1. 사용 시나리오
입력 토큰보내는 텍스트 양
출력 토큰AI가 생성하는 응답 양
추론 토큰
AI가 생각하는 과정 (일부 모델만 지원)API 횟수총 요청 횟수
프롬프트 캐시반복 요청 시 입력의 80%를 재사용하여 비용 절감
속도 표시
프롬프트 직접 입력 (선택사항)
2. 비용 시뮬레이션
| 모델 | 총 최소 | 총 최대 | 총 최소~총 최대 | 단가 |
|---|---|---|---|---|
 GPT OSS 120B | $1.30 | $2.17 | $1.30~2.17 | $0.039/1M |
 Llama 4 Scout | $1.32 | $2.76 | $1.32~2.76 | $0.080/1M |
 Nemotron 3 Nano 30B A3B | $1.47 | $2.43 | $1.47~2.43 | $0.050/1M |
 DeepSeek V4 Flash | $1.59 | $2.54 | $1.59~2.54 | $0.098/1M |
 MiMo V2.5 | $2.27 | $3.61 | $2.27~3.61 | $0.140/1M |
Llama 4 Maverick | $2.61 | $5.49 | $2.61~5.49 | $0.150/1M |
 Gemma 4 31B | $2.74 | $4.46 | $2.74~4.46 | $0.120/1M |
GPT-5 Nano | $2.79 | $4.71 | $2.79~4.71 | $0.050/1M |
 Dola Seed 2.0 mini | $2.94 | $4.86 | $2.94~4.86 | $0.100/1M |
Gemini 2.5 Flash Lite | $2.94 | $4.86 | $2.94~4.86 | $0.100/1M |
DeepSeek V3.2 | $2.95 | $4.60 | $2.95~4.60 | $0.229/1M |
Nemotron 3 Super | $3.24 | $5.40 | $3.24~5.40 | $0.090/1M |
 Longcat Flash Chat | $3.48 | $7.32 | $3.48~7.32 | $0.200/1M |
 Grok 4.1 Fast (Reasoning) | $3.90 | $6.30 | $3.90~6.30 | $0.200/1M |
 Mistral Small 4 | $4.41 | $7.29 | $4.41~7.29 | $0.150/1M |
 K-EXAONE | $5.88 | $9.72 | $5.88~9.72 | $0.200/1M |
 Trinity Large Thinking | $6.27 | $10.35 | $6.27~10.35 | $0.220/1M |
DeepSeek V4 Pro | $7.05 | $11.22 | $7.05~11.22 | $0.435/1M |
MiMo V2.5 Pro | $7.05 | $11.22 | $7.05~11.22 | $0.435/1M |
 Qwen3.6 Flash | $7.99 | $13.39 | $7.99~13.39 | $0.188/1M |
 MiniMax M2.5 | $8.04 | $13.56 | $8.04~13.56 | $0.150/1M |
 ERNIE 4.5 300B A47B | $8.10 | $13.38 | $8.10~13.38 | $0.280/1M |
MiniMax M2.7 | $8.82 | $14.58 | $8.82~14.58 | $0.300/1M |
MiniMax M3 | $8.82 | $14.58 | $8.82~14.58 | $0.300/1M |
GPT-5.4 Nano | $8.85 | $14.85 | $8.85~14.85 | $0.200/1M |
Gemini 3.1 Flash Lite | $10.65 | $17.85 | $10.65~17.85 | $0.250/1M |
Grok 4.20 | $12.75 | $24.75 | $12.75~24.75 | $1.25/1M |
 Kimi K2.5 | $13.74 | $22.86 | $13.74~22.86 | $0.400/1M |
Qwen3.6 Plus | $13.84 | $23.20 | $13.84~23.20 | $0.325/1M |
Dola Seed 2.0 Lite | $13.95 | $23.55 | $13.95~23.55 | $0.250/1M |
GPT-5 Mini | $13.95 | $23.55 | $13.95~23.55 | $0.250/1M |
 GLM-5 | $14.47 | $23.69 | $14.47~23.69 | $0.600/1M |
Qwen3.5 397B A17B | $16.61 | $27.85 | $16.61~27.85 | $0.390/1M |
Gemini 2.5 Flash | $17.40 | $29.40 | $17.40~29.40 | $0.300/1M |
 Nova 2 Lite | $17.40 | $29.40 | $17.40~29.40 | $0.300/1M |
Grok 4.20 (Reasoning) | $20.25 | $32.25 | $20.25~32.25 | $1.25/1M |
Grok 4.3 | $20.25 | $32.25 | $20.25~32.25 | $1.25/1M |
Dola Seed 2.0 Pro | $21.30 | $35.70 | $21.30~35.70 | $0.500/1M |
Gemini 3 Flash | $21.30 | $35.70 | $21.30~35.70 | $0.500/1M |
GLM-5.1 | $23.27 | $38.05 | $23.27~38.05 | $0.980/1M |
Kimi K2.6 | $24.62 | $41.04 | $24.62~41.04 | $0.684/1M |
GLM 5V Turbo | $30.00 | $49.20 | $30.00~49.20 | $1.20/1M |
GPT-5.4 Mini | $31.95 | $53.55 | $31.95~53.55 | $0.750/1M |
GPT-4.1 | $34.80 | $73.20 | $34.80~73.20 | $2.00/1M |
 Claude Haiku 4.5 | $36.00 | $60.00 | $36.00~60.00 | $1.00/1M |
Qwen3.6 Max | $44.30 | $74.26 | $44.30~74.26 | $1.04/1M |
Mistral Medium 3.5 | $54.00 | $90.00 | $54.00~90.00 | $1.50/1M |
Gemini 3.5 Flash | $63.90 | $107.10 | $63.90~107.10 | $1.50/1M |
Gemini 2.5 Pro | $69.75 | $117.75 | $69.75~117.75 | $1.25/1M |
GPT-5 | $69.75 | $117.75 | $69.75~117.75 | $1.25/1M |
Gemini 3.1 Pro | $85.20 | $142.80 | $85.20~142.80 | $2.00/1M |
GPT-5.4 | $106.50 | $178.50 | $106.50~178.50 | $2.50/1M |
Claude Sonnet 4 | $108.00 | $180.00 | $108.00~180.00 | $3.00/1M |
Claude Sonnet 4.5 | $108.00 | $180.00 | $108.00~180.00 | $3.00/1M |
Claude Sonnet 4.6 | $108.00 | $180.00 | $108.00~180.00 | $3.00/1M |
Claude Opus 4.5 | $180.00 | $300.00 | $180.00~300.00 | $5.00/1M |
Claude Opus 4.6 | $180.00 | $300.00 | $180.00~300.00 | $5.00/1M |
Claude Opus 4.7 | $180.00 | $300.00 | $180.00~300.00 | $5.00/1M |
Claude Opus 4.8 | $180.00 | $300.00 | $180.00~300.00 | $5.00/1M |
GPT-5.5 | $213.00 | $357.00 | $213.00~357.00 | $5.00/1M |
Claude Opus 4 | $540.00 | $900.00 | $540.00~900.00 | $15.00/1M |
Claude Opus 4.1 | $540.00 | $900.00 | $540.00~900.00 | $15.00/1M |
GPT-5.4 Pro | $1278.00 | $2142.00 | $1278.00~2142.00 | $30.00/1M |
GPT-5.5 Pro | $1278.00 | $2142.00 | $1278.00~2142.00 | $30.00/1M |
4. 시뮬레이션 요약
최저 비용 모델
GPT OSS 120B
$1.30 /3,000회
최고 성능 모델
Claude Opus 4.8
$180.00 /3,000회
산출 기준
입력 토큰: 1,000
출력 토큰: 1,200 ~ 2,800 (±40%)
추론 토큰: 1,000
사용량: 3,000 회
토큰 프리셋은 시나리오별 통계적 평균값입니다. 실제 토큰 수는 프롬프트 내용에 따라 달라집니다. Reasoning 토큰은 Extended Thinking을 지원하는 모델에만 적용됩니다.
단가 최종 업데이트: 2026년 6월 3일