Agent Pricing
Orion agents use a variety of specialized capabilities for image, video, and document processing. Each capability has a credit cost based on the processing tier selected. The current conversion rate is:100 credits = $1
Pricing by Category
Agent capabilities are priced based on the computational resources required. Select between Fast, Auto, and Pro tiers depending on your use case.- Auto (
vlmrun-orion-1:auto) uses theFasttier tools by default, and is recommended for prototyping and high-volume processing. The agent will automatically select theProtier tools for more complex tasks. This is the default tier for Orion agents. - Fast (
vlmrun-orion-1:fast) uses theFasttier tools, and is recommended for speed and cost-efficiency, using lighter models that process requests quickly. - Pro (
vlmrun-orion-1:pro) uses theProtier tools, and is recommended for production use cases requiring maximum quality, using more powerful models that produce higher quality results but take longer and cost more.
Image
Image capabilities are priced credits per image.| Capability | Description | Fast | Pro |
|---|---|---|---|
| Caption & Tag | Generate captions and tags for images | 1 | 2 |
| Detect, Point, Segment | Detect objects, point to objects, and segment regions | 1 | 2 |
| UI Parsing | Parse UI elements from screenshots and application images | 1 | 2 |
| Generate & Edit | Generate or edit images from text prompts | 4 | 24 |
| Tools | Image I/O, rotation, cropping, and other utilities | Free | Free |
Document
Document capabilities are priced credits per page.| Capability | Description | Fast | Pro |
|---|---|---|---|
| OCR, Layout | Extract text and detect layout elements from documents | 0.10 / page | 0.40 / page |
| Parsing | Parse and extract structured data from documents | 1 / page | 2 / page |
| Tools | Document I/O, page navigation, and other utilities | 0 | 0 |
Video
Video capabilities are priced credits per hour of input video or credits per second of generated output video. The standard output is approximately 6 seconds.| Capability | Description | Fast | Pro |
|---|---|---|---|
| Caption, Summary, & Tag | Generate captions, summaries, and tags for video content | 20 / hour | 80 / hour |
| Generate & Edit | Generate video from text prompts and optional input images | 15 / sec | 40 / sec |
| Tools | Video I/O, sampling, trimming, and other utilities | 0 | 0 |
Standard video generation produces approximately 6 seconds of video, resulting in approximately 240 credits for Pro tier (40 cr/s x 6s) = $2.40 (at $1 per 100 credits).
Total Cost Calculation
Examples
These examples show how credits are calculated for common multi-step agent workflows usingvlmrun-orion-1:auto (Auto/Fast) or vlmrun-orion-1:pro (Pro).
1. Create 3 highlights from a 10-minute video and trim
1. Create 3 highlights from a 10-minute video and trim
| Step | Capability | Auto / Fast | Pro |
|---|---|---|---|
| Caption & analyze video | Caption & Tag (10 min) | 3.33 credits | 13.33 credits |
| Trim 3 highlight clips | Tools | 0 credits | 0 credits |
| Total | 3.33 credits ($0.033) | 13.33 credits ($0.133) |
2. Create a 5-part storyboard with generated video
2. Create a 5-part storyboard with generated video
| Step | Capability | Auto / Fast | Pro |
|---|---|---|---|
| Generate 5 storyboard images | Generate & Edit (5x) | 20 credits | 120 credits |
| Generate 5 video clips (6s each) | Generate & Edit (30s total) | 450 credits | 1200 credits ($12.00) |
| Total | 470 credits ($4.70) | 1320 credits ($13.20) |
3. Detect and segment objects in an image, then visualize
3. Detect and segment objects in an image, then visualize
| Step | Capability | Auto / Fast | Pro |
|---|---|---|---|
| Detect objects in image | Detection | 1 credits | 2 credits |
| Segment detected objects | Segmentation | 1 credits | 2 credits |
| Apply visualization overlay | Tools | 0 credits | 0 credits |
| Total | 2 credits ($0.02) | 4 credits ($0.04) |
4. Process a 50-page document with OCR and parsing
4. Process a 50-page document with OCR and parsing
| Step | Capability | Auto / Fast | Pro |
|---|---|---|---|
| OCR & layout detection | OCR, Layout (50 pages) | 5 credits | 20 credits |
| Parse structured data | Parsing (50 pages) | 5 credits | 20 credits |
| Total | 10 credits ($0.10) | 40 credits ($0.40) |
FAQ
What's the difference between Auto, Fast and Pro tiers?
What's the difference between Auto, Fast and Pro tiers?
Auto (
vlmrun-orion-1:auto) and Fast (vlmrun-orion-1:fast) are optimized for speed and cost-efficiency, using lighter models that process requests quickly. Pro (vlmrun-orion-1:pro) uses more powerful models that produce higher quality results but take longer and cost more. Choose Auto/Fast for prototyping and high-volume processing, and Pro for production use cases requiring maximum quality.How is the total cost of the agent execution priced?
How is the total cost of the agent execution priced?
The total cost of the agent execution is the sum of the credits used for the tools, and the cost of the orchestration. For non-integer credits, we round up to the nearest credit.
How is the cost of the chat portion priced (excluding tools)?
How is the cost of the chat portion priced (excluding tools)?
The cost of the chat completion is priced per token. This is merely a simple cost overhead for orchestration, which we do not charge for if the cost of the single chat completion is less than 1 credit.
Are there any free tools?
Are there any free tools?
Yes, utility tools like image I/O, basic editing operations, video sampling/trimming, and document navigation are included at no additional credit cost when used within an agent session. However, the base agent session cost still applies.