4,154 个模型 · 8,429 个价格 · 最近采集 28 分钟前 · 30 天内 36 条需关注的调价
每个平台公布的每一个价格
采集器定时读取 6 个平台公开的全部价格（默认每天一次），并保存读到的原始页面。没有任何手工录入。搜索一个模型，就能看到现在按单位谁最便宜。
第 6701–6800 条，共 7,913 条
每百万缓存读取 token24
| 平台 | 模型 · 计价项 | 美元 | 平台原文 | 生效于 |
|---|---|---|---|---|
| fal | GPT Image 2.6 Sunburst Text to Image文生图text | $1.25/百万缓存读 | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2 API图片编辑text | $1.25/百万缓存读 | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| OpenRouter | OpenAI: GPT-4o | $1.25/百万缓存读 | input_cache_read: 0.00000125 / token | |
| OpenRouter | OpenAI: GPT-4o (2024-08-06) | $1.25/百万缓存读 | input_cache_read: 0.00000125 / token | |
| OpenRouter | OpenAI: GPT-4o (2024-11-20) | $1.25/百万缓存读 | input_cache_read: 0.00000125 / token | |
| OpenRouter | OpenAI: GPT-5 Image | $1.25/百万缓存读 | input_cache_read: 0.00000125 / token | |
| OpenRouter | Anthropic: Claude Opus 4.1 | $1.5/百万缓存读 | input_cache_read: 0.0000015 / token | |
| kie.ai | gpt-image-2-6-flare文生图图片编辑 | $1.8/百万缓存读 | 360 credits per million tokens ($1.8)平台声称 fal 价 $2/百万缓存读 | |
| kie.ai | gpt-image-2-6-sunburst文生图图片编辑 | $1.8/百万缓存读 | 360 credits per million tokens ($1.8)平台声称 fal 价 $2/百万缓存读 | |
| fal | GPT Image 2 API | $2/百万缓存读 | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.5 Flare Edit图片编辑 | $2/百万缓存读 | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.5 Flare Text to Image文生图 | $2/百万缓存读 | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.5 Sunburst Edit 图片编辑 | $2/百万缓存读 | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.5 Sunburst Text to Image文生图 | $2/百万缓存读 | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.6 Flare Edit图片编辑 | $2/百万缓存读 | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.6 Flare Text to Image文生图 | $2/百万缓存读 | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.6 Sunburst Edit图片编辑 | $2/百万缓存读 | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2.6 Sunburst Text to Image文生图 | $2/百万缓存读 | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| fal | GPT Image 2 API图片编辑 | $2/百万缓存读 | Text tokens (per 1M): $5.00 input, $1.25 cached, $10.00 output. Image tokens (per 1M): $8.00 input, $2.00 cached, $30.00 output. Changing the quality parameter significantly affects cost; by default we use high. Adjust it to your preference. See the description at the bottom of this page for more details on how much canonical image sizes cost. Total cost is rounded up to the closest hundredth of a | |
| OpenRouter | OpenAI: GPT-5.4 Image 2 | $2/百万缓存读 | input_cache_read: 0.000002 / token | |
| OpenRouter | OpenAI: GPT-6 Astra提示词超过 272K | $2/百万缓存读 | input_cache_read: 0.000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Astra Pro提示词超过 272K | $2/百万缓存读 | input_cache_read: 0.000002 / token (>272000) | |
| OpenRouter | OpenAI: GPT Astra Latest提示词超过 272K | $2/百万缓存读 | input_cache_read: 0.000002 / token (>272000) | |
| OpenRouter | Magnum v4 72B | $2.5/百万缓存读 | input_cache_read: 0.0000025 / token |
每百万缓存写入 token76
