For developers

Cheap batch compute,
one import away.

Drop-in SDKs for the expensive parts of your AI stack — embeddings, transcription, OCR, rerankers. Same interfaces you already use. A fraction of the cost.

Read the docs →See pricing

pip install commoncompute·npm i @commoncompute/sdk

quickstart.pypython

1# Embed 10M documents with one call
2from commoncompute import Client
3
4cc = Client(api_key="cc_live_…")
5
6job = cc.embeddings.batch(
7    model="bge-large-en-v1.5",
8    inputs=open("docs.jsonl"),
9    priority="batch",  # 3–6× cheaper than realtime
10    max_spend_usd=50,  # hard cap
11)
12
13for result in job.stream():
14    db.upsert(result.id, result.vector)

Examples

Idiomatic SDK, one-liners per workload.

Embeddings

Bulk vector generation for search, RAG, clustering.

embeddings.pypython

1# Nightly re-embed of 10M product descriptions
2job = cc.embeddings.batch(
3    model="bge-large-en-v1.5",
4    inputs=stream_from_pg("products"),
5    priority="batch",
6)

Drop-in compatibility

Change the import. Keep everything else.

Our SDKs mirror the interfaces you already call. No surgery on retry logic, serialization, or types — just a one-line swap at the top of the file.

Provider
What you have
What to use instead
Coverage

OpenAI

from openai import OpenAI

from commoncompute import OpenAICompat as OpenAI

Embeddings, moderation

Cohere

import cohere

from commoncompute import CohereCompat as cohere

Rerank, embed

AWS Transcribe

import boto3

from commoncompute import TranscribeCompat as boto3

Bulk transcription

HuggingFace

from transformers import pipeline

from commoncompute import pipeline

Any supported model

Guarantees

Production-grade, not a hobbyist cluster.

Deterministic quotes

Every job is priced before it runs. The number you see at submission is the number you pay.

Sandboxed execution

Your code runs in signed, ephemeral containers. No shared state between tenants. No logs retained by default.

Signed receipts

Every completed task emits a cryptographic receipt. Audit trail, attributable to the node that ran it.

Exactly-once semantics

Dedup keys per-task. Reconnect, restart, or re-run without duplicate work or double-billing.

Hard spend caps

Set a max_spend_usd. We pause the job before we cross it, never after.

No lock-in

Compatible interfaces mean you can move back to hyperscalers any time by flipping a flag.

Walkthrough

Watch the first task land.

Walkthrough · 90 sec

Submit your first job in 60 seconds

From npm install to a signed receipt — keys, quote, dispatch, result. Recorded against the live network.

Sign up at commoncompute.ai/signup (you get $5 in credits).
Copy your API key from the dashboard.
npm install @commoncompute/sdk-node.
Submit a small job — embeddings is cheapest.
Inspect the signed receipt the network returns.

Run one job. See it land.

Free credits on signup. No card. No cluster setup. You'll know in five minutes whether this is cheaper.