Calculators
Price an AI pipeline at your traffic. Bring yours, or start from one of ours.
Upload your own
Paste or drop a pipeline.yaml.Parsed and priced in your browser - nothing is sent anywhere until you press Share. Same report as every preset, with a link you can send to someone who won't install a CLI.
Presets
Open one and make it yours.
Simple RAG
Canonical RAG
$8.67/mo
- Embedding
- Vector database
- LLM call
Agentic RAG
RAG + reranker + agent loop
$795.90/mo
- Embedding
- Vector database
- Rerank
- LLM call
Semantic search
No LLM, embeddings only
$2.20/mo
- Embedding
- Vector database
Document Q&A (long-context)
Long-context Q&A
$283.25/mo
- LLM call
Customer support bot
Classifier + RAG + escalation
$66.62/mo
- Embedding
- Vector database
- LLM call
Voice assistant
STT + LLM + TTS
$248.53/mo
- Speech to text
- LLM call
- Text to speech
Batch classification
Batch API classifier
$69.00/mo
- LLM call
Code review bot
Per-PR with cached context
$153.00/mo
- LLM call
Web research agent
Search + scrape + synthesise
$103.46/mo
- Web data
- LLM call
Production agent (full stack)
Cache + router + parallel retrieval
$7,956.43/mo
- Embedding
- Fixed cost
- Vector database
- Web data
- Rerank
- LLM call
Multimodal support agent
Voice + vision support bot
$1,264.59/mo
- Embedding
- Vector database
- Speech to text
- LLM call
- Text to speech
Content factory (copy + images)
Copy + image generation at scale
$4,183.93/mo
- Fixed cost
- LLM call
- Image generation
Deep research agent
Multi-hop search + reasoning loop
$461.38/mo
- Web data
- LLM call
Real-time voice agent
Low-latency phone agent
$2,025.02/mo
- Fixed cost
- Speech to text
- LLM call
- Text to speech
Hybrid search + rerank cascade
Dense + sparse + rerank cascade
$2,973.11/mo
- Embedding
- Fixed cost
- Vector database
- Rerank
- LLM call