| 平台 | 模型 · 计价项 | 美元 | 平台原文 | 生效于 |
|---|---|---|---|---|
| kie.ai | gpt-6-luna | $0.0375/百万缓存写最低 | 7.5 credits per million tokens ($0.0375)平台声称 fal 价 $0.125/百万缓存写 | |
| OpenRouter | Qwen: Qwen3.7 Flash缓存 5 分钟 | $0.038/百万缓存写 | input_cache_write: 0.000000038 / token | |
| OpenRouter | Google: Gemini 3.6 Flash缓存 5 分钟 | $0.0416667/百万缓存写 | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.6 Flash (batch)缓存 5 分钟 | $0.0416667/百万缓存写 | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.7 Flash缓存 5 分钟 | $0.0416667/百万缓存写 | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.7 Flash (batch)缓存 5 分钟 | $0.0416667/百万缓存写 | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.8 Flash缓存 5 分钟 | $0.0416667/百万缓存写 | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini 3.8 Flash (batch)缓存 5 分钟 | $0.0416667/百万缓存写 | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Google: Gemini Flash Latest缓存 5 分钟 | $0.0416667/百万缓存写 | input_cache_write: 0.0000000416666666666667 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5 (batch)缓存 5 分钟 | $0.0625/百万缓存写 | input_cache_write: 0.0000000625 / token | |
| OpenRouter | OpenAI: GPT-6 Luna Pro (batch)缓存 5 分钟 | $0.0625/百万缓存写 | input_cache_write: 0.0000000625 / token | |
| OpenRouter | OpenAI: GPT-6 Luna (batch)缓存 5 分钟 | $0.0625/百万缓存写 | input_cache_write: 0.0000000625 / token | |
| kie.ai | gpt-5.6-luna | $0.07/百万缓存写 | 14 credits per million tokens ($0.07)平台声称 fal 价 $0.25/百万缓存写 | |
| OpenRouter | Google: Gemini 2.5 Flash缓存 5 分钟 | $0.0833333/百万缓存写 | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Google: Nano Banana (Gemini 2.5 Flash Image)缓存 5 分钟 | $0.0833333/百万缓存写 | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Google: Gemini 2.5 Flash Lite缓存 5 分钟 | $0.0833333/百万缓存写 | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Google: Gemini 3 Flash Preview缓存 5 分钟 | $0.0833333/百万缓存写 | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite缓存 5 分钟 | $0.0833333/百万缓存写 | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Google: Gemini 3.1 Flash Lite Preview缓存 5 分钟 | $0.0833333/百万缓存写 | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Google: Gemini 3.5 Flash缓存 5 分钟 | $0.0833333/百万缓存写 | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Google: Gemini 3.5 Flash Lite缓存 5 分钟 | $0.0833333/百万缓存写 | input_cache_write: 0.0000000833333333333333 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5 (batch)缓存 1 小时 | $0.1/百万缓存写 | input_cache_write_1h: 0.0000001 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5缓存 5 分钟 | $0.125/百万缓存写 | input_cache_write: 0.000000125 / token | |
| OpenRouter | OpenAI: GPT-6 Luna缓存 5 分钟 | $0.125/百万缓存写 | input_cache_write: 0.000000125 / token | |
| OpenRouter | OpenAI: GPT-6 Luna Pro缓存 5 分钟 | $0.125/百万缓存写 | input_cache_write: 0.000000125 / token | |
| OpenRouter | OpenAI: GPT-6 Luna Pro (batch)缓存 5 分钟提示词超过 272K | $0.125/百万缓存写 | input_cache_write: 0.000000125 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Luna (batch)缓存 5 分钟提示词超过 272K | $0.125/百万缓存写 | input_cache_write: 0.000000125 / token (>272000) | |
