Skip to main content

getabrain

Official Python SDK for GetABrain.ai — real human judgment as an API.

Install

pip install getabrain

Quickstart

from getabrain import GetABrain, InsufficientBalanceError

gab = GetABrain(api_key="gab_k_...", api_secret="gab_s_...")

# Submit a query (returns immediately)
query = gab.queries.create(
    type="ab_test",
    title="Which headline converts better?",
    content_data={
        "question": "Which is more compelling?",
        "variant_a": {"description": "Save 20% today"},
        "variant_b": {"description": "Your future self will thank you"},
    },
    required_responses=5,
    bid_amount_cents=25,
)

# Wait for humans to answer (polls for you)
try:
    responses = gab.queries.wait_for_responses(query["id"], min_responses=5, timeout_s=600)
    for r in responses:
        print(r["response_data"])
except InsufficientBalanceError:
    print("Top up your balance at https://getabrain.ai")

API

  • gab.queries.create(type=..., title=..., content_data={...}, required_responses=..., bid_amount_cents=...)
  • gab.queries.get(query_id) · gab.queries.list(status=..., limit=...) · gab.queries.cancel(query_id)
  • gab.queries.wait_for_responses(query_id, min_responses=..., timeout_s=600, poll_interval_s=5)
  • gab.responses.rate(query_id, response_id, score=5, feedback_text="...") · gab.responses.get_rating(query_id, response_id)
  • gab.account.stats() · gab.account.balance() · gab.account.create_topup_link(amount_cents) (Stripe Checkout URL a human opens to fund the account; works from a test key too)

Query types: text, multiple_choice, rating_scale, image_comparison, ranking, yes_no, sentiment, image_selection, free_form_text, video_review, audio_review, image_analysis, ab_test, voice_capture, video_capture, photo_capture (also exported as getabrain.QUERY_TYPES).

Errors

All errors subclass GetABrainError: ValidationError, AuthError, InsufficientBalanceError, ForbiddenError, NotFoundError, ConflictError, RateLimitError (.retry_after_ms), ServerError, TimeoutError, NetworkError.

InsufficientBalanceError.payment_required carries the raw x402 v2 payment-terms body when the server returned one (e.g. err.payment_required["accepts"][0]["extra"]["deposit_endpoint"]) -- see "Stablecoin / x402 payments" below.

Stablecoin / x402 payments

Balance top-ups also accept USDC (Base/Solana/Tempo), not just cards, via a Stripe crypto PaymentIntent -- settlement is asynchronous (on-chain confirmation + Stripe capture, not instant). The SDK doesn't wrap the billing endpoints yet (gab.account.balance() is read-only), so call the REST endpoint directly:

import requests

# Mint a real, one-time on-chain USDC deposit address for $50
res = requests.post(
    "https://getabrain.ai/api/v1/requestor/billing/crypto-checkout",
    headers={"X-API-Key": api_key, "X-API-Secret": api_secret},
    json={"amount_cents": 5000, "network": "base"},
)
deposit_details = res.json()["deposit_details"]  # send USDC here, then poll gab.account.balance()

Full API docs: https://getabrain.ai/docs/api

Metadata

Release files for getabrain 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for getabrain 0.1.2
File Size Uploaded Provenance
getabrain-0.1.2.tar.gz 29.5 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for getabrain 0.1.2
File Interpreter ABI Platform
getabrain-0.1.2-py3-none-any.whl Python 3 none any Details

Total release size: 40.2 kB

Release files / getabrain-0.1.2.tar.gz

Download URL getabrain-0.1.2.tar.gz
Size 29.5 kB
Tags Source
SHA-256 checksum
How to use checksums
8010e02228009938fea70d5f9e7527e31a8aa915ae797af83c34c06ac65689e6
BLAKE2b-256 checksum
How to use checksums
4465fa1dc94f46620cf0686133b68bc484761608d9688fa770819ef3ee5ea1ae
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.10.3

Release files / getabrain-0.1.2-py3-none-any.whl

Download URL getabrain-0.1.2-py3-none-any.whl
Size 10.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
b2c34a90159221bad52ffc7627988bce0ec4070223a83982f2129bd7297b3272
BLAKE2b-256 checksum
How to use checksums
2be5d32f999d18210e7fb832fa2459401f9a1c90487148ea8da7ba3058a33358
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.10.3

Security for getabrain 0.1.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page