة

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding.

o3

مباشر

OpenAI

محادثة

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks.

o3-mini

مباشر

OpenAI

محادثة

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding.

o4-mini

مباشر

OpenAI

محادثة

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities.

OpenAI: GPT-6 Luna Decisions

مباشر

OpenAI

قرار

GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI's Decisions API.

p-image

مباشر

PrunaAI

imageمغلق المصدر

P-Image is a state-of-the-art real-time generation model with exceptional text rendering, fine-detail accuracy, and rock-solid prompt adherence. It’s built for instant creativity at high-fidelity images in about one second at a fraction of typical model costs.

paraphrase-minilm-l6-v2

مباشر

SBERT

EmbeddingWeights مفتوحة

We present a sentence similarity model based on the Sentence Transformers architecture, which maps sentences to a 384-dimensional dense vector space. The model uses a pre-trained BERT encoder and applies mean pooling on top of the contextualized word embeddings to obtain sentence embeddings. We evaluate the model on the Sentence Embeddings Benchmark.

phi-4

مباشر

Microsoft

محادثةWeights مفتوحة

Phi-4 is a model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets. The goal of this approach was to ensure that small capable models were trained with data focused on high quality and advanced reasoning.

qwen-image-max

مباشر

Alibaba

imageمغلق المصدر

Compared with the Plus series, it significantly reduces the “AI-like” feel in generated images, enhancing their realism. It delivers more lifelike material textures for human subjects, finer and more detailed natural textures, and more visually appealing text rendering.

Qwen: Qwen3 Coder Flash

مباشر

Alibaba

محادثة

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus.

Qwen: Qwen3 Coder Next

مباشر

Alibaba

محادثة

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows.

Qwen: Qwen3.5 Plus 2026-02-15

مباشر

Alibaba

محادثة

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency.

Qwen: Qwen3.5 Plus 2026-04-20

مباشر

Alibaba

محادثة

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window.

Qwen: Qwen3.5-Flash

مباشر

Alibaba

محادثة

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.

Qwen: Qwen3.6 Flash

مباشر

Alibaba

محادثة

Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window.

Qwen: Qwen3.7 Flash

مباشر

Alibaba

محادثة

Qwen3.7 Flash is a vision-language reasoning model from Alibaba.

Qwen: Qwen3.8 27B

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3.8 27B is an open-weight dense vision-language model from Qwen.

Qwen: Qwen3.8 Flash

مباشر

Alibaba

محادثةمغلق المصدر

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

Qwen: Qwen3.8 Max

مباشر

Alibaba

محادثةمغلق المصدر

Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview.

Qwen2.5-VL (72B) Instruct

مباشر

Alibaba

محادثةWeights مفتوحة

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.

Qwen3 Coder 30B A3b Instruct

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use.

Qwen3 Next 80B A3b Thinking

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default.

qwen3-14b

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support.

qwen3-235b-a22b-instruct-2507

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3-235B-A22B-Instruct-2507 is the updated version of the Qwen3-235B-A22B non-thinking mode, featuring Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.

qwen3-235b-a22b-thinking-2507

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3-235B-A22B-Thinking-2507 is the Qwen3's new model with scaling the thinking capability of Qwen3-235B-A22B, improving both the quality and depth of reasoning.

qwen3-30b-a3b

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support

qwen3-32b

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support

qwen3-embedding-0.6b

مباشر

Alibaba

EmbeddingWeights مفتوحة

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).

qwen3-embedding-4b

مباشر

Alibaba

EmbeddingWeights مفتوحة

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).

qwen3-embedding-8b

مباشر

Alibaba

EmbeddingWeights مفتوحة

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).

qwen3-next-80b-a3b-instruct

مباشر

Alibaba

محادثةWeights مفتوحة

Over the past few months, we have observed increasingly clear trends toward scaling both total parameters and context lengths in the pursuit of more powerful and agentic artificial intelligence (AI). We are excited to share our latest advancements in addressing these demands, centered on improving scaling efficiency through innovative model architecture. We call this next-generation foundation models Qwen3-Next.

qwen3-vl-235b-a22b-instruct

مباشر

Alibaba

محادثةWeights مفتوحة

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.

qwen3-vl-30b-a3b-instruct

مباشر

Alibaba

محادثةWeights مفتوحة

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.

