OpenRouter의 무료 AI 모델
모델 순위가 실제 사용 데이터를 기반으로 업데이트되었습니다.
모델 순위는 최근 7일 동안 OpenRouter API를 통해 처리된 프롬프트 및 완성 토큰의 총수에 따라 결정됩니다. 상위 16개 모델을 표시합니다. 순위는 OpenRouter에서의 사용량을 측정하고 도입 현황을 반영하며, 모델 품질이나 벤치마크 성능을 나타내지 않습니다.
아래는 지난 일주일간 OpenRouter의 실제 사용량을 기준으로 가장 많이 사용된 무료 AI 모델의 순위이며, 모든 모델의 프롬프트 가격은 $0입니다. 현재 최상위 모델은 Nemotron 3 Ultra (free), Nemotron 3.5 Super VL (free) 및 ERNIE-5.5-Flash-Preview (free)입니다. 무료 모델을 사용하면 거의 예산 없이 프로토타입을 만들고, 학습하고, 사이드 프로젝트를 운영할 수 있으며, OpenRouter는 제공업체를 온보딩하고 비용을 직접 부담하여 무료 용량을 계속 확대하고 있습니다. 직접 선택하고 싶지 않다면 openrouter/free가 각 요청을 그에 맞는 무료 모델로 라우팅합니다.
OpenRouter의 인기 무료 모델
NVIDIA: Nemotron 3 Ultra (free)
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.
NVIDIA: Nemotron 3.5 Super VL (free)
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.
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.
Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second Inkling generation. It was trained with reinforcement learning on long-horizon coding tasks across many agent harnesses, and is suited for agentic coding, autonomous research, agentic knowledge work and retrieval-augmented generation, with English and general multilingual support. It accepts text and image input (no audio), supports tool calling and variable reasoning effort, and has a 1M-token context window.
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.
Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is suited for reasoning, coding, multimodal understanding, long-context processing, and multi-step agent workflows.
Particle AI: Particle-1 (free)
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.

Cohere: North Mini Code (free)
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized for code generation, agentic software engineering, and terminal tasks, and is trained to generalize across agent harnesses such as OpenCode and SWE-Agent.
It offers a 256K-token context window with up to 64K tokens of output, supports interleaved reasoning and tool use via JSON schema, and is released open-weight under the Apache 2.0 license. Its small active-parameter footprint enables low-latency inference, including on local hardware.
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.
Recursive: Flint (free)
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.

Perplexity: Decider V1.3 (free)
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.
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.

LiquidAI: LFM3-1.7B (free)
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.
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.
Respan: Span-01 Lite
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.
자주 묻는 질문
예. 이 페이지의 모든 모델은 모델 가격이 $0이므로 사용 요금이 청구되지 않습니다. ID가 :free로 끝나는 무료 변형 모델은 크레딧 구매가 필요하지 않지만, 다른 $0 모델은 잔액이 있는 계정이 필요할 수 있습니다. 무료 사용에는 요청 속도 제한이 적용됩니다.
ID가 :free로 끝나는 무료 버전은 분당 20회, 하루 50회의 요청으로 제한되며, 계정에서 $10의 크레딧을 구매하면 하루 1,000회로 늘어납니다(충전 수수료를 감안하여 더 높은 한도는 $9부터 적용됩니다). 실패한 시도도 일일 한도에 포함됩니다. 다른 $0 모델에는 이러한 한도가 적용되지 않지만 OpenRouter 또는 제공업체가 설정한 모델별 한도에 도달할 수 있습니다. 속도 제한 문서를 참조하십시오.
채팅 모델의 경우 유료 모델에 사용하는 것과 동일한 OpenAI 호환 Chat Completions 엔드포인트로 요청을 보내되, model 필드에 무료 모델 ID를 지정하십시오. 다른 모델 유형은 재순위 모델의 /api/v1/rerank 및 의사결정 모델의 /api/alpha/decisions와 같이 자체 API를 사용하므로, 모델 페이지에서 올바른 엔드포인트를 확인하십시오. 유료 모델의 무료 버전은 :free로 끝납니다.
예. 모델을 openrouter/free로 설정하면 각 요청이 그에 맞는 무료 모델로 라우팅되므로 현재 어떤 무료 모델을 사용할 수 있는지 확인할 필요가 없습니다.
아닙니다. OpenRouter API 키 하나로 무료 모델과 유료 모델을 모두 사용할 수 있으므로, API 키 페이지에서 키를 만들고 모든 모델에서 재사용하십시오.