| OpenRouter | Qwen: Qwen3.7 Flash缓存 5 分钟提示词超过 32K | $0.125/百万缓存写 | input_cache_write: 0.000000125 / token (>32000) | |
| OpenRouter | Anthropic: Claude Haiku Latest缓存 5 分钟 | $0.125/百万缓存写 | input_cache_write: 0.000000125 / token | |
| OpenRouter | OpenAI: GPT Luna Latest缓存 5 分钟 | $0.125/百万缓存写 | input_cache_write: 0.000000125 / token | |
| OpenRouter | Google: Gemini 4 Argon缓存 5 分钟 | $0.1875/百万缓存写 | input_cache_write: 0.0000001875 / token | |
| OpenRouter | Google: Gemini 4 Argon (batch)缓存 5 分钟 | $0.1875/百万缓存写 | input_cache_write: 0.0000001875 / token | |
| OpenRouter | Google: Gemini Pro Latest缓存 5 分钟 | $0.1875/百万缓存写 | input_cache_write: 0.0000001875 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5缓存 1 小时 | $0.2/百万缓存写 | input_cache_write_1h: 0.0000002 / token | |
| OpenRouter | Anthropic: Claude Haiku Latest缓存 1 小时 | $0.2/百万缓存写 | input_cache_write_1h: 0.0000002 / token | |
| OpenRouter | Qwen: Qwen3.6 Flash缓存 5 分钟 | $0.234375/百万缓存写 | input_cache_write: 0.000000234375 / token | |
| OpenRouter | Qwen: Qwen3 Coder Flash缓存 5 分钟 | $0.24375/百万缓存写 | input_cache_write: 0.00000024375 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna缓存 5 分钟 | $0.25/百万缓存写 | input_cache_write: 0.00000025 / token | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro缓存 5 分钟 | $0.25/百万缓存写 | input_cache_write: 0.00000025 / token | |
| OpenRouter | OpenAI: GPT-6 Luna缓存 5 分钟提示词超过 272K | $0.25/百万缓存写 | input_cache_write: 0.00000025 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6 Luna Pro缓存 5 分钟提示词超过 272K | $0.25/百万缓存写 | input_cache_write: 0.00000025 / token (>272000) | |
| OpenRouter | Qwen: Qwen3.7 Flash缓存 5 分钟提示词超过 256K | $0.25/百万缓存写 | input_cache_write: 0.00000025 / token (>256000) | |
| OpenRouter | OpenAI: GPT Luna Latest缓存 5 分钟提示词超过 272K | $0.25/百万缓存写 | input_cache_write: 0.00000025 / token (>272000) | |
| OpenRouter | Anthropic: Claude Haiku 5.5 (batch)缓存 5 分钟提示词超过 100K | $0.3125/百万缓存写 | input_cache_write: 0.0000003125 / token (>100000) | |
| OpenRouter | Qwen: Qwen-Plus缓存 5 分钟 | $0.325/百万缓存写 | input_cache_write: 0.000000325 / token | |
| kie.ai | gpt-6-1-terra | $0.375/百万缓存写 | 75 credits per million tokens ($0.375)平台声称 fal 价 $1.25/百万缓存写 | |
| OpenRouter | Google: Gemini 2.5 Pro缓存 5 分钟 | $0.375/百万缓存写 | input_cache_write: 0.000000375 / token | |
| OpenRouter | Google: Gemini 2.5 Pro Preview 06-05缓存 5 分钟 | $0.375/百万缓存写 | input_cache_write: 0.000000375 / token | |
| OpenRouter | Google: Nano Banana Pro (Gemini 3 Pro Image)缓存 5 分钟 | $0.375/百万缓存写 | input_cache_write: 0.000000375 / token | |
| OpenRouter | Google: Nano Banana Pro (Gemini 3 Pro Image Preview)缓存 5 分钟 | $0.375/百万缓存写 | input_cache_write: 0.000000375 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview缓存 5 分钟 | $0.375/百万缓存写 | input_cache_write: 0.000000375 / token | |
