1. Use case
Input tokensText you send to the AI
Output tokensResponse the AI generates
Reasoning tokens
AI's thinking process (some models only)API callsTotal number of requests
Prompt cacheReuses 80% of repeated input to reduce cost
Show speed
Paste your prompt (optional)
2. Cost simulation
| Model | Total Min | Total Max | Total Min~Total Max | Unit |
|---|---|---|---|---|
 Granite 4.1 8B | $0.510 | $0.990 | $0.510~0.990 | $0.050/1M |
 GPT OSS 120B | $1.23 | $2.05 | $1.23~2.05 | $0.037/1M |
 Llama 4 Scout | $1.38 | $2.82 | $1.38~2.82 | $0.100/1M |
 DeepSeek V4 Flash | $1.46 | $2.32 | $1.46~2.32 | $0.090/1M |
 Nemotron 3 Nano 30B A3B | $1.47 | $2.43 | $1.47~2.43 | $0.050/1M |
 MiMo V2.5 | $2.27 | $3.61 | $2.27~3.61 | $0.140/1M |
 Gemma 4 31B | $2.54 | $4.18 | $2.54~4.18 | $0.100/1M |
GPT-5 Nano | $2.79 | $4.71 | $2.79~4.71 | $0.050/1M |
Nemotron 3 Super | $2.89 | $4.82 | $2.89~4.82 | $0.085/1M |
 Dola Seed 2.0 mini | $2.94 | $4.86 | $2.94~4.86 | $0.100/1M |
DeepSeek V3.2 | $3.45 | $5.37 | $3.45~5.37 | $0.269/1M |
Llama 4 Maverick | $3.48 | $7.32 | $3.48~7.32 | $0.200/1M |
 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 |
GPT-5.6 Luna | $4.26 | $7.14 | $4.26~7.14 | $0.100/1M |
Ring-2.6-1T | $4.35 | $7.35 | $4.35~7.35 | $0.075/1M |
 Mistral Small 4 | $4.41 | $7.29 | $4.41~7.29 | $0.150/1M |
 Solar Pro 3 | $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 |
 Sonar | $6.60 | $11.40 | $6.60~11.40 | $1.00/1M |
 MiniMax M2.5 | $6.60 | $10.92 | $6.60~10.92 | $0.220/1M |
 Qwen: Qwen3.6 35B A3B | $7.02 | $11.82 | $7.02~11.82 | $0.140/1M |
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 |
 Step 3.7 Flash | $8.19 | $13.71 | $8.19~13.71 | $0.200/1M |
LongCat 2.0 | $8.82 | $14.58 | $8.82~14.58 | $0.300/1M |
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 |
Qwen3.7 Plus | $9.41 | $15.55 | $9.41~15.55 | $0.320/1M |
 ERNIE 4.5 VL 424B A47B | $9.51 | $15.51 | $9.51~15.51 | $0.420/1M |
Gemini 3.1 Flash Lite | $10.65 | $17.85 | $10.65~17.85 | $0.250/1M |
 GLM 5.2 | $11.60 | $18.97 | $11.60~18.97 | $0.489/1M |
Grok 4.20 | $12.75 | $24.75 | $12.75~24.75 | $1.25/1M |
Qwen: Qwen3.5 Plus 2026-04-20 | $12.78 | $21.42 | $12.78~21.42 | $0.300/1M |
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 |
Grok Build 0.1 | $16.20 | $25.80 | $16.20~25.80 | $1.00/1M |
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 |
Gemini 3.5 Flash-Lite | $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 |
 Kimi K2.6 | $17.84 | $29.55 | $17.84~29.55 | $0.580/1M |
GLM-5 | $19.68 | $31.92 | $19.68~31.92 | $0.950/1M |
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 |
Kimi K2.5 | $20.52 | $34.20 | $20.52~34.20 | $0.570/1M |
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 | $22.60 | $36.96 | $22.60~36.96 | $0.952/1M |
Kimi K2.7 Code | $25.20 | $42.00 | $25.20~42.00 | $0.700/1M |
Nemotron 3 Ultra | $25.56 | $42.84 | $25.56~42.84 | $0.600/1M |
 Sakana Namazu | $29.25 | $48.45 | $29.25~48.45 | $0.950/1M |
GLM 5V Turbo | $30.00 | $49.20 | $30.00~49.20 | $1.20/1M |
GLM-5-Turbo | $30.00 | $49.20 | $30.00~49.20 | $1.20/1M |
Muse Spark 1.1 | $31.80 | $52.20 | $31.80~52.20 | $1.25/1M |
GPT-5.4 Mini | $31.95 | $53.55 | $31.95~53.55 | $0.750/1M |
Qwen: Qwen3.7 Max | $33.63 | $54.87 | $33.63~54.87 | $1.48/1M |
GPT-4.1 | $34.80 | $73.20 | $34.80~73.20 | $2.00/1M |
K-EXAONE 2.0 | $35.28 | $58.32 | $35.28~58.32 | $1.20/1M |
 Claude Haiku 4.5 | $36.00 | $60.00 | $36.00~60.00 | $1.00/1M |
GPT-5.6 Terra | $42.60 | $71.40 | $42.60~71.40 | $1.00/1M |
Qwen3.6 Max | $43.75 | $73.33 | $43.75~73.33 | $1.03/1M |
Grok 4.5 | $45.60 | $74.40 | $45.60~74.40 | $2.00/1M |
Gemini 3.6 Flash | $54.00 | $90.00 | $54.00~90.00 | $1.50/1M |
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 |
Claude Sonnet 5 | $72.00 | $120.00 | $72.00~120.00 | $2.00/1M |
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 |
Kimi K3 | $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 |
Claude Opus 5 | $180.00 | $300.00 | $180.00~300.00 | $5.00/1M |
Fugu Ultra | $213.00 | $357.00 | $213.00~357.00 | $5.00/1M |
GPT-5.5 | $213.00 | $357.00 | $213.00~357.00 | $5.00/1M |
GPT-5.6 Sol | $213.00 | $357.00 | $213.00~357.00 | $5.00/1M |
Claude Fable 5 | $360.00 | $600.00 | $360.00~600.00 | $10.00/1M |
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 |
4. Simulation summary
Cheapest model
Granite 4.1 8B
$0.510 /3,000calls
Best performance model
Claude Opus 5
$180.00 /3,000calls
Calculation basis
Input tokens: 1,000
Output tokens: 1,200 ~ 2,800 (±40%)
Reasoning tokens: 1,000
Usage: 3,000 calls
Token presets are statistical averages for each scenario. Actual token counts vary depending on prompt content. Reasoning tokens only apply to models that support Extended Thinking.
Pricing last updated: 2026년 8월 8일