152 models

all-minilm-l12-v2

Live

SBERT

EmbeddingOpen weights

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

Live

SBERT

EmbeddingOpen weights

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

Live

SBERT

EmbeddingOpen weights

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.

bge-base-en-v1.5

Live

BAAI

EmbeddingOpen weights

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

Live

BAAI

EmbeddingOpen weights

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

Live

BAAI

EmbeddingOpen weights

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

Live

BAAI

EmbeddingOpen weights

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

Live

BAAI

EmbeddingOpen weights

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

Live

BAAI

Embedding

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.

blur-background

Live

Bria

image

Bria Blur Background softens and de-emphasizes image backgrounds while keeping the subject sharp and clear for professional-quality results. Trained fully on licensed data, it delivers safe, natural, and commercial-ready outputs.

bria-3.2

Live

Bria

image

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

Live

Bria

image

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

Live

Anthropic

ChatProprietary

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

Live

Anthropic

ChatProprietary

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

Live

Anthropic

ChatProprietary

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

claude-opus-4.8

Live

Anthropic

ChatProprietary

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-opus-5

Live

Anthropic

Chat

Claude Opus 5 is Anthropic's most advanced Opus model, powering long-running agents while delivering improvements in coding and professional work.

claude-sonnet-4.6

Live

Anthropic

ChatProprietary

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

claude-sonnet-5

Live

Anthropic

ChatProprietary

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

Live

SBERT

EmbeddingOpen weights

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

Live

SBERT

EmbeddingOpen weights

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

Live

DeepSeek

ChatOpen weights

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

deepseek-v3

Live

DeepSeek

ChatOpen weights

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-v3-0324

Live

DeepSeek

ChatOpen weights

DeepSeek-V3-0324, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token, an improved iteration over DeepSeek-V3.

deepseek-v3.1

Live

DeepSeek

ChatOpen weights

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-v3.2

Live

DeepSeek

ChatOpen weights

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

Live

DeepSeek

ChatOpen weights

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-flash-0731

Live

DeepSeek

Chat

DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities. DeepSeek-V4-Flash-0731 outperforms DeepSeek-V4-Pro (Preview) on benchmarks listed below despite its far smaller activated parameter count, and is broadly competitive with the strongest proprietary models available.

deepseek-v4-flash-vision-exp

Live

DeepSeek

Chat

DeepSeek-V4-Flash-Vision-Exp is DeepSeek's experimental multimodal model in the V4-Flash family, adding visual understanding to the V4-Flash architecture. It serves a 1M-token (1,048,576) context window and supports image input with visual grounding, tool calling, structured/JSON output, and configurable reasoning effort (low/high/max, or disabled).

deepseek-v4-pro

Live

DeepSeek

ChatOpen weights

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-pro-0813

Live

DeepSeek

Chat

DeepSeek-V4-Pro-0813 is the official release of DeepSeek-V4-Pro, superseding the preview version, with greatly enhanced agentic capabilities and performance improvements that are especially pronounced in production environments. It is built on the DeepSeek-V4-Pro (Preview) model structure, with a DSpark speculative decoding module attached.

deepseek-v4.1-flash

Live

DeepSeek

Chat

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.

e5-base-v2

Live

intfloat

EmbeddingOpen weights

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

e5-large-v2

Live

intfloat

EmbeddingOpen weights

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

embeddinggemma-300m

Live

Google

EmbeddingOpen weights

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.

erase-foreground

Live

Bria

image

Bria Erase Foreground precisely removes main subjects or foreground objects from images. Built entirely on licensed data, it is safe and optimized for professional and commercial use.

expand

Live

Bria

image

Bria Expand expands images beyond their borders in high quality. Resizing the image by generating new pixels to expand to the desired aspect ratio. Trained exclusively on licensed data for safe and risk-free commercial use.

fibo

Live

Bria

image

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-edit

Live

Bria

image

🥳 For a limited time, Fibo Edit is free on DeepInfra 🥳 YOUR AI, YOUR RULES. Visual Generation for Production-Grade. FIBO Edit. An open-source image editing model with native masking and a lightweight 8B architecture.

flux-1-dev

Live

black-forest-labs

image

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-redux-dev

Live

black-forest-labs

image

FLUX.1 Redux [dev] is an image variation generation adapter for all FLUX.1 base models. It enables users to refine images with slight variations and supports text-based restyling via API. Integrated with FLUX1.1 [pro] Ultra, it allows for high-quality 4-megapixel outputs. The model can be used with Diffusers in Python for efficient image generation. While powerful, it has ethical and factual limitations and is governed by a non-commercial license.

