Prompt caching AI models: send the same prefix twice, pay once
| # | AI model | Capabilities | API $/1M (in / out) | Context window | Price / mo | Output $/1M | Overview | Visit site |
|---|---|---|---|---|---|---|---|---|
| 121 |  Qwen3 Coder Plus Qwen |    | $0.65 / $3.25 | 1M tokens | API only | 3.25 | View | |
| 122 |  GPT-5.1-Codex-Mini OpenAI |  | $0.25 / $2 | 400K tokens | API only | 2 | View | |
| 123 |  GLM 4.6V Z.ai |  | $0.3 / $0.9 | 131.1K tokens | API only | 0.9 | View | |
| 124 | GPT-5.1-Codex OpenAI | | $1.25 / $10 | 400K tokens | API only | 10 | View | |
| 125 |  MiniMax M2.1 MiniMax |  | $0.3 / $1.2 | 204.8K tokens | API only | 1.2 | View | |
| 126 | MiniMax M2-her MiniMax | | $0.3 / $1.2 | 65.5K tokens | API only | 1.2 | View | |
| 127 | MiniMax M2 MiniMax | | $0.255 / $1.02 | 204.8K tokens | API only | 1.02 | View | |
| 128 | GPT-5.5 Pro OpenAI | | $30 / $180 | 1.05M tokens | API only | 180 | View | |
| 129 | GPT-5.1-Codex-Max OpenAI | | $1.25 / $10 | 400K tokens | API only | 10 | View | |
| 130 | Qwen3 Max Thinking Qwen |  | $0.78 / $3.9 | 262.1K tokens | API only | 3.9 | View | |
| 131 | GPT Audio Mini OpenAI |   | $0.6 / $2.4 | 128K tokens | API only | 2.4 | View | |
| 132 | GPT-5.4 Pro OpenAI | | $30 / $180 | 1.05M tokens | API only | 180 | View | |
| 133 |  Mistral Large 3 Mistral AI | | $0.5 / $1.5 | 256K tokens | API only | 1.5 | View | |
| 134 | Qwen3.8 Omni Flash Qwen | | 1M tokens | API only | View | |||
| 135 |  MiMo-V2.6-Pro Xiaomi | | $0.435 / $0.87 | 1M tokens | API only | 0.87 | View | |
| 136 | MiMo-V2.6-Flash Xiaomi | | $0.14 / $0.28 | 1M tokens | API only | 0.28 | View | |
| 137 | MiMo-V2.6-Pro-UltraSpeed Xiaomi | | $4.35 / $8.7 | 1M tokens | API only | 8.7 | View | |
| 138 |  Hy4 preview Tencent | | $0.84 / $2.52 | 1M tokens | API only | 2.52 | View | |
| 139 |  Fugu Max Sakana | | $2 / $6 | API only | 6 | View | ||
| 140 |  Aion 3.5 Aion Labs |  | $3 / $6 | 256K tokens | API only | 6 | View |
Browse by need
Prompt caching stores an identical prompt prefix between calls, so repeated context is charged at a fraction of the base input rate - typically 10%, and as little as 2.5% on Claude Fable 5.1. If your application sends the same lengthy system prompt with every request, this is usually the biggest saving available to you.
147 models support it. The saving applies to input only, so the effect is largest where prompts are long and answers are short - support bots with detailed instructions, agents with big tool catalogues, RAG systems that resend the same corpus. Cache entries expire, so the economics favour high request frequency against a stable prefix.
Models with this capability
The 147 models below all support this capability. Prices are input and output per 1M tokens from the vendor official price list; for dirhams multiply by 3.6725. Tap a card to open the model page.
How to choose
- Put everything stable at the very front: system prompt, tool definitions, reference documents.
- Keep user-specific content after the cached prefix.
- Check the cache lifetime — short TTLs punish low-traffic applications.
- Account for write cost: some vendors charge a premium to create the entry.
Common mistakes
Who this suits
Related filters
Frequently asked questions
How much does caching save?
What has to stay identical?
When is caching pointless?
How much can I realistically save?
Does caching change answers?
Frequently searched
Rate this page
Help us improve