docs(ai): improve recommended orchestrator pricing (#690)

EAsuperstar · rickstaa · web-flow · commit 8127dcd6526b · 2024-11-18T21:55:33.000+01:00
This commit enhances the recommended pricing documentation, providing orchestrators with clearer guidance for setting their initial prices effectively.

---------

Co-authored-by: Rick Staa &lt;rick.staa@outlook.com&gt;
diff --git a/ai/orchestrators/models-config.mdx b/ai/orchestrators/models-config.mdx
@@ -25,50 +25,27 @@ currently **recommended** models and their respective prices.
   {
     "pipeline": "text-to-image",
     "model_id": "SG161222/RealVisXL_V4.0_Lightning",
-    "price_per_unit": 4768371
-  },
-  {
-    "pipeline": "image-to-image",
-    "model_id": "timbrooks/instruct-pix2pix",
-    "price_per_unit": 4768371
+    "price_per_unit": 4768371,
   },
   {
     "pipeline": "upscale",
     "model_id": "stabilityai/stable-diffusion-x4-upscaler",
-    "price_per_unit": 4768371
+    "price_per_unit": "0.5e-2USD",
+    "warm": true,
+    "optimization_flags": {
+      "SFAST": true,
+      "DEEPCACHE": false
+    }
   },
   {
     "pipeline": "audio-to-text",
     "model_id": "openai/whisper-large-v3",
     "price_per_unit": 12882811,
+    "pixels_per_unit": 1,
+    "currency": "USD",
     "url": "<CONTAINER_URL>:<PORT>",
     "token": "<OPTIONAL_BEARER_TOKEN>",
     "capacity": 1
-  },
-  {
-    "pipeline": "segment-anything-2",
-    "model_id": "facebook/sam2-hiera-large",
-    "price_per_unit": 3565,
-    "pixels_per_unit": 1e13,
-    "currency": "USD",
-    "warm": true
-  },
-  {
-    "pipeline": "image-to-video",
-    "model_id": "stabilityai/stable-video-diffusion-img2vid-xt-1-1",
-    "price_per_unit": 3390842,
-    "warm": true,
-    "optimization_flags": {
-      "SFAST": true,
-      "DEEPCACHE": false
-    }
-  },
-  {
-    "pipeline": "text-to-speech",
-    "model_id": "parler-tts/parler-tts-large-v1",
-    "price_per_unit": 11,
-    "pixels_per_unit": 1e2,
-    "currency": "USD"
   }
 ]
 ```
diff --git a/ai/pipelines/audio-to-text.mdx b/ai/pipelines/audio-to-text.mdx
@@ -107,6 +107,21 @@ The following system requirements are recommended for optimal performance:
 - [NVIDIA GPU](https://developer.nvidia.com/cuda-gpus) with **at least 12GB** of
   VRAM.
 
+## Recommended Pipeline Pricing
+
+<Note>
+  We are planning to simplify the pricing in the future so orchestrators can set
+  one AI price per compute unit and have the system automatically scale based on
+  the model's compute requirements.
+</Note>
+
+The pricing for the `audio-to-text` pipeline is based on competitor pricing.
+However, we strongly encourage orchestrators to set their own pricing based on
+their costs and requirements. Setting a competitive price will help attract more
+jobs, as Gateways can set their maximum price for a job. The currently
+recommended pricing for this pipeline is `0.02e-6 USD` per **milliseconds** of
+audio input.
+
 ## API Reference
 
 <Card
diff --git a/ai/pipelines/image-to-image.mdx b/ai/pipelines/image-to-image.mdx
@@ -141,6 +141,21 @@ The following system requirements are recommended for optimal performance:
 - [NVIDIA GPU](https://developer.nvidia.com/cuda-gpus) with **at least 20GB** of
   VRAM.
 
+## Recommended Pipeline Pricing
+
+<Note>
+  We are planning to simplify the pricing in the future so orchestrators can set
+  one AI price per compute unit and have the system automatically scale based on
+  the model's compute requirements.
+</Note>
+
+The pricing for the `image-to-image` pipeline is based on competitor pricing.
+However, we strongly encourage orchestrators to set their own pricing based on
+their costs and requirements. Setting a competitive price will help attract more
+jobs, as Gateways can set their maximum price for a job. The current recommended
+pricing for this pipeline is `1.9073484e-08 USD` per **input pixel**
+(`height * width * output images`).
+
 ## API Reference
 
 <Card
diff --git a/ai/pipelines/image-to-video.mdx b/ai/pipelines/image-to-video.mdx
@@ -126,6 +126,21 @@ The following system requirements are recommended for optimal performance:
 - [NVIDIA GPU](https://developer.nvidia.com/cuda-gpus) with **at least 24GB** of
   VRAM.
 
+## Recommended Pipeline Pricing
+
+<Note>
+  We are planning to simplify the pricing in the future so orchestrators can set
+  one AI price per compute unit and have the system automatically scale based on
+  the model's compute requirements.
+</Note>
+
+The pricing for the `image-to-video` pipeline is based on competitor pricing.
+However, we strongly encourage orchestrators to set their own pricing based on
+their costs and requirements. Setting a competitive price will help attract more
