CommonCompute
Get startedDownload the Mac app
Pricing

Locked quote. Pay only on success.

Every job returns its exact price before it runs, capped by your max_spend_usd. Failed jobs are never billed. We're the cheapest in the market on the workloads Apple Silicon was built for.

Apple-Silicon-native workloads

Apple Neural Engine, Apple Vision, VideoToolbox, Translation, MLX. Hardware NVIDIA clouds don't have. We're the cheapest option in the market on every row below.

Workload
Unit
Batch
Realtime
Compare against
Savings
OCR (Apple Vision)
per 1k pages
$1.05
$2.10
AWS Textract @ $1.50
−30%
Transcription (Whisper)
per audio hour
$0.25
$0.50
OpenAI Whisper API @ $0.36
−30%
Reranking
per 1k queries
$0.70
$1.40
Cohere Rerank @ $1.00
−30%
iOS test farm (XCTest)Soon
per test minute
$0.70
$1.40
Sauce Labs @ ~$1/min
−30%
Translation
per 1M chars
$14.00
$28.00
Google Translate @ $20
−30%
Background removal
per image
$0.14
$0.28
remove.bg @ $0.20
−30%
Face detection
per 1k images
$0.70
$1.40
AWS Rekognition @ $1.00
−30%
Object detection
per 1k images
$0.70
$1.40
AWS Rekognition @ $1.00
−30%
Pose estimation
per 1k images
$0.70
$1.40
AWS Rekognition @ $1.00
−30%
Barcode / QR scanning
per scan
$0.0007
$0.0014
AWS Rekognition @ $0.001
−30%
Image segmentation
per image
$0.038
$0.077
Replicate SAM @ $0.055
−30%
Image upscale (2×/4×)Soon
per image
$0.0035
$0.0070
Replicate Real-ESRGAN @ $0.005
−30%
Aesthetics scoring
per image
$0.0003
$0.0006
manual review
Language detection
per 1k texts
$0.70
$1.40
Google Natural Language @ $1.00
−30%
Entity extraction (NER)
per 1M tokens
$0.70
$1.40
AWS Comprehend @ $1.00
−30%
Sentiment analysis
per 1M chars
$0.70
$1.40
AWS Comprehend @ $1.00
−30%
Speaker diarizationPreview
per audio hour
$0.26
$0.52
AssemblyAI @ $0.37
−30%
Subtitle generation
per video hour
$0.32
$0.63
AssemblyAI @ $0.45
−30%
Audio cleanup
per audio hour
$0.067
$0.13
Krisp Enterprise (subscription)
Audio classification
per audio hour
$0.070
$0.14
ACRCloud @ $0.10
−30%
Text-to-speech
per 1k chars
$0.21
$0.42
ElevenLabs @ $0.30
−30%
Speech-to-text (on-device)Preview
per audio hour
$0.67
$1.34
Google Speech-to-Text @ ~$0.96/hr
−30%
Embeddings
per 1M tokens
$0.014
$0.028
Video transcode
per output minute
$0.012
$0.024
AWS MediaConvert @ $0.017
−30%
HEIC conversion (photo batches, ≤100 MB/file)
per GB
$0.012
$0.024
AWS MediaConvert @ ~$0.017/min
Video thumbnails
per image
$0.0021
$0.0042
Cloudinary @ $0.003
−30%
Scene detection
per video minute
$0.070
$0.14
AWS Rekognition @ $0.10
−30%
Image generationPreview
per image
$0.0019
$0.0038
Replicate SDXL @ $0.0055
−65%
Xcode build farmSoon
per build minute
$0.056
$0.11
GitHub Actions macOS @ $0.08/min
−30%
Safari / WebKit testingSoon
per test minute
$0.70
$1.40
Sauce Labs @ ~$1/min
−30%
Notarize + code-signSoon
per build minute
$0.056
$0.11
GitHub macOS runner @ $0.08/min
−30%
Core ML model conversionSoon
per build minute
$0.056
$0.11
GitHub macOS runner @ $0.08/min
−30%
Image similarity / dedup
per 1k images
$0.70
$1.40
AWS Rekognition @ $1.00
−30%
Image filters / transforms
per image
$0.0021
$0.0042
Cloudinary @ ~$0.003
−30%
Document segmentation
per scan
$0.0007
$0.0014
AWS Rekognition @ $0.001 per scan
−30%
Rectangle detection
per scan
$0.0007
$0.0014
AWS Rekognition @ $0.001 per scan
−30%
Hand pose detection
per 1k images
$0.70
$1.40
AWS Rekognition @ $1.00
−30%
Animal pose detection
per 1k images
$0.70
$1.40
AWS Rekognition @ $1.00
−30%
Saliency detection
per 1k images
$0.70
$1.40
AWS Rekognition @ $1.00
−30%
Animal recognition
per 1k images
$0.70
$1.40
AWS Rekognition @ $1.00
−30%
Image classification
per 1k images
$0.70
$1.40
AWS Rekognition @ $1.00
−30%
Person segmentation
per image
$0.14
$0.28
remove.bg @ $0.20
−30%
Trajectory detection
per video minute
$0.070
$0.14
AWS Rekognition Video @ $0.10
−30%
Optical flow
per video minute
$0.070
$0.14
AWS Rekognition Video @ $0.10
−30%
Video composition
per video minute
$0.070
$0.14
AWS Rekognition Video @ $0.10
−30%
PDF operations
per operation
$0.0056
$0.011
PDF.co @ ~$0.008 per operation
−30%
Create ML training
per train minute
$0.038
$0.077
Vertex AI AutoML @ ~$0.055/min
−30%
Loudness normalization
per audio hour
$0.030
$0.060
Auphonic (subscription)
Prices in USD. Batch tolerates 3–6 sec dispatch. Realtime is 2× batch (sub-second). Quotes locked at submission, capped by max_spend_usd. Failed tasks aren't billed.
Estimator

