惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

J
Java Code Geeks
IT之家
IT之家
爱范儿
爱范儿
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
博客园_首页
Blog — PlanetScale
Blog — PlanetScale
V
Visual Studio Blog
云风的 BLOG
云风的 BLOG
MyScale Blog
MyScale Blog
阮一峰的网络日志
阮一峰的网络日志
Stack Overflow Blog
Stack Overflow Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
GbyAI
GbyAI
V
V2EX
N
Netflix TechBlog - Medium
Vercel News
Vercel News
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
T
The Blog of Author Tim Ferriss
量子位
博客园 - Franky
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
博客园 - 司徒正美
月光博客
月光博客
F
Fortinet All Blogs

Replicate's changelog

Agent skills for Replicate – Replicate changelog Fallback model for Nano Banana Pro – Replicate changelog MCP server auto-discovery – Replicate changelog Filter predictions by source – Replicate changelog The little things, week ending December 19, 2025 – Replicate changelog The little things, week ending December 5, 2025 – Replicate changelog The little things, week ending November 21, 2025 – Replicate changelog Code mode for Replicate's MCP server – Replicate changelog The little things, week ending November 7, 2025 – Replicate changelog Deployment setup monitoring – Replicate changelog The little things, week ending October 24, 2025 – Replicate changelog The little things, week ending October 10, 2025 – Replicate changelog Download invoices from billing settings – Replicate changelog Sort models by creation date via API – Replicate changelog Update model metadata via API – Replicate changelog The little things, week ending September 26, 2025 – Replicate changelog New search API, now in beta – Replicate changelog The little things, week ending September 12, 2025 – Replicate changelog Torch compile caching – Replicate changelog The little things, week ending August 29, 2025 – Replicate changelog The little things, week ending August 14, 2025 – Replicate changelog Run all models with the same API endpoint – Replicate changelog The little things, week ending August 1, 2025 – Replicate changelog Purchase prepaid credit – Replicate changelog Introducing a new Cog runtime – Replicate changelog The little things, week ending July 18, 2025 – Replicate changelog The little things, week ending July 4, 2025 – Replicate changelog Set a monthly spend limit deprecated – Replicate changelog See up to 24 hours of data on deployment metric graphs – Replicate changelog The little things, week ending June 20, 2025 – Replicate changelog
Set deadlines for predictions – Replicate changelog
2025-10-16 · via Replicate's changelog

You can now set a deadline to automatically cancel a prediction if it doesn’t complete within a specified duration. This is useful when you’re building real-time or interactive experiences, like a virtual try-on experience for an online clothing store. In this case, shoppers have usually moved on if an image takes more than 15 seconds to generate.

How it works

Set a deadline by including a Cancel-After header when creating a prediction. See our docs for details on the header format.

Here’s an example that sets a 1 minute deadline:

What happens when a deadline is reached

Replicate sets the prediction’s status to aborted if the deadline is reached before it starts running, and canceled if the deadline is reached while it’s running.

For public models, you’re only charged for predictions with a canceled status, not for aborted ones.

Deadline vs sync mode wait duration

Prediction deadlines and sync mode serve different purposes. Use prediction deadline (Cancel-After header) to control when the prediction itself should be canceled. Use sync mode (Prefer: wait header) to control how long the HTTP request stays open waiting for results.

You can also use both together. In the previous cURL example, Prefer: wait defaults to 1 min and we’ve explicitly set Cancel-After to 1 min. This means that the HTTP request will stay open for 1 minute to wait for results, after which the prediction will be canceled, even if it has not completed.

Alternatively, setting Cancel-After: 1m and Prefer: wait=10 means that the request returns after 10 seconds. If the prediction is still running, you’ll get an incomplete prediction object, and the prediction will continue to run until it completes or is canceled at the 1-minute deadline.

Read more in the docs: