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

T
Troy Hunt's Blog
Y
Y Combinator Blog
云风的 BLOG
云风的 BLOG
B
Blog RSS Feed
S
Securelist
H
Help Net Security
Security Archives - TechRepublic
Security Archives - TechRepublic
S
Secure Thoughts
Spread Privacy
Spread Privacy
C
Check Point Blog
WordPress大学
WordPress大学
AWS News Blog
AWS News Blog
L
Lohrmann on Cybersecurity
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
P
Privacy International News Feed
T
The Exploit Database - CXSecurity.com
N
News and Events Feed by Topic
Blog — PlanetScale
Blog — PlanetScale
PCI Perspectives
PCI Perspectives
T
Tor Project blog
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
C
Cyber Attacks, Cyber Crime and Cyber Security
Google Online Security Blog
Google Online Security Blog
The Hacker News
The Hacker News
宝玉的分享
宝玉的分享
www.infosecurity-magazine.com
www.infosecurity-magazine.com
C
Cisco Blogs
Last Week in AI
Last Week in AI
Webroot Blog
Webroot Blog
GbyAI
GbyAI
I
InfoQ
罗磊的独立博客
The GitHub Blog
The GitHub Blog
Google DeepMind News
Google DeepMind News
Latest news
Latest news
P
Palo Alto Networks Blog
博客园 - Franky
T
Threat Research - Cisco Blogs
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
S
Security Affairs
H
Hacker News: Front Page
P
Privacy & Cybersecurity Law Blog
小众软件
小众软件
The Register - Security
The Register - Security
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
B
Blog
V
Vulnerabilities – Threatpost
人人都是产品经理
人人都是产品经理
博客园_首页
aimingoo的专栏
aimingoo的专栏

Replicate's changelog

Agent skills for Replicate – 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 Set deadlines for predictions – 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 Environment variables in running containers – Replicate changelog Slimmer API responses for model metadata – Replicate changelog The little things, week ending June 6, 2025 – Replicate changelog Faster, cheaper Flux training – Replicate changelog The little things, week ending May 23, 2025 – Replicate changelog Streaming text support in the playground – Replicate changelog Web URLs now in prediction objects – Replicate changelog Iterate in playground with audio support – Replicate changelog NVIDIA H100 GPUs now available – Replicate changelog More by this user – Replicate changelog The little things, week ending May 9, 2025 – Replicate changelog Copy docs directly to your LLM – Replicate changelog The little things, week ending April 25, 2025 – Replicate changelog The little things, week ending March 28, 2025 – Replicate changelog Simplified organizations – Replicate changelog The little things, week ending March 14, 2025 – Replicate changelog The little things, week ending February 28, 2025 – Replicate changelog Better prediction list – Replicate changelog The little things, week ending February 14, 2025 – Replicate changelog The little things, week ending January 31, 2025 – Replicate changelog Official models – Replicate changelog The little things, week ending January 17, 2025 – Replicate changelog The little things, week ending December 20, 2024 – Replicate changelog Language model training no longer supported – Replicate changelog GPU memory monitoring – Replicate changelog The little things, week ending December 06, 2024 – Replicate changelog The little things, week ending November 22, 2024 – Replicate changelog The little things, week ending November 8, 2024 – Replicate changelog A fond farewell to Python 3.7 – Replicate changelog The little things, week ending October 25, 2024 – Replicate changelog Dark mode – Replicate changelog Playground (beta) – Replicate changelog New documentation – Replicate changelog Synchronous API – Replicate changelog Large log outputs might be truncated – Replicate changelog Time limit for sharing predictions – Replicate changelog View training outputs on the web – Replicate changelog API for searching public models – Replicate changelog Streams always available, stream parameter deprecated – Replicate changelog Secret inputs for models – Replicate changelog Disable API tokens – Replicate changelog RSS and Atom feeds – Replicate changelog Delete stuff – Replicate changelog Docs and client library support for webhook verification – Replicate changelog Search for deployments – Replicate changelog Webhooks activity UI – Replicate changelog Improved validation for API prediction payloads – Replicate changelog T4 models now have more RAM – Replicate changelog GitHub secret scanning – Replicate changelog Bearer tokens – Replicate changelog Deployments API – Replicate changelog 3D viewer for GLB outputs – Replicate changelog Task-oriented collections – Replicate changelog Webhook verification – Replicate changelog Fine-tune SDXL from the web – Replicate changelog Compare image inputs to outputs – Replicate changelog Code snippets for every prediction – Replicate changelog API for creating models – Replicate changelog Improved training detail pages – Replicate changelog Prediction parameters as JSON – Replicate changelog API for listing public models – Replicate changelog Deployments – Replicate changelog Prediction query parameter – Replicate changelog Fullscreen training logs – Replicate changelog Dynamic status favicons – Replicate changelog Streaming output for language models – Replicate changelog Multiple API tokens for users – Replicate changelog A40 GPUs now available – Replicate changelog Hardware and pricing for trainable models – Replicate changelog Training API for language models – Replicate changelog
Fallback model for Nano Banana Pro – Replicate changelog
2026-03-02 · via Replicate's changelog

Nano Banana Pro can now fall back to a backup model (currently ByteDance Seedream 5.0 lite) when Google’s API is at capacity, instead of failing with a rate limit error.

How it works

Set allow_fallback_model to true when calling the API. If Nano Banana Pro hits a rate limit, it tries to generate the image with Seedream 5.0 lite instead. For certain inputs, for example if the aspect ratio isn’t supported, the original rate limit error is returned.

The fallback is off by default. If you don’t set allow_fallback_model, nothing changes — you’ll get a rate limit error when Google’s API is at capacity.

When the fallback is triggered, your logs still show a prediction to Nano Banana Pro. You can tell the fallback was used by checking the resolution field in your output — it says "fallback" instead of the actual resolution. You’re charged the cost of the fallback model, not Nano Banana Pro.

Limitations

Our current fallback model, Seedream 5.0 lite, doesn’t support all the same options as Nano Banana Pro:

  • Seedream 5.0 lite doesn’t support 1K resolution. If you request 1K, the fallback generates at 2K and downscales the result.
  • Seedream 5.0 lite doesn’t support 4K resolution. If you request 4K, the fallback won’t be used and the original rate limit error is returned.
  • Seedream 5.0 lite doesn’t support the 4:5 and 5:4 aspect ratios. Requests with these ratios won’t fall back and will return the original rate limit error.