---
title: "Cached input: the published replay rate · Undominated.ai"
canonical: https://undominated.ai/vi/cache/
description: "186 of 327 standard models publish a cached-input rate. The median is 12.5% of fresh input."
---

# Cached input: the published replay rate · Undominated.ai

> 186 of 327 standard models publish a cached-input rate. The median is 12.5% of fresh input.

# Cache

A cached-input rate is what the seller publishes for tokens already seen. Equal to the fresh rate is not a discount. No published cache rate means this catalogue will not invent one.

As of 28 thg 8, 2026, 186 of 327 standard models publish a cached-input rate. The median is 12.5% of the fresh input rate. 6 publish cache equal to input. 141 publish no cache rate.

Hit rate is yours, not ours. The table is the published rates, sorted cheapest cache relative to fresh input. Workload blends live on the leaderboard.

| Model | Fresh in | Cached in | Cached / fresh |
| --- | --- | --- | --- |
| MiMo-V2.5-Pro | $0.435 | $0.0036 | 0.8% |
| MiMo-V2.5 | $0.140 | $0.0028 | 2% |
| LongCat 2.0 | $0.300 | $0.0060 | 2% |
| Muse Spark 1.2 Contributor | $0.100 | $0.0020 | 2% |
| DeepSeek V4 Flash Vision Exp | $0.220 | $0.0070 | 3.2% |
| DeepSeek V4 Pro 0813 | $1.32 | $0.044 | 3.3% |
| DeepSeek V4 Pro 0423 | $0.870 | $0.072 | 8.3% |
| Claude Sonnet 4 | $3.00 | $0.300 | 10% |
| Claude Sonnet 4.5 | $3.00 | $0.300 | 10% |
| Claude Sonnet 4.6 | $3.00 | $0.300 | 10% |
| Devstral 2 2512 | $0.440 | $0.044 | 10% |
| Gemini 2.5 Flash Lite | $0.100 | $0.010 | 10% |
| Gemini 3.5 Flash | $1.50 | $0.150 | 10% |
| Gemini 3.6 Flash | $0.750 | $0.075 | 10% |
| Gemini 3.7 Flash | $0.375 | $0.037 | 10% |
| GPT-5 Nano | $0.050 | $0.0050 | 10% |
| GPT-5.2 | $1.75 | $0.175 | 10% |
| GPT-5.2 Chat | $1.75 | $0.175 | 10% |
| GPT-5.2-Codex | $1.75 | $0.175 | 10% |
| GPT-5.3-Codex | $1.75 | $0.175 | 10% |
| GPT-5.4 Mini | $0.750 | $0.075 | 10% |
| GPT-5.4 Nano | $0.200 | $0.020 | 10% |
| GPT-5.6 Luna | $0.200 | $0.020 | 10% |
| GPT-5.6 Luna Pro | $0.200 | $0.020 | 10% |
| Kimi K3 | $3.00 | $0.300 | 10% |
| Laguna S 2.1 | $0.090 | $0.0090 | 10% |
| MiniMax M2.5 | $0.270 | $0.027 | 10% |
| Ministral 3 14B 2512 | $0.200 | $0.020 | 10% |
| Ministral 3 3B 2512 | $0.100 | $0.010 | 10% |
| Mistral Medium 3 | $0.400 | $0.040 | 10% |
| Mistral Medium 3.1 | $0.400 | $0.040 | 10% |
| Nex-N2-Mini | $0.025 | $0.0025 | 10% |
| Saba | $0.200 | $0.020 | 10% |
| Voxtral Small 24B 2507 | $0.100 | $0.010 | 10% |
| Claude Fable 5 | $10.00 | $1.00 | 10% |
| Claude Haiku 4.5 | $1.00 | $0.100 | 10% |
| Claude Opus 4 | $15.00 | $1.50 | 10% |
| Claude Opus 4.1 | $15.00 | $1.50 | 10% |
| Claude Opus 4.5 | $5.00 | $0.500 | 10% |
| Claude Opus 4.6 | $5.00 | $0.500 | 10% |
| Claude Opus 4.7 | $5.00 | $0.500 | 10% |
| Claude Opus 4.7 (Fast) | $30.00 | $3.00 | 10% |
| Claude Opus 4.8 | $5.00 | $0.500 | 10% |
| Claude Opus 4.8 (Fast) | $10.00 | $1.00 | 10% |
| Claude Opus 5 | $5.00 | $0.500 | 10% |
| Claude Opus 5 (Fast) | $10.00 | $1.00 | 10% |
| Claude Sonnet 5 | $2.00 | $0.200 | 10% |
| Codestral 2508 | $0.300 | $0.030 | 10% |
| Fugu Ultra | $5.00 | $0.500 | 10% |
| Gemini 2.5 Flash | $0.300 | $0.030 | 10% |
| Gemini 2.5 Pro | $1.25 | $0.125 | 10% |
| Gemini 2.5 Pro Preview 05-06 | $1.25 | $0.125 | 10% |
| Gemini 2.5 Pro Preview 06-05 | $1.25 | $0.125 | 10% |
| Gemini 3 Flash Preview | $0.500 | $0.050 | 10% |
| Gemini 3.1 Flash Lite | $0.250 | $0.025 | 10% |
| Gemini 3.1 Flash Lite Preview | $0.250 | $0.025 | 10% |
| Gemini 3.1 Pro Preview | $2.00 | $0.200 | 10% |
| Gemini 3.1 Pro Preview Custom Tools | $2.00 | $0.200 | 10% |
| Gemini 3.5 Flash Lite | $0.300 | $0.030 | 10% |
| GPT Chat Latest | $5.00 | $0.500 | 10% |
| GPT-5 | $1.25 | $0.125 | 10% |
| GPT-5 Image Mini | $2.50 | $0.250 | 10% |
| GPT-5 Mini | $0.250 | $0.025 | 10% |
| GPT-5.1 | $1.25 | $0.125 | 10% |
| GPT-5.1-Codex-Max | $1.25 | $0.125 | 10% |
| GPT-5.4 | $2.50 | $0.250 | 10% |
| GPT-5.5 | $5.00 | $0.500 | 10% |
| GPT-5.6 Sol | $2.00 | $0.200 | 10% |
| GPT-5.6 Sol Pro | $2.00 | $0.200 | 10% |
| GPT-5.6 Terra | $2.00 | $0.200 | 10% |
| GPT-5.6 Terra Pro | $2.00 | $0.200 | 10% |
| Mercury 2 | $0.250 | $0.025 | 10% |
| MiniMax M2-her | $0.300 | $0.030 | 10% |
| MiniMax M2.1 | $0.300 | $0.030 | 10% |
| Ministral 3 8B 2512 | $0.150 | $0.015 | 10% |
| Mistral Large | $2.00 | $0.200 | 10% |
| Mistral Large 2407 | $2.00 | $0.200 | 10% |
| Mistral Large 3 2512 | $0.500 | $0.050 | 10% |
| Mistral Small 4 | $0.150 | $0.015 | 10% |
| Mixtral 8x22B Instruct | $2.00 | $0.200 | 10% |
| Nano Banana (Gemini 2.5 Flash Image) | $0.300 | $0.030 | 10% |
| Nano Banana Pro (Gemini 3 Pro Image Preview) | $2.00 | $0.200 | 10% |
| Nano Banana Pro (Gemini 3 Pro Image) | $2.00 | $0.200 | 10% |
| Nex-N2-Pro | $0.250 | $0.025 | 10% |
| Solar Pro 3 | $0.150 | $0.015 | 10% |
| GPT-5.1-Codex | $1.25 | $0.130 | 10.4% |
| Muse Glimmer 30B | $0.350 | $0.040 | 11.4% |
| Claude 3 Haiku | $0.250 | $0.030 | 12% |
| GPT-5.1-Codex-Mini | $0.250 | $0.030 | 12% |
| Muse Spark 1.1 | $1.25 | $0.150 | 12% |
| Muse Spark 1.2 | $1.25 | $0.150 | 12% |
| GPT-5 Image | $10.00 | $1.25 | 12.5% |
| Qwen3.8 2.4T A95B | $2.00 | $0.250 | 12.5% |
| Qwen3.8 Max | $2.00 | $0.250 | 12.5% |
| Grok 4.5 | $2.00 | $0.300 | 15% |
| Kimi K2.5 | $0.450 | $0.070 | 15.6% |
| Sakana Namazu | $0.950 | $0.150 | 15.8% |
| Grok 4.20 | $1.25 | $0.200 | 16% |
| Grok 4.20 Multi-Agent | $1.25 | $0.200 | 16% |
| Grok 4.3 | $1.25 | $0.200 | 16% |
| GLM 4.7 Flash | $0.060 | $0.010 | 16.7% |
| Inkling | $0.950 | $0.160 | 16.8% |
| Kimi K2.6 | $0.950 | $0.160 | 16.8% |
| GLM 4.5 | $0.600 | $0.110 | 18.3% |
| GLM 4.5V | $0.600 | $0.110 | 18.3% |
| GLM 4.6V | $0.300 | $0.055 | 18.3% |
| GLM 5.1 | $1.26 | $0.234 | 18.6% |
| GLM 5.2 | $1.19 | $0.221 | 18.6% |
| GLM 5.3 | $1.40 | $0.260 | 18.6% |
| GLM 4.5 Air | $0.130 | $0.025 | 19.2% |
| DeepSeek V4 Flash 0423 | $0.081 | $0.016 | 20% |
| GLM 4.7 | $0.400 | $0.080 | 20% |
| Ling-3.0-flash | $0.021 | $0.0042 | 20% |
| Qwen-Plus | $0.260 | $0.052 | 20% |
| Qwen3 Coder Flash | $0.195 | $0.039 | 20% |
| Qwen3 Max | $0.780 | $0.156 | 20% |
| Qwen3.7 Max | $1.48 | $0.295 | 20% |
| Step 3.7 Flash | $0.200 | $0.040 | 20% |
| DeepSeek V4 Flash 0731 | $0.060 | $0.012 | 20% |
| GLM 4.6 | $0.500 | $0.100 | 20% |
| GLM 5 | $0.600 | $0.120 | 20% |
| GLM 5 Turbo | $1.20 | $0.240 | 20% |
| GLM 5.3 Flash | $0.075 | $0.015 | 20% |
| GLM 5V Turbo | $1.20 | $0.240 | 20% |
| Grok Build 0.1 | $1.00 | $0.200 | 20% |
| KAT-Coder-Air V2.5 | $0.150 | $0.030 | 20% |
| KAT-Coder-Pro V2 | $0.300 | $0.060 | 20% |
| MiniMax M2.7 | $0.300 | $0.060 | 20% |
| MiniMax M3 | $0.300 | $0.060 | 20% |
| Qwen3 Coder Plus | $0.650 | $0.130 | 20% |
| Qwen3.7 Flash | $0.030 | $0.0060 | 20% |
| Qwen3.7 Plus | $0.320 | $0.064 | 20% |
| Qwen3.8 27B | $0.425 | $0.085 | 20% |
| Solar Pro 4 | $0.030 | $0.0060 | 20% |
| KAT-Coder-Pro V2.5 | $0.740 | $0.150 | 20.3% |
| Inkling Small | $0.450 | $0.100 | 22.2% |
| Hy3 | $0.083 | $0.021 | 25% |
| Aion-2.0 | $0.800 | $0.200 | 25% |
| Aion-3.0 | $3.00 | $0.750 | 25% |
| GPT-4.1 | $2.00 | $0.500 | 25% |
| GPT-4.1 Mini | $0.400 | $0.100 | 25% |
| GPT-4.1 Nano | $0.100 | $0.025 | 25% |
| GPT-5.4 Image 2 | $8.00 | $2.00 | 25% |
| Grok 4.6 | $2.00 | $0.500 | 25% |
| Kimi K2 Thinking | $0.600 | $0.150 | 25% |
| Nova Premier 1.0 | $2.50 | $0.625 | 25% |
| o3 | $2.00 | $0.500 | 25% |
| o4 Mini | $1.10 | $0.275 | 25% |
| o4 Mini High | $1.10 | $0.275 | 25% |
| Aion-3.0-Mini | $0.700 | $0.180 | 25.7% |
| Trinity Large Thinking | $0.220 | $0.060 | 27.3% |
| Kimi K2.7 Code | $0.670 | $0.190 | 28.4% |
| Hy3 preview | $0.180 | $0.060 | 33.3% |
| Nemotron 3 Ultra | $0.600 | $0.200 | 33.3% |
| Qwen3 Coder 480B A35B | $0.300 | $0.100 | 33.3% |
| Qwen3.6 35B A3B | $0.140 | $0.050 | 35.7% |
| Skyfall 36B V2 | $0.550 | $0.250 | 45.5% |
| Qwen3 VL 235B A22B Instruct | $0.210 | $0.100 | 47.6% |
| Cydonia 24B V4.1 | $0.300 | $0.150 | 50% |
| DeepSeek V3.1 Terminus | $0.270 | $0.135 | 50% |
| DeepSeek V3.2 | $0.260 | $0.130 | 50% |
| Gemma 3 27B | $0.080 | $0.040 | 50% |
| GPT-4o | $2.50 | $1.25 | 50% |
| GPT-4o (2024-08-06) | $2.50 | $1.25 | 50% |
| GPT-4o (2024-11-20) | $2.50 | $1.25 | 50% |
| GPT-4o-mini | $0.150 | $0.075 | 50% |
| GPT-4o-mini (2024-07-18) | $0.150 | $0.075 | 50% |
| gpt-oss-safeguard-20b | $0.075 | $0.037 | 50% |
| Laguna XS 2.1 | $0.060 | $0.030 | 50% |
| Llama 3.1 8B Instruct | $0.050 | $0.025 | 50% |
| Llama 4 Scout | $0.110 | $0.055 | 50% |
| Nemotron 3.5 Lightning | $0.080 | $0.040 | 50% |
| o1 | $15.00 | $7.50 | 50% |
| o3 Mini | $1.10 | $0.550 | 50% |
| o3 Mini High | $1.10 | $0.550 | 50% |
| Gemma 4 31B | $0.090 | $0.050 | 55.6% |
| Qwen3 Coder Next | $0.120 | $0.070 | 58.3% |
| Nemotron 3 Nano 30B A3B | $0.050 | $0.030 | 60% |
| R1 0528 | $0.500 | $0.350 | 70% |
| Qwen3 Next 80B A3B Instruct | $0.100 | $0.070 | 70% |
| DeepSeek V3.1 | $0.550 | $0.550 | 100% |
| gpt-oss-20b | $0.030 | $0.030 | 100% |
| Granite 4.1 8B | $0.050 | $0.050 | 100% |
| Llama 3.3 70B Instruct | $0.710 | $0.710 | 100% |
| Qwen3.5-35B-A3B | $0.250 | $0.250 | 100% |
| UI-TARS 7B | $0.100 | $0.100 | 100% |