+jobs, as Gateways can set their maximum price for a job. The current recommended
+pricing for this pipeline is `1.3563368e-08 USD` per **output pixel**
+(`height * width * frames`).
+
 ## API Reference
 
 <Card
diff --git a/ai/pipelines/segment-anything-2.mdx b/ai/pipelines/segment-anything-2.mdx
@@ -104,6 +104,21 @@ The following system requirements are recommended for optimal performance:
 - [NVIDIA GPU](https://developer.nvidia.com/cuda-gpus) with **at least 6GB** of
   VRAM.
 
+## Recommended Pipeline Pricing
+
+<Note>
+  We are planning to simplify the pricing in the future so orchestrators can set
+  one AI price per compute unit and have the system automatically scale based on
+  the model's compute requirements.
+</Note>
+
+The pricing for the `segment-anything-2` pipeline is based on competitor
+pricing. However, we strongly encourage orchestrators to set their own pricing
+based on their costs and requirements. Setting a competitive price will help
+attract more jobs, as Gateways can set their maximum price for a job. The
+current recommended pricing for this pipeline is `3.22e-11 USD` per **input
+pixel** (`height * width`).
+
 ### Pipeline-Specific Image
 
 To serve the `segment-anything-2` pipeline, you must use a pipeline specific AI
diff --git a/ai/pipelines/text-to-image.mdx b/ai/pipelines/text-to-image.mdx
@@ -37,8 +37,8 @@ The current warm model requested for the `text-to-image` pipeline is:
 Furthermore, several Orchestrators are currently maintaining the following model
 in a ready state:
 
-- [ByteDance/SDXL-Lightning](https://huggingface.co/ByteDance/SDXL-Lightning):
-  A high-performance diffusion model developed by ByteDance.
+- [ByteDance/SDXL-Lightning](https://huggingface.co/ByteDance/SDXL-Lightning): A
+  high-performance diffusion model developed by ByteDance.
 
 <Tip>
   For faster responses with different
@@ -157,6 +157,21 @@ The following system requirements are recommended for optimal performance:
 - [NVIDIA GPU](https://developer.nvidia.com/cuda-gpus) with **at least 24GB** of
   VRAM.
 
+## Recommended Pipeline Pricing
+
+<Note>
+  We are planning to simplify the pricing in the future so orchestrators can set
+  one AI price per compute unit and have the system automatically scale based on
+  the model's compute requirements.
+</Note>
+
+The pricing for the `text-to-image` pipeline is based on competitor pricing.
+However, we strongly encourage orchestrators to set their own pricing based on
+their costs and requirements. Setting a competitive price will help attract more
+jobs, as Gateways can set their maximum price for a job. The current recommended
+pricing for this pipeline is `1.9073484e-08 USD` per **output pixel**
+(`height * width * output images`).
+
 ## API Reference
 
 <Card
diff --git a/ai/pipelines/text-to-speech.mdx b/ai/pipelines/text-to-speech.mdx
@@ -83,6 +83,20 @@ The following system requirements are recommended for optimal performance:
 - [NVIDIA GPU](https://developer.nvidia.com/cuda-gpus) with **at least 12GB** of
   VRAM.
 
+## Recommended Pipeline Pricing
+
+<Note>
+  We are planning to simplify the pricing in the future so orchestrators can set
+  one AI price per compute unit and have the system automatically scale based on
+  the model's compute requirements.
+</Note>
+
+The pricing for the `text-to-speech` pipeline is based on competitor pricing.
+However, we strongly encourage orchestrators to set their own pricing based on
+their costs and requirements. Setting a competitive price will help attract more
+jobs, as Gateways can set their maximum price for a job. The current recommended
+pricing for this pipeline is `1.5e-6 USD` per **character**.
+
 ### Pipeline-Specific Image
 
 To serve the `text-to-speech` pipeline, you must use a pipeline specific AI
diff --git a/ai/pipelines/upscale.mdx b/ai/pipelines/upscale.mdx
@@ -121,6 +121,21 @@ The following system requirements are recommended for optimal performance:
 - [NVIDIA GPU](https://developer.nvidia.com/cuda-gpus) with **at least 24GB** of
   VRAM.
 
+## Recommended Pipeline Pricing
+
+<Note>
+  We are planning to simplify the pricing in the future so orchestrators can set
+  one AI price per compute unit and have the system automatically scale based on
+  the model's compute requirements.
+</Note>
+
+The pricing for the `upscale` pipeline is based on competitor pricing. However,
+we strongly encourage orchestrators to set their own pricing based on their
+costs and requirements. Setting a competitive price will help attract more jobs,
+as Gateways can set their maximum price for a job. The current recommended
+pricing for this pipeline is `1.9073484e-08 USD` per **input pixel**
+(`height * width`).
+
 ## API Reference
 
 <Card
