replicate

library1.0.7pypypi✓ verified 28d ago

Python client for running ML models on Replicate's cloud API. v0.x stable client is at 1.x on PyPI. A v2.0 beta (replicate-python-beta) exists as a separate package with a redesigned API. replicate.stream() is deprecated in v2. Billing changed to prepaid credit for new accounts in July 2025.

ai-ml llm-agents http-networking

pip install replicate

github ↗package ↗homepage ↗

INSTALL

IMPORT

SIG · REPLICATE

replicate

ai-mlpythonv1.0.7

Install

4.0s avg

Import

598ms

Disk

32MB

Pass rate

10/ 10

Env Coverage10 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v2.0.0a16 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.910 runs

installs and imports cleanly · install 0.0s · import 0.632s · 33.5MB

glibc

py 3.10–3.910 runs

installs and imports cleanly · install 4.0s · import 0.564s · 33MB

32MB installed

● package 32MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

Client

✓ from replicate import Client

✗ import replicate

run

✓ from replicate import run

✗ import replicate

Run a model on Replicate. Requires REPLICATE_API_TOKEN environment variable.

import replicate output = replicate.run( "black-forest-labs/flux-schnell", input={"prompt": "an iguana on the beach"} ) # output is a list of FileOutput objects for image models with open('output.png', 'wb') as f: f.write(output[0].read())

Debug

Known issues

breakingreplicate.run() output for image models is a list of FileOutput objects, not URLs or strings. Treating output[0] as a string raises AttributeError.

fix

Use output[0].read() to get bytes, or output[0].url to get the URL string.

affects: >= 0.25.0

breakingv2.0 alpha (replicate-python-beta) has a completely redesigned API with replicate.use() replacing replicate.run(). The two packages are incompatible — do not mix v1 and v2 patterns.

fix

Stick to stable v1.x unless explicitly opting into the v2 beta. Do not install replicate-python-beta alongside replicate.

affects: 2.0.0a*

deprecatedreplicate.stream() is deprecated in v2 SDK. Still available for v1 backwards compatibility but will be removed.

fix

Use replicate.run() with stream=True parameter, or use predictions.create() with streaming for fine-grained control.

affects: >= 2.0.0

gotchaModel versions are pinned by hash in many tutorials (e.g. 'owner/model:abc123'). Pinned version hashes go stale as models are updated. Unpinned calls use the latest deployment which may have different inputs/outputs.

fix

Use versioned model strings for production ('owner/model:hash'). Check replicate.com/owner/model/versions for current hashes.

affects: all

gotchareplicate.run() is synchronous and blocks until the prediction completes. For long-running models this can block for minutes.

fix

Use replicate.predictions.create() to get a prediction ID immediately, then poll with predictions.get() or use AsyncReplicate for non-blocking calls.

affects: all

gotchaNew Replicate accounts (post July 2025) use prepaid credit billing, not monthly billing. API calls will fail with 402 if credit balance is zero, unlike monthly billing which allows negative balances until invoice.

fix

Add credit at replicate.com/account/billing before making API calls. Set up auto-reload to avoid unexpected failures.

affects: all

Upgrade

Version history

1.0.7latest on PyPI · released May 27, 2025

Audit

Dependencies

httpxrequiredHTTP client used internally. Installed automatically.

pydanticrequiredUsed for model input/output validation.

Agent activity

24 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/replicate/replicate-python ↗

packagehttps://pypi.org/project/replicate/ ↗

homepagehttps://replicate.com ↗