flux-1-schnell

Live

black-forest-labs

image

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

Live

black-forest-labs

image

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

Live

black-forest-labs

image

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

Live

black-forest-labs

image

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

Live

black-forest-labs

image

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

Live

black-forest-labs

image

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

flux-2-pro

Live

black-forest-labs

image

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.

flux.1-kontext-dev

Live

black-forest-labs

image

FLUX.1 Kontext [dev] is a 12-billion-parameter image editing model that transforms visuals based on natural language instructions. It allows highly consistent, multi-step edits and is released with open weights under a non-commercial license to empower artists and researchers.

gemini-2.5-flash

Live

Google

ChatProprietary

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

Live

Google

ChatProprietary

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

Live

Google

image

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

Live

Google

ChatProprietary

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

Live

Google

ChatProprietary

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

Live

Google

ChatProprietary

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.

gemini-3.7-flash

Live

Google

Chat

Gemini 3.7 Flash delivers near-Pro intelligence at Flash-tier cost and speed; exceeding Pro’s performance for most agentic tasks.

gemma-3-12b-it

Live

Google

ChatOpen weights

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

Live

Google

ChatOpen weights

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

Live

Google

ChatOpen weights

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

Live

Google

ChatOpen weights

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

Live

Google

ChatOpen weights

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

Live

Google

ChatOpen weights

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

Live

Google

Chat

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

glm-4.6

Live

zai-org

ChatOpen weights

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

Live

zai-org

ChatOpen weights

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-5.1

Live

zai-org

ChatOpen weights

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

Live

zai-org

ChatOpen weights

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

Live

zai-org

Chat

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.

gpt-oss-120b

Live

OpenAI

ChatOpen weights

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-120b-ultra

Live

OpenAI

Chat

Ultra speed version of gpt-oss-120b

gpt-oss-20b

Live

OpenAI

ChatOpen weights

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-4.2-30B is the flagship reasoning model in the Granite 4.2 family. It delivers the strongest performance across 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.

Granite-4.2-3B is the compact reasoning model in the Granite 4.2 family. Despite its small parameter count, 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.

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

Live

thenlper

EmbeddingOpen weights

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

Live

thenlper

EmbeddingOpen weights

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-3.1-405b

Live

NousResearch

ChatOpen weights

Hermes 3 is a cutting-edge language model that offers advanced capabilities in roleplaying, reasoning, and conversation. It's a fine-tuned version of the Llama-3.1 405B foundation model, designed to align with user needs and provide powerful control. Key features include reliable function calling, structured output, generalist assistant capabilities, and improved code generation. Hermes 3 is competitive with Llama-3.1 Instruct models, with its own strengths and weaknesses.

hermes-3-llama-3.1-70b

Live

NousResearch

ChatOpen weights

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 a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs.

Inkling-Small is a Mixture-of-Experts transformer with 276B total parameters, 12B active, trained on NVIDIA GB300 NVL72 systems. Like Inkling, it features native reasoning over audio and images, variable thinking effort

kimi-k2.6

Live

moonshotai

ChatOpen weights

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

Live

moonshotai

ChatOpen weights

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.

kimi-k3

Live

moonshotai

Chat

Kimi K3 is Moonshot AI's 2.8T-parameter open-weight multimodal reasoning model. Built for complex coding, knowledge work, and long-horizon agentic workflows, it excels at navigating large repositories, calling tools, debugging, and iterating on images, logs, tests, and runtime feedback. Its architecture relies on KDA and Attention Residuals for computational efficiency.

The model prioritizes token efficiency and agentic inference at production scale, stretching what developers can achieve within limited token, latency, and serving-cost budgets.

Ling-3.0-flash-Fin is the first finance-enhanced model in the Ant Ling family. Developed by Ant Group with leading financial institutions and domain experts, it extends Ling-3.0-flash through continued training on high-quality financial data.

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

Live

Meta

ChatOpen weights

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-maverick-17b-128e-instruct-fp8

Live

Meta

ChatOpen weights

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 Maverick, a 17 billion parameter model with 128 experts

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

Live

Meta

ChatOpen weights

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

Live

Meta

ChatOpen weights

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

Live

NVIDIA

EmbeddingOpen weights

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-3.1-70b-instruct-turbo

Live

Meta

ChatOpen weights

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

Live

Meta

ChatOpen weights

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

Live

XiaomiMiMo

ChatOpen weights

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

Live

XiaomiMiMo

ChatOpen weights

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.

minimax-m2.7-turbo

Live

MiniMaxAI

ChatProprietary

Speed-optimized MiniMax-M2.7

minimax-m3

Live

MiniMaxAI

ChatOpen weights

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

mistral-nemo-instruct-2407

Live

Mistral AI

ChatOpen weights

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

mistral-small-24b-instruct-2501

Live

Mistral AI

ChatOpen weights

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

Live

Mistral AI

ChatOpen weights

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.

multi-qa-mpnet-base-dot-v1

Live

SBERT

EmbeddingOpen weights

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

Live

intfloat

EmbeddingOpen weights

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

Live

intfloat

EmbeddingOpen weights

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.

