AI 大语言模型目录

Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...

Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...

Qwen vision-language model for visual reasoning, documents, and agent tasks

Efficient Qwen model for fast chat, extraction, and high-volume workloads

Flagship Qwen model for complex reasoning, coding, and agentic workflows

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

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

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

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

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

Efficient Qwen model for fast chat, extraction, and high-volume workloads

Qwen vision-language model for visual reasoning, documents, and agent tasks

OCR model for extracting structured text from documents and screenshots

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

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

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen instruction model for multilingual chat, reasoning, and tool use

Large open Qwen MoE for multilingual reasoning, coding, and tool use

Dense open Qwen model for self-hosted chat, reasoning, and coding

Qwen instruction model for multilingual chat, reasoning, and tool use

Speech transcription model for accurate audio-to-text and captioning workflows

Smaller Qwen coder for efficient local agents and repo-level fixes

Open Qwen coding heavyweight for repository reasoning and agentic engineering

Qwen coding model for software agents, repository edits, and code reasoning

Hosted Qwen coder for software agents, repo edits, and long-context code

Speech generation model for controllable voice, narration, and audio delivery

Flagship Qwen3 model for coding agents, complex reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

Efficient Qwen thinking model for local reasoning, math, and coding agents

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

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

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen vision-language model for visual reasoning, documents, and agent tasks

Large open Qwen multimodal MoE for visual agents and long technical tasks

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen vision-language model for visual reasoning, documents, and agent tasks

Open multimodal Qwen MoE for local agents that need vision, audio, and code

Qwen vision-language model for visual reasoning, documents, and agent tasks

Flagship Qwen model for complex reasoning, coding, and agentic workflows

Earlier Qwen multimodal workhorse for million-token agent and document tasks

Lightweight multimodal Qwen model for high-throughput text, image, and video tasks

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

Multimodal Qwen workhorse for long-context agents, visual inputs, and coding

Qwen vision-language model for visual reasoning, documents, and agent tasks

2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows

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

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

Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...

Qwen instruction model for multilingual chat, reasoning, and tool use

Efficient Qwen model for fast chat, extraction, and high-volume workloads

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

Efficient Qwen model for fast chat, extraction, and high-volume workloads

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen coding model for software agents, repository edits, and code reasoning

Qwen coding model for software agents, repository edits, and code reasoning

Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen instruction model for multilingual chat, reasoning, and tool use

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

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

DeepSeek chat model for instruction following, coding, and analysis

DeepSeek chat model for instruction following, coding, and analysis

DeepSeek chat model for instruction following, coding, and analysis

General-purpose chat model for instruction following, writing, and analysis

Qwen coding model for software agents, repository edits, and code reasoning

Flagship Qwen model for complex reasoning, coding, and agentic workflows

Video model for image-to-video generation

Video model for reference-guided video generation

Video model for prompt-driven text-to-video generation

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

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

Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows

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

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

Claude model for creative writing, analysis, and controlled agent workflows

Claude model for demanding reasoning and long-horizon agentic work

Fast Claude lane for lightweight agents, office tasks, and responsive chat

Fast Claude model for responsive assistance, classification, and lightweight agents

Fast Claude model for responsive assistance, classification, and lightweight agents

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

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

High-end Claude for difficult coding, planning, and slower expert reasoning

Stronger Opus tier for advanced software work and high-stakes reasoning

Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents

Strongest Claude Opus model for coding, agents, and professional work

Claude model for long-running agentic coding and knowledge work

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

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

Claude workhorse for coding agents, careful analysis, and production cost control

Everyday Claude agent model for coding, planning, browsing, and general work

Fast Claude model for everyday coding, agents, and knowledge work

Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use

Open-weight instruction model for adaptable chat and self-hosted production workloads

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

Open multilingual model optimized for generation across 23 languages

Cohere command model for multilingual enterprise agents, tools, and chat

Cohere's stronger command model for multilingual agents and enterprise workflows

Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows

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

Cohere vision model for multilingual document analysis, OCR, and image understanding

Cohere retrieval model for long-context chat and enterprise RAG workflows

Cohere's RAG workhorse for long-context enterprise search and tool use

Cohere retrieval model for long-context chat and enterprise RAG workflows

Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge

Cohere coding model for practical software engineering and agentic edits

Open-weight translation model for more than 50 languages and locale variants

Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...

Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...

Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...

Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports

Agentic model for autonomous multi-step research, synthesis, and cited reports

Specialized Gemini 2.5 model for browser-control agents that automate UI tasks

Fast Gemini workhorse for multimodal apps where latency and price matter

Nano Banana image model for fast generation, edits, and character-consistent assets

Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

Speech generation model for controllable voice, narration, and audio delivery

Google's proven reasoning model for coding, math, and multimodal analysis

Speech generation model for controllable voice, narration, and audio delivery

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

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

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

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

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

Low-latency Gemini model for high-volume multimodal and agent workloads

Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing

Legacy model retained for compatibility with older integrations

High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications

Low-latency speech generation with steerable prompts and expressive audio tags

Reasoning-first Gemini preview for agentic coding and complex problem solving

Advanced Gemini model for complex reasoning, coding, and multimodal analysis

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Low-latency audio-to-audio model for real-time speech translation across 70+ languages

Fast Gemini model balancing multimodal reasoning, tool use, and cost

High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents

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

Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space

High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

Fast Gemini model balancing multimodal reasoning, tool use, and cost

Video generation and editing model for fast, conversational text- and image-to-video workflows

Reasoning-first Gemini preview for agentic coding and complex problem solving

Music generation model for short 30-second clips, loops, and previews from text or image prompts

Music generation model for full-length songs from text or images with vocals and structure

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...

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

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception

Inception's diffusion reasoning model for chat, multi-step problem solving, and tool use

Code editing dLLM for autocomplete (FIM) and next-edit suggestions

Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...

Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.

Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...

Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...

LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...

Open multimodal Llama model for strong reasoning and fast responses

Open multimodal Llama model for long-context analysis and efficient agents

Open multimodal Llama model for strong reasoning and fast responses

Open Llama instruction model for multilingual chat, reasoning, and coding

Open Llama instruction model for multilingual chat, reasoning, and coding

Open multimodal Llama model for strong reasoning and fast responses

Open multimodal Llama model for long-context analysis and efficient agents

Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...

Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...

Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window

Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.

Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.

Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.

Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.

Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.

Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.

Efficient open MiniMax model built for coding agents and tool-heavy workflows

Earlier MiniMax agent model for practical coding and productivity tasks

High-speed MiniMax model for low-latency coding and agent workflows

Prior MiniMax coding model for agent workflows, office edits, and automation

High-speed MiniMax model for low-latency coding and agent workflows

Open MiniMax flagship for coding agents, office automation, and complex environments

Low-latency M2.7 variant for interactive coding plans and agent loops

MiniMax multimodal model for long-context coding, perception, and agent planning

Frontier multimodal coding model with 1M context window and tunable thinking depth

Frontier multimodal coding model with 1M context window and tunable thinking depth

Mistral code model for low-latency completion, fill-in-the-middle, and code generation

Mistral code model for completions, refactors, and developer IDE workflows

Mistral's coding-agent model for repository work, terminal tasks, and software fixes

Legacy model retained for compatibility with older integrations

Legacy model retained for compatibility with older integrations

Legacy model retained for compatibility with older integrations

Legacy model retained for compatibility with older integrations

Legacy model retained for compatibility with older integrations

Open flagship GLM for long-horizon coding agents and million-token context work

Legacy model retained for compatibility with older integrations

An updated Lean 4 formal proof engineering model optimised for automated theorem proving and autoformalization. 119B total parameters, 6.5B active.