Qwen3-VL-8B-Instruct

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video.

qwen3.5-122b-a10b

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3.5-122B-A10B is a large Mixture-of-Experts model from Alibaba's Qwen3.5 series with 122B total parameters and 10B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Excels at complex reasoning, coding, multimodal understanding, and agentic tasks with the efficiency of sparse activation.

qwen3.5-27b

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3.5-27B is Alibaba's largest dense Qwen3.5 model, delivering near-frontier quality across reasoning, coding, and instruction following. It features a 262K token context window (extensible to 1M), thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Best suited for production deployments and complex enterprise tasks requiring top-tier performance.

qwen3.5-35b-a3b

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3.5-35B-A3B is an efficient Mixture-of-Experts model from Alibaba's Qwen3.5 series with 35B total parameters and only 3B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Delivers strong performance on reasoning, coding, and vision-language tasks at a fraction of the compute cost.

qwen3.5-397b-a17b

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3.5-397B-A17B is Alibaba's most capable Qwen3.5 model, a Mixture-of-Experts architecture with 397B total parameters and 17B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling with MCP integration, and support for 201 languages. Sets state-of-the-art results on reasoning, coding, math, and multimodal benchmarks.

qwen3.5-9b

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It features a 262K token context window, thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Excels at reasoning, coding, instruction following, and long-context tasks.

qwen3.6-35b-a3b

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3.6-35B-A3B is Alibaba's latest flagship Mixture-of-Experts model, with 35B total parameters and only 3B activated per token (256 experts, 8 routed + 1 shared). Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience.

Qwen3.7 Plus

مباشر

Alibaba

محادثة

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series.

qwen3.8-2.4t-a95b

مباشر

Alibaba

محادثةWeights مفتوحة

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.

sdxl-turbo

مباشر

stabilityai

imageWeights مفتوحة

The SDXL Turbo model, developed by Stability AI, is an optimized, fast text-to-image generative model. It is a distilled version of SDXL 1.0, leveraging Adversarial Diffusion Distillation (ADD) to generate high-quality images in less steps.

seed-1.8

مباشر

ByteDance

محادثةمغلق المصدر

Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.

seed-2.0-code

مباشر

ByteDance

محادثةمغلق المصدر

A coding model optimized for real-world development environments, with reliable tool use in common IDEs such as Claude Code. It delivers strong front-end performance and supports Skills.

seed-2.0-mini

مباشر

ByteDance

محادثةمغلق المصدر

Built for low-latency, high-concurrency, cost-sensitive use cases, with flexible deployment, four-tier thinking, and multimodal

seed-2.0-pro

مباشر

ByteDance

محادثةمغلق المصدر

Built for the Agent era, it delivers stable performance in complex reasoning and long-horizon tasks, including multi-step planning, visual-text reasoning, video understanding, and advanced analysis.

seedream-4

مباشر

ByteDance

imageمغلق المصدر

Seedream 4.0 is a SOTA multimodal image creation model built on leading architecture. It breaks through the boundaries of traditional text-to-image models by natively supporting text, single-image, and multi-image inputs. Users can freely combine text and images to achieve diverse creative modes within a single model—such as multi-image blending, image editing, and sequentially batch image generation, featuring subject consistency, making image creation more free and controllable.

seedream-4.5

مباشر

ByteDance

imageمغلق المصدر

The latest image model, delivering better editing consistency, improved multi-image fusion, finer detail control, natural small text and faces, and harmonious, aesthetic visuals.

seedream-5.0-pro

مباشر

ByteDance

imageمغلق المصدر

ByteDance's flagship image model, with precise interactive editing, stronger multi-reference fusion and notably accurate text rendering at up to 2K.

step-3.7-flash

مباشر

stepfun-ai

محادثةWeights مفتوحة

Step 3.7 Flash is an open-source multimodal reasoning model by StepFun with 198B total parameters (11B active) using Mixture of Experts. It accepts text and image inputs and features a 256K context window, selectable reasoning effort, tool calling, and agentic capabilities for coding and search workflows, scoring 80.9% on GPQA Diamond and 56.3% on SWE-bench Pro.

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total.

text2vec-base-chinese

مباشر

shibing624

EmbeddingWeights مفتوحة

A sentence similarity model that can be used for various NLP tasks such as text classification, sentiment analysis, named entity recognition, question answering, and more. It utilizes the CoSENT architecture, which consists of a transformer encoder and a pooling module, to encode input texts into vectors that capture their semantic meaning. The model was trained on the nli_zh dataset and achieved high performance on various benchmark datasets.

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total.

Jev is a structured decision model from TypeSafe, and the first of its System One models.

voxtral-small-24b-2507

مباشر

Mistral AI

محادثةWeights مفتوحة

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.

wan2.6-t2i

مباشر

Wan-AI

imageمغلق المصدر

Wan2.6 text to image, Upgraded visual quality, aesthetics, and instruction-following deliver precise style control, realistic portraits, long-text understanding, and broad historical/cultural IP coverage, enabling high-quality, highly expressive visual generation.

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.

MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi.

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.