실제 사용량으로 순위를 매긴 최고의 코딩용 AI 모델

모델 순위가 실제 사용 데이터를 기반으로 업데이트되었습니다.

이 코딩 컬렉션의 모델 순위는 최근 7일 동안 OpenRouter API를 통해 처리된 프롬프트 및 완성 토큰의 총수를 기준으로 매겨집니다. 상위 10개 모델을 표시합니다. 순위는 OpenRouter에서의 사용량을 측정하고 도입 현황을 반영하며, 모델 품질이나 벤치마크 성능을 나타내지 않습니다.

아래의 코딩용 최고 AI 모델 순위는 벤치마크 점수가 아니라 지난 일주일 동안 개발자들이 OpenRouter에서 실제로 사용한 양을 기준으로 매겨집니다. 현재 최상위 모델은 DeepSeek V4.1 Flash 1017, Hy4 flash 및 DeepSeek V4.1 Flash입니다. 각 목록에는 OpenRouter에서 정보를 보유한 경우 모델의 컨텍스트 길이와 요금이 표시되므로, 모델을 선택하기 전에 사용량 대비 비용을 비교할 수 있습니다. 모든 모델을 하나의 OpenRouter API 키로 사용할 수 있으므로, 자체 코드베이스에서 테스트하고 연동 코드를 다시 작성하지 않고도 모델을 전환할 수 있습니다.

소프트웨어 및 기술 LLM 리더보드

6.
5.0%
7.
4.6%
8.
z-ai의 파비콘
GLM 5.3
제작: z-ai
4.4%
10.
38.0%

OpenRouter의 상위 코딩 모델

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp.

It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.

제작: deepseek1.05M 컨텍스트US$0.036/M 입력 US$0.50/M 출력
tencent의 파비콘

Tencent: Hy4 flash

67.6T개 토큰

Hy4 flash is a cost-efficient variant of Hy4 from Tencent, served with roughly a quarter of the flagship's parameter count for lower latency and cost. It targets code assistance, agent pipelines, document and chart comprehension, and high-volume routine automation, with the same context and output limits as Hy4.

제작: tencent1.05M 컨텍스트US$0.035/M 입력 US$0.1405/M 출력 50% off

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp.

It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.

제작: deepseek1.05M 컨텍스트US$0.0507/M 입력 US$0.2028/M 출력 83% off
tencent의 파비콘

Tencent: Hy4

14.4T개 토큰

The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity tasks. It also introduces visual understanding for the first time.

제작: tencent1.05M 컨텍스트US$0.417/M 입력 US$1.251/M 출력 50% off
z-ai의 파비콘

Z.ai: GLM 5.3 Flash

12T개 토큰

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.

제작: z-ai1.05M 컨텍스트US$0.0399/M 입력 US$0.0784/M 출력
openai의 파비콘

OpenAI: GPT-6 Luna

9.89T개 토큰

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

제작: openai1.05M 컨텍스트US$0.10/M 입력 US$0.50/M 출력

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.

The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.

제작: anthropic1M 컨텍스트US$4/M 입력 US$20/M 출력
stepfun의 파비콘

StepFun: Step 5 Preview

6.71T개 토큰

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional knowledge work, with particular strength in finance.

It is designed for extended tasks that span large codebases and documents, using tools and refining results over multiple steps.

제작: stepfun1M 컨텍스트US$1/M 입력 US$2.70/M 출력
xiaomi의 파비콘

Xiaomi: MiMo-V2.6-Flash

4.54T개 토큰

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for greater computational efficiency. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers strong performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.

제작: xiaomi1.05M 컨텍스트US$0.10/M 입력 US$0.28/M 출력

MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex, multi-step co-work automation, understanding real codebases, fixing bugs, and building features, and visual understanding and creation, including frontend and presentation creation. It is an open-weight mixture-of-experts model with 23B active / 428B total parameters.

제작: minimax1.05M 컨텍스트US$0.075/M 입력 US$0.30/M 출력

더 많은 컬렉션 살펴보기