4,757 个接口 · 10,634 个价格 · 最近采集 38 分钟前 · 30 天内 399 条需关注的调价
每个平台公布的每一个价格
采集器定时抓取 8 个平台公开的全部价格（默认每日一次），并完整保存原始页面快照，绝无任何手工篡改。搜索具体模型，即可查看当前各单位下的最低价格。
Llama 
DeepSeek 
Nemotron 
Mistral 
Qwen 第 1–100 条，共 103 条
按输出秒数4
| 平台 | 模型 · 计价项 | 美元 | 平台原文 | 生效于 |
|---|---|---|---|---|
| Fal平台自部署 | MoonDreamNext | $0.0011/秒最低 | $0.0011 / seconds | |
| Fal平台自部署 | MoonDreamNext Batch | $0.0011/秒最低 | $0.0011 / seconds | |
| Fal平台自部署 | Sa2VA 4B Video | $0.04/秒 | $0.04 / seconds | |
| Fal平台自部署 | Sa2VA 8B Video | $0.08/秒 | $0.08 / seconds |
按张5
| 平台 | 模型 · 计价项 | 美元 | 平台原文 | 生效于 |
|---|---|---|---|---|
| Fal平台自部署 | NSFW Filter | $0.001/张最低 | $0.001 / images | |
| Fal平台自部署 | Moondream2 | $0.02/张 | $0.02 / images | |
| Fal平台自部署 | Moondream2 | $0.02/张 | $0.02 / images | |
| Fal平台自部署 | Sa2VA 4B Image | $0.02/张 | $0.02 / images | |
| Fal平台自部署 | Sa2VA 8B Image | $0.04/张 | $0.04 / images |
每百万输入 token36
| 平台 | 模型 · 计价项 | 美元 | 平台原文 | 生效于 |
|---|---|---|---|---|
| Replicate平台自部署 | ibm-granite/granite-3.0-2b-instruct | $0.03/百万输入最低 | $0.03 per million input tokens | |
| Replicate平台自部署 | ibm-granite/granite-3.1-2b-instruct | $0.03/百万输入最低 | $0.03 per million input tokens | |
| Replicate平台自部署 | ibm-granite/granite-3.1-8b-instruct | $0.03/百万输入最低 | $0.03 per million input tokens | |
| Replicate平台自部署 | ibm-granite/granite-3.2-8b-instruct | $0.03/百万输入最低 | $0.03 per million input tokens | |
| Replicate平台自部署 | ibm-granite/granite-3.3-8b-instruct | $0.03/百万输入最低 | $0.03 per million input tokens | |
| Replicate平台自部署 | ibm-granite/granite-speech-4.1-2b | $0.03/百万输入最低 | $0.03 per million input tokens | |
| Replicate平台自部署 | ibm-granite/granite-3.0-8b-instruct | $0.05/百万输入 | $0.05 per million input tokens | |
| Replicate平台自部署 | ibm-granite/granite-8b-code-instruct-128k | $0.05/百万输入 | $0.05 per million input tokens | |
| Replicate平台自部署 | meta/llama-2-7b | $0.05/百万输入 | $0.05 per million input tokens | |
| Replicate平台自部署 | meta/llama-2-7b-chat | $0.05/百万输入 | $0.05 per million input tokens | |
| Replicate平台自部署 | meta/meta-llama-3-8b | $0.05/百万输入 | $0.05 per million input tokens | |
| Replicate平台自部署 | meta/meta-llama-3-8b-instruct | $0.05/百万输入 | $0.05 per million input tokens | |
| Replicate平台自部署 | mistralai/mistral-7b-v0.1 | $0.05/百万输入 | $0.05 per million input tokens | |
| Replicate平台自部署 | ibm-granite/granite-4.0-h-small | $0.06/百万输入 | $0.06 per million input tokens | |
| Replicate平台自部署 | ibm-granite/granite-4.1-8b | $0.06/百万输入 | $0.06 per million input tokens | |
| Replicate平台自部署 | ibm-granite/granite-4.2-8b | $0.06/百万输入 | $0.06 per million input tokens | |
| Replicate平台自部署 | ibm-granite/granite-vision-4.1-4b | $0.06/百万输入 | $0.06 per million input tokens | |
| Replicate平台自部署 | ibm-granite/granite-20b-code-instruct-8k | $0.1/百万输入 | $0.10 per million input tokens | |
| Replicate平台自部署 | meta/llama-2-13b | $0.1/百万输入 | $0.10 per million input tokens | |
| Replicate平台自部署 | meta/llama-2-13b-chat | $0.1/百万输入 | $0.10 per million input tokens | |
| Replicate平台自部署 | meta/llama-4-scout-instruct | $0.17/百万输入 | $0.17 per million input tokens | |
| Replicate平台自部署 | openai/gpt-oss-120b | $0.18/百万输入 | $0.18 per million input tokens | |
| Replicate平台自部署 | meta/llama-guard-4-12b | $0.2/百万输入 | $0.20 per million input tokens | |