Muse Glimmer is a 30B multimodal agentic model distilled from Muse Spark — reasoning, tool use, and failure recovery in a single model that runs locally on consumer hardware.

nemotron-3-nano-30b-a3b

Live

NVIDIA

ChatOpen weights

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

Live

NVIDIA

ChatOpen weights

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.

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

Live

NVIDIA

ChatOpen weights

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

Live

NVIDIA

ChatOpen weights

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

Live

NVIDIA

Chat

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.

p-image

Live

PrunaAI

image

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

Live

SBERT

EmbeddingOpen weights

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

Live

Microsoft

ChatOpen weights

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-edit

Live

Alibaba

image

Qwen-Image-Edit is a next-generation image editing model built on top of Qwen-Image, designed for both semantic and appearance-level edits. It excels at tasks like precise text modifications, style transfers, viewpoint transformations, and element adjustments while preserving overall visual consistency.

qwen-image-max

Live

Alibaba

image

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.

qwen2.5-72b-instruct

Live

Alibaba

ChatOpen weights

Qwen2.5 is a model pretrained on a large-scale dataset of up to 18 trillion tokens, offering significant improvements in knowledge, coding, mathematics, and instruction following compared to its predecessor Qwen2. The model also features enhanced capabilities in generating long texts, understanding structured data, and generating structured outputs, while supporting multilingual capabilities for over 29 languages.

qwen3-14b

Live

Alibaba

ChatOpen weights

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

Live

Alibaba

ChatOpen weights

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.

qwen3-30b-a3b

Live

Alibaba

ChatOpen weights

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

Live

Alibaba

ChatOpen weights

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-coder-480b-a35b-instruct-turbo

Live

Alibaba

ChatOpen weights

Qwen3-Coder-480B-A35B-Instruct is the Qwen3's most agentic code model, featuring Significant Performance on Agentic Coding, Agentic Browser-Use and other foundational coding tasks, achieving results comparable to Claude Sonnet.

qwen3-embedding-0.6b

Live

Alibaba

EmbeddingOpen weights

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

Live

Alibaba

EmbeddingOpen weights

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

Live

Alibaba

EmbeddingOpen weights

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-max

Live

Alibaba

ChatProprietary

The latest flagship model in the Qwen family. State-of-the-art results across a comprehensive suite of benchmarks — including knowledge, reasoning, coding, instruction following, human preference alignment, agent tasks, and multilingual understanding.

qwen3-max-thinking

Live

Alibaba

ChatProprietary

The latest flagship reasoning model in the Qwen3 family. Further enhanced by multiple innovations like adaptive tool-use and advanced test-time scaling techniques

qwen3-next-80b-a3b-instruct

Live

Alibaba

ChatOpen weights

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

Live

Alibaba

ChatOpen weights

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

Live

Alibaba

ChatOpen weights

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.

qwen3.5-122b-a10b

Live

Alibaba

ChatOpen weights

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

Live

Alibaba

ChatOpen weights

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

Live

Alibaba

ChatOpen weights

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

Live

Alibaba

ChatOpen weights

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

Live

Alibaba

ChatOpen weights

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

Live

Alibaba

ChatOpen weights

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-max

Live

Alibaba

ChatProprietary

The largest and most capable in the Qwen3.7 series. Qwen3.7 is a next‑generation flagship model designed for the agent‑centric.

qwen3.8-2.4t-a95b

Live

Alibaba

Chat

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.

qwen3.8-flash

Live

Alibaba

Chat

Qwen's fast, low-cost model with a one-million-token context window, billed at a flat rate across the entire window.

qwen3.8-max

Live

Alibaba

Chat

Qwen's latest 2.4-trillion-parameter MoE flagship model delivering a comprehensive leap in coding and professional work.

remove-background

Live

Bria

image

Bria RMBG 2.0 enables seamless removal of backgrounds from images, ideal for professional editing tasks. Trained exclusively on licensed data for safe and risk-free commercial use.

sdxl-turbo

Live

stabilityai

image

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

Live

ByteDance

ChatProprietary

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

seed-2.0-code

Live

ByteDance

ChatProprietary

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

Live

ByteDance

ChatProprietary

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

seed-2.0-pro

Live

ByteDance

ChatProprietary

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

Live

ByteDance

image

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.

step-3.7-flash

Live

stepfun-ai

ChatOpen weights

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.

text2vec-base-chinese

Live

shibing624

EmbeddingOpen weights

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.

wan2.6-t2i

Live

Wan-AI

image

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.