모델을 불러오고 있습니다…
모델을 불러오고 있습니다…
스토리텔링·감정 이해·언어별 벤치마크를 오각형으로 비교합니다.
시스템 프롬프트와 대사를 직접 바꾸며 캐릭터의 말투와 관계를 실험하고, 완성한 프롬프트를 내려받으세요.
프롬프트 실험하기 →코드 작성, 리뷰와 도구 호출에 맞는 텍스트 모델을 검색하고 가격과 지원 기능을 비교하세요.
코딩 모델 보기 →텍스트와 참고 이미지·영상으로 캐릭터 영상과 숏폼을 만드는 방법과 API 요청 형식을 확인하세요.
Seedance 2.5 열기 →캐릭터 이미지 생성, 스타일 변환과 편집에 맞는 도구를 골라 바로 사용하세요.
실제 대화·소설 응답이 공개된 모델을 먼저 보여드립니다. 모델 카드에서 예시를 무료로 바로 읽어보세요.
총 269개 중 181–210개
텍스트와 참고 이미지를 활용한 이미지 생성·편집 모델입니다.
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...
텍스트와 참고 이미지를 활용한 이미지 생성 모델입니다.
Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.
GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...
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%...
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.
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...
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...
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,...
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...
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...
Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...
Alibaba Cloud에서 직접 제공하는 Qwen 텍스트 모델입니다.
Alibaba Cloud에서 직접 제공하는 Qwen 텍스트 모델입니다.
캐릭터의 설정과 대화 흐름을 유지하는 역할극 전용 Qwen 모델입니다.
캐릭터의 설정과 대화 흐름을 유지하는 역할극 전용 Qwen 모델입니다.
Alibaba Cloud에서 직접 제공하는 Qwen 텍스트 모델입니다.
Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...
GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...
OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...
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...
o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....
The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...
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...
Google의 영상 생성 모델입니다. 텍스트와 이미지로 오디오를 포함한 4~8초 영상을 생성하며 최대 4K 출력을 지원합니다.
빠른 영상 제작을 위한 Google Veo 모델입니다. 텍스트와 이미지로 오디오를 포함한 4~8초 영상을 생성하며 최대 4K 출력을 지원합니다.
반복적인 영상 제작에 적합한 경제적인 Google Veo 모델입니다. 텍스트와 이미지로 오디오를 포함한 4~8초 영상을 생성하며 최대 1080p 출력을 지원합니다.
Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...