모델 탐색

실제 OpenRouter 사용, 프로덕션 성능 및 독립적인 벤치마크를 기반으로 한 실용적인 출발점입니다.

전체 624 개 모델 보기
오늘의 프런티어

Claude Fable 5.2 프런티어 선두 등극

Anthropic이 Artificial Analysis 지능 지수에서 Google을 5점 차로 근소하게 앞서고 있습니다.

모델지능(0–100)

Auto is OpenRouter’s flagship model router, built for general-purpose usage. It adapts to each request, choosing cost-optimal models and adjusting reasoning effort. It balances task difficulty, benchmark results, live prices, and prompt caching. Use it for apps, chat, and general agents. For agent sessions, it follows progress across turns, keeps the same model while work is going well, and adjusts reasoning effort or switches models when the task gets stuck. It respects all your governance settings, including guardrails, ZDR, and budgets.

Auto Code is OpenRouter’s router built specifically for coding agents and harnesses. It uses the same routing engine as the [Auto Router](https://dynamicsinfo.com/openrouter/auto), with every request treated as part of an agent session and model choices guided by coding-task pass rate, completion time, and cost per solved task. It follows edits, test results, and recurring errors across turns, keeping the model while work is going well and trying more reasoning effort before switching when trouble persists. Its default coding tier starts from stronger models and weighs failed code changes more heavily. Your model and provider restrictions still apply.

The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta quality. When new improvements are proven in auto-beta, we graduate them to the auto router. We've love to hear your feedback on whether auto-beta is working for you, or requests for routing improvements. To see which model was used, visit [Activity](/activity), or read the `model` attribute of the response. Your response will be priced at the same rate as the routed model. Learn more, including how to customize the models for routing, in our [docs](/docs/guides/routing/routers/auto-router).

Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a judge model synthesizes their responses into a structured analysis — consensus, contradictions, partial coverage, unique insights, and blind spots — and writes the final answer from it. By default the panel is the `Quality` preset; switch to `Budget` for cheaper members, or override the panel and judge entirely with the fusion plugin's `analysis_models` and `model` fields. Reach for Fusion when a single model isn't enough — research, expert critique, or anywhere the cost of being wrong outweighs a few extra completions. Because Fusion runs every panel member plus a judge call, your request is priced as the sum of those underlying completions rather than a single model. To see which models ran, visit [Activity](/activity). Note: Context limits are dependent on which models you select. Learn more in our [docs](/docs/guides/features/plugins/fusion). For another way to route, see the [Auto Router](/openrouter/auto).

The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://dynamicsinfo.com/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how strong a coder you need; higher scores select stronger (and typically more expensive) models. If you omit min_coding_score, the router defaults to the High tier. Selecting Nitro from the variant dropdown ranks the models in your tier by measured throughput and routes each request to the fastest one, so you trade some model variety for lower latency. Read the [Pareto Router docs](https://dynamicsinfo.com/docs/guides/routing/routers/pareto-router) for the full selection logic, fallback behavior, and how to customize routing. For another way to route, see the [Auto Router](/openrouter/auto).

가성비 상위 모델

정가 기준 달러당 가장 높은 성능.

순위모델지능 백분위코딩 백분위에이전트 백분위수토큰
1
z-ai의 파비콘
GLM 5.3 Flash
40799111.9T
2
deepseek의 파비콘
DeepSeek V4 Flash 0731 (batch)
–757382.5M
3
inclusionai의 파비콘
Ling 3.0 Flash VL
–60576B
4
anthropic의 파비콘
Claude Haiku 5.5 (batch)
65––30.4B
5
deepseek의 파비콘
DeepSeek V4 Flash 0423
–59542.2T

가장 빠른 모델

여러 제공업체에 걸쳐 가장 높은 출력 속도 중앙값.

순위모델처리량TTFT p50제공업체
1
qwen의 파비콘
Qwen3.8 27B
883 tok/s253ms23
2
openai의 파비콘
gpt-oss-120b
832 tok/s138ms26
3
deepseek의 파비콘
DeepSeek V4.1 Flash 1017
492 tok/s209ms48
4
meta-llama의 파비콘
Llama 3.1 8B Instruct
470 tok/s143ms4
5
openai의 파비콘
gpt-oss-20b
423 tok/s117ms12

항상 최신 버전을 가리키는 별칭

모델 ID 하나를 고정하면 해당 제품군의 최신 릴리스를 항상 사용할 수 있습니다.

순위모델모델 계열 토큰컨텍스트
1
perplexity의 파비콘
Decider Flash Latest
32.5B262K
2
anthropic의 파비콘
Claude Fable Latest
1T1M
3
google의 파비콘
Gemini Flash Latest
4.1T1M
4
z-ai의 파비콘
GLM Latest
5.1T1M
5
liquid의 파비콘
d1-ultra Latest
44.1B33K

무료 모델

무료 엔드포인트가 있는 모델 중 가장 많이 사용되는 모델입니다.

순위모델토큰/주컨텍스트
1
nvidia의 파비콘
Nemotron 3 Ultra (free)
3.2T1M
2
nvidia의 파비콘
Nemotron 3.5 Super VL (free)
3T1M
3
baidu의 파비콘
ERNIE-5.5-Flash-Preview (free)
1.9T1M
4
nvidia의 파비콘
Nemotron 3.5 Lightning (free)
1.2T1M
5
thinkingmachines의 파비콘
Inkling 2 Small (free)
1.1T1M

이미지 모델

주요 모델 제공업체의 모델로 이미지를 생성하고 편집합니다.

모두 보기

동영상 모델

주요 모델 제공업체의 모델을 통해 텍스트 및 이미지 프롬프트로 동영상을 생성하십시오.

모두 보기

모든 모달리티 살펴보기

수행할 작업에 맞춰 엄선된 모델로 시작하십시오.

모든 모델 둘러보기모델 페이지에서 전체 카탈로그를 검색, 필터링, 정렬하고 비교하십시오.
전체 624 개 모델 보기