Mistral reasoning model for transparent analysis, math, and complex decisions

Open vision-language model for efficient local deployment, instruction following, and tool use

Compact open vision-language model for edge deployment, instruction following, and tool use

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

Compact open vision-language model for edge deployment, instruction following, and tool use

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

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

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

Mistral's largest general model for enterprise agents, coding, and multilingual reasoning

Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work

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

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Balanced Mistral model for enterprise assistants, multilingual work, and tools

Balanced Mistral model for enterprise assistants, multilingual work, and tools

Efficient Mistral-NVIDIA open model for multilingual chat and local deployment

Efficient Mistral model for fast chat, extraction, and production assistants

Fast Mistral production model for chat, extraction, and cost-sensitive agents

Efficient Mistral model for fast chat, extraction, and production assistants

Legacy model retained for compatibility with older integrations

Mistral vision-language model for image understanding and multimodal chat

Mistral's larger vision model for document-heavy image understanding and chat

Instruct model with native audio input for speech understanding and tool use

Instruct model with native audio input for speech understanding and tool use

Open flagship GLM for long-horizon coding agents and million-token context work

Flagship GLM model for long-horizon coding, agents, and complex project delivery

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...

Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...

Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...

Automatic model router for matching prompts to suitable backends and budgets

Efficient model for low-latency assistance, extraction, and routine automation

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

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...

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

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

Compact GPT model for low-latency assistance and high-volume workloads

GPT model for general reasoning, writing, coding, and tool-assisted tasks

Compact GPT model for low-latency assistance and high-volume workloads

Long-lived GPT workhorse for coding, instruction following, and production apps

Affordable GPT-4.1 lane for fast coding help and structured extraction

Tiny GPT-4.1 option for classification, routing, and very high-volume tasks

Omni-era GPT for multimodal chat, practical coding, and general assistants

GPT model for general reasoning, writing, coding, and tool-assisted tasks

GPT model for general reasoning, writing, coding, and tool-assisted tasks

GPT model for general reasoning, writing, coding, and tool-assisted tasks

Small omni GPT for cheap multimodal assistance and production-scale traffic

Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows

Small GPT-5 for responsive agents, coding help, and everyday automation

Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs

Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning

Sharper GPT-5 generation for coding, product work, and tool-assisted tasks

Reliable GPT generation for broad coding, writing, and tool-assisted product work

Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows

Coding-optimized GPT model for repository edits, reviews, and agentic software work

Coding-optimized GPT model for repository edits, reviews, and agentic software work

Agent-ready GPT for coding and computer-use workflows at a lower cost

Strong small GPT for coding subagents, quick tool use, and high-volume work

Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation

More exact GPT-5.4 tier for demanding professional reasoning and agent tasks

Default frontier GPT for coding, computer use, research, and knowledge work

Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding

Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows

Cost-efficient GPT-5.6 model for fast, high-volume workloads

Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows

Balanced GPT-5.6 model for capable, cost-efficient everyday work

GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.

OpenAI's most efficient model for focused, high-volume tasks

OpenAI model for complex coding and agentic workflows

Near-Astra performance for complex coding, computer use, and professional work at a lower cost.

Alias for flagship general-purpose models with safeguards for defensive cybersecurity work

Alias for advanced cybersecurity models for authorized vulnerability research and security testing

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

Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior

O-series reasoning model for hard analysis, math, coding, and planning

O-series reasoning model for hard analysis, math, coding, and planning

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

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

High-effort o3 tier for difficult technical reasoning and careful answers

Fast o-series model for compact reasoning, coding, and tool use

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

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

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

Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...

Fast web-grounded Sonar for current answers, citations, and lightweight retrieval

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

Deeper Sonar search model with broader retrieval and stronger synthesis

Web-grounded Sonar for multi-step research questions that need cited reasoning

Poolside's open-weight model for agentic coding and long-horizon work

Agentic coding model from Poolside in the XS size class for local deployment

Agentic coding model from Poolside in the XS size class for local deployment

Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...

Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...

Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...

Quality-first multi-agent model for hard research, analysis, and competitions

Quality-first multi-agent model for hard research, analysis, and competitions

Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows

Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...

Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...

Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...

Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...

