視覚機能を備えた AI モデル:画像理解のためのマルチモーダル LLM

モデルランキングは に実際の利用データに基づいて更新されました。

モデルは、直近 7 日間に OpenRouter API を通じて処理されたプロンプトと補完の合計トークン数で順位付けされます。 上位 10 個のモデルを表示しています。 ランキングは OpenRouter での使用状況を測定し、モデルの品質やベンチマーク性能ではなく、採用状況を反映しています。

ビジョンモデルは、テキストとともに画像の分析、文書の読み取り、グラフの解釈、視覚コンテンツに関する質問への回答を行うマルチモーダル LLM です。このコレクションでは、過去一週間の OpenRouter での使用量に基づいて、視覚機能を備えたモデルをランキングしています。 現在のトップモデルは DeepSeek V4.1 Flash 1017、Hy4 flash、DeepSeek V4.1 Flash です。 単一の API を通じて Anthropic、Google、OpenAI などのプロバイダーのモデルにアクセスし、コンテキスト長、料金、機能を比較できます。

OpenRouter の上位画像認識モデル

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 from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp.

It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.

作成者: deepseek1.05M コンテキスト$0.036/M 入力 $0.50/M 出力
tencent のファビコン

Tencent: Hy4 flash

67.6T トークン

Hy4 flash is a cost-efficient variant of Hy4 from Tencent, served with roughly a quarter of the flagship's parameter count for lower latency and cost. It targets code assistance, agent pipelines, document and chart comprehension, and high-volume routine automation, with the same context and output limits as Hy4.

作成者: tencent1.05M コンテキスト$0.035/M 入力 $0.1405/M 出力 50% off

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 output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp.

It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.

作成者: deepseek1.05M コンテキスト$0.0507/M 入力 $0.2028/M 出力 83% off
tencent のファビコン

Tencent: Hy4

14.4T トークン

The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity tasks. It also introduces visual understanding for the first time.

作成者: tencent1.05M コンテキスト$0.417/M 入力 $1.251/M 出力 50% off
z-ai のファビコン

Z.ai: GLM 5.3 Flash

12T トークン

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

作成者: z-ai1.05M コンテキスト$0.0399/M 入力 $0.0784/M 出力
openai のファビコン

OpenAI: GPT-6 Luna

9.89T トークン

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

作成者: openai1.05M コンテキスト$0.10/M 入力 $0.50/M 出力
anthropic のファビコン

Anthropic: Claude Opus 5.5

8.43T トークン

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.

The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.

作成者: anthropic1M コンテキスト$4/M 入力 $20/M 出力
stepfun のファビコン

StepFun: Step 5 Preview

6.71T トークン

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional knowledge work, with particular strength in finance.

It is designed for extended tasks that span large codebases and documents, using tools and refining results over multiple steps.

作成者: stepfun1M コンテキスト$1/M 入力 $2.70/M 出力
xiaomi のファビコン

Xiaomi: MiMo-V2.6-Flash

4.54T トークン

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for greater computational efficiency. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers strong performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.

作成者: xiaomi1.05M コンテキスト$0.10/M 入力 $0.28/M 出力
minimax のファビコン

MiniMax: MiniMax M3.1 Flash

4.2T トークン

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex, multi-step co-work automation, understanding real codebases, fixing bugs, and building features, and visual understanding and creation, including frontend and presentation creation. It is an open-weight mixture-of-experts model with 23B active / 428B total parameters.

作成者: minimax1.05M コンテキスト$0.075/M 入力 $0.30/M 出力

よくある質問

その他のコレクションを見る