| Replicate平台自部署 | meta/llama-4-maverick-instruct | $0.25/百万输入 | $0.25 per million input tokens | |
| Replicate平台自部署 | perceptron-ai-inc/isaac-0.1 | $0.26/百万输入 | $0.26 per million input tokens | |
| Replicate平台自部署 | qwen/qwen3-235b-a22b-instruct-2507 | $0.264/百万输入 | $0.264 per million input tokens | |
| Fal平台自部署 | Moondream3 Preview [Caption] | $0.4/百万输入 | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| Fal平台自部署 | Moondream3 Preview [Detect] | $0.4/百万输入 | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| Fal平台自部署 | Moondream3 Preview [Point] | $0.4/百万输入 | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| Fal平台自部署 | Moondream 3 Preview [Query] | $0.4/百万输入 | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| Replicate平台自部署 | meta/llama-2-70b | $0.65/百万输入 | $0.65 per million input tokens | |
| Replicate平台自部署 | meta/llama-2-70b-chat | $0.65/百万输入 | $0.65 per million input tokens | |
| Replicate平台自部署 | meta/meta-llama-3-70b | $0.65/百万输入 | $0.65 per million input tokens | |
| Replicate平台自部署 | meta/meta-llama-3-70b-instruct | $0.65/百万输入 | $0.65 per million input tokens | |
| Replicate平台自部署 | deepseek-ai/deepseek-v3 | $1.45/百万输入 | $1.45 per million input tokens | |
| Replicate平台自部署 | deepseek-ai/deepseek-r1 | $3.75/百万输入 | $3.75 per million input tokens |
每百万输出 token38
| 平台 | 模型 · 计价项 | 美元 | 平台原文 | 生效于 |
|---|---|---|---|---|
| Replicate平台自部署 | meta/llama-guard-4-12b | $0.2/百万输出最低 | $0.20 per million output tokens | |
| Replicate平台自部署 | ibm-granite/granite-3.0-2b-instruct | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | ibm-granite/granite-3.0-8b-instruct | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | ibm-granite/granite-3.1-2b-instruct | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | ibm-granite/granite-3.1-8b-instruct | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | ibm-granite/granite-3.2-8b-instruct | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | ibm-granite/granite-3.3-8b-instruct | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | ibm-granite/granite-4.0-h-small | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | ibm-granite/granite-4.1-8b | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | ibm-granite/granite-4.2-8b | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | ibm-granite/granite-8b-code-instruct-128k | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | ibm-granite/granite-speech-4.1-2b | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | ibm-granite/granite-vision-3.3-2b | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | ibm-granite/granite-vision-4.1-4b | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | meta/llama-2-7b | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | meta/llama-2-7b-chat | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | meta/meta-llama-3-8b | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | meta/meta-llama-3-8b-instruct | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | mistralai/mistral-7b-v0.1 | $0.25/百万输出 | $0.25 per million output tokens | |
| Replicate平台自部署 | ibm-granite/granite-20b-code-instruct-8k | $0.5/百万输出 | $0.50 per million output tokens | |
| Replicate平台自部署 | meta/llama-2-13b | $0.5/百万输出 | $0.50 per million output tokens | |