How much would your workload cost?

Workload
Priority
Volume
10 1k pages
Estimated cost
$10.50
OCR (Apple Vision) · batch · 10 1k pages
Unit price$1.050 / 1k pages
vs. hyperscalersave 30%

Also available

H100-class hardware wins on price for these workloads. We support them so you can hit one API for everything — but if price is the only thing that matters, route them to a hyperscale inference host.

Workload
Unit
Batch
Realtime
Compare against
Savings
Transcription (Parakeet)
per audio hour
$0.25
$0.50
OpenAI Whisper API @ $0.36
−30%
Image captioning
per 1k images
$0.35
$0.70
GPT-4o vision @ ~$0.50
−30%
Stable Diffusion (SDXL)Preview
per image
$0.0039
$0.0077
Replicate SDXL @ $0.0055
PyTorch (MPS)Soon
per GPU minute
$0.0091
$0.018
RunPod A100 Spot @ $0.013/min
Blender (Metal)Soon
per render minute
$0.021
$0.042
AWS Deadline + Spot @ ~$0.03/min
−30%
LoRA fine-tunePreview
per training minute
$0.055
$0.11
RunPod A100 on-demand @ ~$0.020/min
Small LLM (private RAG)
per 1M tokens
$0.070
$0.14
DeepInfra Llama 3.2 1B @ $0.02 in / $0.05 out
Vision Q&A / doc understanding
per 1k images
$0.35
$0.70
GPT-4o vision @ ~$0.50
−30%
Frontier LLM (405B+, clustered)Soon
per 1M tokens
$2.10
$4.20
Fireworks Llama 405B @ ~$3.00
On-device LLM (Apple Foundation)
per 1M tokens
$0.42
$0.84
OpenAI gpt-4o-mini @ $0.60
Custom batchSoon
quoted
Bring-your-own container
Same per-task contract as featured workloads — locked quote, max_spend cap, no charges on failure. Pricing reflects honest provider cost on Apple Silicon, not a market-matched price.
FAQ

Pricing, explained.

How do you charge so little?
The hardware is already bought, powered, and idle. No data centers, no cooling, no hyperscaler markup — just Apple Silicon that would otherwise sit unused.
Are quotes really locked?
Yes. Every submission returns a deterministic price before execution. Tasks that would exceed your max_spend_usd are paused, not silently billed.
What counts as "batch" vs "realtime"?
Batch tolerates 3–6 sec dispatch — runs on the cheapest available capacity. Realtime gets priority dispatch — good for interactive workloads, 2× the price.
Why is chat priced so much higher than Together / Groq?
Apple Silicon serves transformer chat at maybe 1/100th the throughput of an H100. We won't pretend otherwise — chat is in the catalog so you can hit one API for everything, but at honest cost. For pure chat workloads, Together / Groq / Fireworks will be cheaper.
Do you charge for failed tasks?
No. Only successful, receipted results are billed. Retries are free.
Is there a free tier?
No free tier or trial. You add a card, buy credit ($10 minimum), and jobs draw against that balance at the quoted price — you only pay for successful work. An evaluation across the featured catalog costs well under a dollar of that credit, and whatever you don't spend stays on your account.
Can I get volume pricing?
Yes. Per-task prices step down automatically as your monthly usage grows — your dashboard shows your current rate. For sustained volume above ~$5k/mo we also offer reserved capacity and dedicated provider pools; contact sales.