AI Models

Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4...

GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5ミニ](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, 書類, and temporal sequences. It integrates enhanced multimodal alignment and...

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, 画像, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...

[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, コードの品質, and user experience while incorporating GPT Image 1's superior instruction following,...

o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.

o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.

Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, コード, 科学, and...

ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model, refined to boost reasoning depth and quality for top-tier performance in logical puzzles, 数学, 科学, コーディング, text generation, and expert-level academic benchmarks.

ジェミニ 2.5 Flash Image, 別名. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...

Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, 数学, and complex tasks. It excels...

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...

GPT-5 Pro is OpenAI’s most advanced model, 推論に大きな改善をもたらす, コードの品質, ユーザーエクスペリエンスと. 段階的な推論を必要とする複雑なタスク向けに最適化されています。, instruction following, and...

Compared with GLM-4.5, this generation 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...

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. DeepSeek スパース アテンションを導入します (DSA), a fine-grained sparse attention mechanism...

Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...

ジェミニ 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 家族, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...

Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...

Qwen3-Max is an updated release built on the Qwen3 series, 推論に大きな改善をもたらす, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 バージョン. It...

Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...

GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. インタラクティブな開発セッションと長時間の開発セッションの両方向けに設計されています。, independent execution of complex engineering tasks....

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-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...

Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billion per token. It's optimized for long-horizon, deep information-seeking tasks...

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, コード生成, knowledge QA, and multilingual...

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, コード生成, knowledge QA, and multilingual...

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (教育省) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...

Hermes 4 70B は、Nous Research のハイブリッド推論モデルです。, Meta-Llama-3.1-70B に基づいて構築. より大型の 405B リリースと同じハイブリッド モードが導入されています, allowing the model to either...

Hermes 4 Meta-Llama-3.1-405B に基づいて構築され、Nous Research によってリリースされた大規模推論モデルです。. ハイブリッド推論モードを導入します, where the model can choose to deliberate internally with...

DeepSeek-V3.1 は大規模なハイブリッド推論モデルです (671Bパラメータ, 37Bアクティブ) プロンプトテンプレートを介して思考モードと非思考モードの両方をサポートします. It extends the DeepSeek-V3 base with a two-phase long-context...

gpt-4o-audio-preview モデルは、プロンプトとしてのオーディオ入力のサポートを追加します。. この機能強化により、モデルは音声録音内のニュアンスを検出し、生成されるユーザー エクスペリエンスに深みを加えることができます。. Audio outputs...

Mistral Medium 3.1 Mistral Medium の更新バージョンです 3, これは、大幅に削減された運用コストでフロンティアレベルの機能を提供するように設計された、高性能のエンタープライズグレードの言語モデルです。. It balances...

洗練されたテキストベースの専門家の混合 (教育省) 合計 21B のパラメータを備えたモデル (トークンごとに 3B が有効), 異種 MoE 構造とモダリティ分離ルーティングを通じて、優れたマルチモーダルの理解と生成を実現します。. Supporting an...

強力なマルチモーダル専門家混合チャット モデル。合計 280 億のパラメーターを備え、トークンごとに 30 億がアクティブ化されます。, delivering exceptional text and vision understanding through its innovative heterogeneous MoE structure with modality-isolated routing....

GLM-4.5V は、マルチモーダル エージェント アプリケーション向けのビジョン言語基盤モデルです。. 専門家の混合に基づいて構築 (教育省) 106B パラメータと 12B アクティブ化パラメータを備えたアーキテクチャ, ビデオ理解において最先端の結果を達成します,...

Jamba Large 1.7 Jamba オープンファミリーの最新モデルです, 接地性を向上させる, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 256K context...

GPT-5 チャットは上級者向けに設計されています, 自然, マルチモーダル, エンタープライズアプリケーション向けのコンテキスト認識型の会話.

GPT-5はOpenAIの最も先進的なモデルです, 推論に大きな改善をもたらす, コードの品質, ユーザーエクスペリエンスと. 段階的な推論を必要とする複雑なタスク向けに最適化されています。, instruction following, and accuracy...

GPT-5 MiniはGPT-5のコンパクト版です。, 軽量の推論タスクを処理するように設計されています. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

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. While limited in reasoning depth compared to its larger...