| Replicate平台自部署 | meta/llama-2-13b-chat | $0.5/百万输出 | $0.50 per million output tokens | |
| Replicate平台自部署 | meta/llama-4-scout-instruct | $0.65/百万输出 | $0.65 per million output tokens | |
| Replicate平台自部署 | openai/gpt-oss-120b | $0.72/百万输出 | $0.72 per million output tokens | |
| Replicate平台自部署 | meta/llama-4-maverick-instruct | $0.95/百万输出 | $0.95 per million output tokens | |
| Replicate平台自部署 | qwen/qwen3-235b-a22b-instruct-2507 | $1.06/百万输出 | $1.06 per million output tokens | |
| Replicate平台自部署 | deepseek-ai/deepseek-v3 | $1.45/百万输出 | $1.45 per million output tokens | |
| Replicate平台自部署 | perceptron-ai-inc/isaac-0.1 | $2.17/百万输出 | $2.17 per million output tokens | |
| Replicate平台自部署 | meta/llama-2-70b | $2.75/百万输出 | $2.75 per million output tokens | |
| Replicate平台自部署 | meta/llama-2-70b-chat | $2.75/百万输出 | $2.75 per million output tokens | |
| Replicate平台自部署 | meta/meta-llama-3-70b | $2.75/百万输出 | $2.75 per million output tokens | |
| Replicate平台自部署 | meta/meta-llama-3-70b-instruct | $2.75/百万输出 | $2.75 per million output tokens | |
| Fal平台自部署 | Moondream3 Preview [Caption] | $3.5/百万输出 | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| Fal平台自部署 | Moondream3 Preview [Detect] | $3.5/百万输出 | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| Fal平台自部署 | Moondream3 Preview [Point] | $3.5/百万输出 | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| Fal平台自部署 | Moondream 3 Preview [Query] | $3.5/百万输出 | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| Replicate平台自部署 | ibm-granite/granite-speech-3.3-8b | $4.9/百万输出 | $4.90 per million output tokens | |
| Replicate平台自部署 | deepseek-ai/deepseek-r1 | $10/百万输出 | $0.01 per thousand output tokens |
每百万 token5
| 平台 | 模型 · 计价项 | 美元 | 平台原文 | 生效于 |
|---|---|---|---|---|
| Fal平台自部署 | Bytedance Seed V2 Mini | $0.1/百万 token最低 | $0.0001 / 1000 tokens | |
| Fal平台自部署 | NVIDIA Nemotron 3.5 Super Text | $10/百万 token | $0.01 / 1000 tokens | |
| Fal平台自部署 | Nemotron 3 Nano Omni | $10/百万 token | $0.01 / 1000 tokens | |
| Fal平台自部署 | Marlin | $15/百万 token | $0.015 / 1000 tokens | |
| Fal平台自部署 | Marlin Find | $15/百万 token | $0.015 / 1000 tokens |
每千字符2
| 平台 | 模型 · 计价项 | 美元 | 平台原文 | 生效于 |
|---|---|---|---|---|
| Fal平台自部署 | Moondream2 | $0.01/千字符最低 | $0.01 / 1000 characters | |
| Fal平台自部署 | Moondream2 | $0.01/千字符最低 | $0.01 / 1000 characters |
按计算秒数10
| 平台 | 模型 · 计价项 | 美元 | 平台原文 | 生效于 |
|---|---|---|---|---|
| Fal平台自部署 | Ffmpeg Api | $0.00017/计算秒最低 | $0.00017 / compute seconds | |
| Fal平台自部署 | FFmpeg API Metadata | $0.00017/计算秒最低 | $0.00017 / compute seconds | |
| Fal平台自部署 | FFmpeg API Waveform | $0.00017/计算秒最低 | $0.00017 / compute seconds | |
| Fal平台自部署 | Florence 2 Large Caption | $0.0013/计算秒 | $0.00125 / compute seconds | |
| Fal平台自部署 | Florence 2 Large Detailed Caption | $0.0013/计算秒 | $0.00125 / compute seconds | |
| Fal平台自部署 | Florence-2 Large | $0.0013/计算秒 | $0.00125 / compute seconds | |
| Fal平台自部署 | Florence 2 Large OCR | $0.0013/计算秒 | $0.00125 / compute seconds | |
| Fal平台自部署 | Florence 2 Large Region To Category | $0.0013/计算秒 | $0.00125 / compute seconds | |
| Fal平台自部署 | Florence-2 Large | $0.0013/计算秒 | $0.00125 / compute seconds | |
| Fal平台自部署 | LLaVA v1.6 34B | $0.0013/计算秒 | $0.00125 / compute seconds |