MODEL RADAR · OPENROUTER
AI 모델을 같은 기준으로 비교하세요.
OpenRouter에 현재 공개된 모든 모델의 모달리티, 컨텍스트, 가격, 설정, 제공업체 정보를 한곳에서 비교할 수 있습니다.
- 카탈로그 범위
- 전체 공개 모델
- 개 모델
- 631
- 개 제공업체
- 86
- 마지막 동기화
- 2026. 9. 29.
openaiOpenAI: GPT-5.2 Pro (batch)
GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...
- 컨텍스트
- 400K
- 입력
- image · text · file
- 출력
- text
openaiOpenAI: GPT-5.2
GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...
- 컨텍스트
- 400K
- 입력
- file · image · text
- 출력
- text
openaiOpenAI: GPT-5.2 (batch)
GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...
- 컨텍스트
- 400K
- 입력
- file · image · text
- 출력
- text
mistralaiMistral: Devstral 2 2512
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...
- 컨텍스트
- 262K
- 입력
- text · file
- 출력
- text
relaceRelace: Relace Search
The relace-search model uses 4-12 viewfile and grep tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...
- 컨텍스트
- 256K
- 입력
- text
- 출력
- text
z-aiZ.ai: GLM 4.6V
GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...
- 컨텍스트
- 131K
- 입력
- image · text · video
- 출력
- text
openrouterBody Builder (beta)
Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...
- 컨텍스트
- 128K
- 입력
- text
- 출력
- text
openaiOpenAI: GPT-5.1-Codex-Max
GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...
- 컨텍스트
- 400K
- 입력
- text · image
- 출력
- text
amazonAmazon: Nova 2 Lite
Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...
- 컨텍스트
- 1M
- 입력
- text · image · video · file
- 출력
- text
mistralaiMistral: Ministral 3 14B 2512
The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...
- 컨텍스트
- 262K
- 입력
- text · image
- 출력
- text
mistralaiMistral: Ministral 3 8B 2512
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
- 컨텍스트
- 262K
- 입력
- text · image
- 출력
- text
mistralaiMistral: Ministral 3 8B 2512 (batch)
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
- 컨텍스트
- 262K
- 입력
- text · image
- 출력
- text
mistralaiMistral: Ministral 3 3B 2512
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
- 컨텍스트
- 131K
- 입력
- text · image
- 출력
- text
mistralaiMistral: Mistral Large 3 2512
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
- 컨텍스트
- 262K
- 입력
- text · image · file
- 출력
- text
mistralaiMistral: Mistral Large 3 2512 (batch)
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
- 컨텍스트
- 262K
- 입력
- text · image · file
- 출력
- text
deepseekDeepSeek: DeepSeek V3.2
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
- 컨텍스트
- 164K
- 입력
- text
- 출력
- text
black-forest-labsBlack Forest Labs: FLUX.2 Flex
FLUX.2 [flex] excels at rendering complex text, typography, and fine details, and supports multi-reference editing in the same unified architecture. Pricing is as follows, per the docs: We charge $0.06...
- 컨텍스트
- 67K
- 입력
- text · image
- 출력
- image
black-forest-labsBlack Forest Labs: FLUX.2 Pro
A high-end image generation and editing model focused on frontier-level visual quality and reliability. It delivers strong prompt adherence, stable lighting, sharp textures, and consistent character/style reproduction across multi-reference inputs....
- 컨텍스트
- 47K
- 입력
- text · image
- 출력
- image
anthropicAnthropic: Claude Opus 4.5
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
- 컨텍스트
- 200K
- 입력
- file · image · text
- 출력
- text
anthropicAnthropic: Claude Opus 4.5 (batch)
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
- 컨텍스트
- 200K
- 입력
- file · image · text
- 출력
- text
googleGoogle: Nano Banana Pro (Gemini 3 Pro Image Preview)
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...
- 컨텍스트
- 66K
- 입력
- image · text
- 출력
- image · text
thenlperThenlper: GTE-Base
The gte-base embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, delivering efficient and effective semantic embeddings optimized for textual similarity, semantic search, and clustering applications.
- 컨텍스트
- 1K
- 입력
- text
- 출력
- embeddings
thenlperThenlper: GTE-Large
The gte-large embedding model converts English sentences, paragraphs and moderate-length documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for information retrieval, semantic textual similarity, reranking and...
- 컨텍스트
- 1K
- 입력
- text
- 출력
- embeddings
intfloatIntfloat: E5-Large-v2
The e5-large-v2 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-accuracy semantic embeddings optimized for retrieval, semantic search, reranking, and similarity-scoring tasks.
- 컨텍스트
- 1K
- 입력
- text
- 출력
- embeddings