SenseNova lightweight multimodal agent model for real-world complex tasks, data analysis, and complex information presentation

StepFun flash model for efficient multimodal reasoning, coding, and tool use

StepFun flash model for efficient multimodal reasoning, coding, and tool use

StepFun flash lane for quick multimodal reasoning and coding assistance

StepFun flash model for efficient multimodal reasoning, coding, and tool use

Newer StepFun flash model for faster agents, coding, and multimodal prompts

StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Automatic model router for matching prompts to suitable backends and budgets

Tencent Hy reasoning model for coding, instruction following, and agent tasks

A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

Efficient model for low-latency assistance, extraction, and routine automation

Upstage's compact, cost-efficient model for agentic use

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

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

Upstage's flagship model, specialized for agentic use

ByteDance Seed model for long-context reasoning, instruction following, and tool-assisted tasks

Low-latency ByteDance Seed model for high-throughput chat, extraction, and lightweight tool use

ByteDance Seed multimodal model for image understanding, visual reasoning, and tool-assisted tasks

ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows

ByteDance Seed coding model for multimodal software engineering and long-running agents

Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation

Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks

Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows

Flagship ByteDance Seed 2.1 model for complex multimodal reasoning, coding, and agents

Faster ByteDance Seed 2.1 model for multimodal reasoning and latency-sensitive agent workflows

ByteDance Seed model optimized for character-driven dialogue and consistent conversational behavior

Rolling ByteDance Seed model for rapidly updated reasoning, coding, and agent capabilities

Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation

Faster ByteDance Seed 2.1 model for multimodal reasoning and latency-sensitive agent workflows

Legacy model retained for compatibility with older integrations

Legacy model retained for compatibility with older integrations

Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks

Open MiMo model for multimodal coding agents and long-context automation

Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution

MiMo pro model for strong multimodal reasoning and agent execution

MiMo Flash model for multimodal coding agents and long-context automation

MiMo Pro model for multimodal coding agents and long-context automation

MiMo pro model for strong multimodal reasoning and agent execution

Speech generation model for controllable voice, narration, and audio delivery

Speech generation model for controllable voice, narration, and audio delivery

Speech generation model for controllable voice, narration, and audio delivery

Speech generation model for controllable voice, narration, and audio delivery

Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token...

Hybrid-reasoning GLM release that made the 4.5 line broadly useful

Lighter GLM-4.5 variant for fast coding assistance and cheaper agents

Efficient GLM model for fast reasoning, coding, and agent workflows

GLM vision model for visual reasoning, documents, and multimodal agents

Late GLM-4 workhorse for coding agents, reasoning, and structured tasks

GLM vision model for visual reasoning, documents, and multimodal agents

Lightweight GLM vision model for visual reasoning, documents, and multimodal agents

Mature GLM model for dependable coding, reasoning, and structured agent tasks

Budget GLM lane for fast coding help, routing, and everyday automation

Efficient GLM model for fast reasoning, coding, and agent workflows

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

Faster GLM-5 lane for coding agents that need lower latency

Strong GLM coding model for agentic engineering, terminals, and repository generation

Open flagship GLM for long-horizon coding agents and million-token context work

Flagship GLM model for long-horizon coding, agents, and complex project delivery

Native multimodal GLM model for efficient coding and long-horizon agent tasks

High-speed GLM-5.3-Flash serving option for coding and agent workflows

Fast GLM vision model for screenshots, documents, and multimodal agent tasks

GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...

Open flagship GLM for long-horizon coding agents and million-token context work

Flagship GLM model for long-horizon coding, agents, and complex project delivery

Grok model for agentic tool use, reasoning, coding, and live assistance

Reasoning Grok for document-heavy analysis and long-horizon tool use

Grok model for agentic tool use, reasoning, coding, and live assistance

xAI's Grok for chat, coding, agentic tools, and lower hallucination risk

xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

xAI's frontier model for long-running agents, coding, knowledge work, and visual projects

Fast Grok coding model tuned for agentic engineering and iterative edits