| OpenRouter | Google: Gemini 3.1 Pro Preview Custom Tools缓存 5 分钟 | $0.375/百万缓存写 | input_cache_write: 0.000000375 / token | |
| OpenRouter | Qwen: Qwen3.5 Plus 2026-04-20缓存 5 分钟 | $0.375/百万缓存写 | input_cache_write: 0.000000375 / token | |
| OpenRouter | Qwen: Qwen3.7 Plus缓存 5 分钟 | $0.4/百万缓存写 | input_cache_write: 0.0000004 / token | |
| OpenRouter | Qwen: Qwen3 Coder Flash缓存 5 分钟提示词超过 32K | $0.40625/百万缓存写 | input_cache_write: 0.00000040625 / token (>32000) | |
| OpenRouter | Qwen: Qwen3.6 Plus缓存 5 分钟 | $0.40625/百万缓存写 | input_cache_write: 0.00000040625 / token | |
| OpenRouter | Qwen: Qwen3.5 Plus 2026-04-20缓存 5 分钟提示词超过 256K | $0.46875/百万缓存写 | input_cache_write: 0.00000046875 / token (>256000) | |
| OpenRouter | Anthropic: Claude Haiku 5.5 (batch)缓存 1 小时提示词超过 100K | $0.5/百万缓存写 | input_cache_write_1h: 0.0000005 / token (>100000) | |
| OpenRouter | OpenAI: GPT-5.6 Luna缓存 5 分钟提示词超过 272K | $0.5/百万缓存写 | input_cache_write: 0.0000005 / token (>272000) | |
| OpenRouter | OpenAI: GPT-5.6 Luna Pro缓存 5 分钟提示词超过 272K | $0.5/百万缓存写 | input_cache_write: 0.0000005 / token (>272000) | |
| OpenRouter | Anthropic: Claude Haiku 4.5 (batch)缓存 5 分钟 | $0.625/百万缓存写 | input_cache_write: 0.000000625 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5缓存 5 分钟提示词超过 100K | $0.625/百万缓存写 | input_cache_write: 0.000000625 / token (>100000) | |
| OpenRouter | OpenAI: GPT-6.1 Terra Pro (batch)缓存 5 分钟 | $0.625/百万缓存写 | input_cache_write: 0.000000625 / token | |
| OpenRouter | OpenAI: GPT-6.1 Terra (batch)缓存 5 分钟 | $0.625/百万缓存写 | input_cache_write: 0.000000625 / token | |
| OpenRouter | Anthropic: Claude Haiku Latest缓存 5 分钟提示词超过 100K | $0.625/百万缓存写 | input_cache_write: 0.000000625 / token (>100000) | |
| OpenRouter | Qwen: Qwen3 Coder Flash缓存 5 分钟提示词超过 128K | $0.65/百万缓存写 | input_cache_write: 0.00000065 / token (>128000) | |
| kie.ai | gpt-5.6-terra | $0.7/百万缓存写 | 140 credits per million tokens ($0.70)平台声称 fal 价 $2.5/百万缓存写 | |
| kie.ai | gpt-6-1-sol | $0.75/百万缓存写 | 150 credits per million tokens ($0.75)平台声称 fal 价 $2.5/百万缓存写 | |
| kie.ai | gpt-6-sol | $0.75/百万缓存写 | 150 credits per million tokens ($0.75)平台声称 fal 价 $2.5/百万缓存写 | |
| OpenRouter | Qwen: Qwen3.6 Flash缓存 5 分钟提示词超过 256K | $0.9375/百万缓存写 | input_cache_write: 0.0000009375 / token (>256000) | |
| OpenRouter | Qwen: Qwen-Plus缓存 5 分钟提示词超过 256K | $0.975/百万缓存写 | input_cache_write: 0.000000975 / token (>256000) | |
| OpenRouter | Anthropic: Claude Haiku 4.5 (batch)缓存 1 小时 | $1/百万缓存写 | input_cache_write_1h: 0.000001 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5缓存 1 小时提示词超过 100K | $1/百万缓存写 | input_cache_write_1h: 0.000001 / token (>100000) | |
| OpenRouter | Anthropic: Claude Haiku Latest缓存 1 小时提示词超过 100K | $1/百万缓存写 | input_cache_write_1h: 0.000001 / token (>100000) | |
| OpenRouter | Qwen: Qwen3.7 Plus缓存 5 分钟提示词超过 256K | $1.2/百万缓存写 | input_cache_write: 0.0000012 / token (>256000) | |
| OpenRouter | Anthropic: Claude Haiku 4.5缓存 5 分钟 | $1.25/百万缓存写 | input_cache_write: 0.00000125 / token |
