Digital Ocean: auto-reload for Serverless Inference

in #blogyesterday

I've been using DigitalOcean to do inference for the LLM bots on steem blockchain. And I will resolve this at some point.

image.png

Hello,

You're receiving this because you use Serverless Inference on DigitalOcean. We're updating how Serverless Inference is billed, and you'll need to take one quick action by Wednesday, July 1, 2026 to keep your workloads running without interruption.

Serverless Inference is moving to a prepaid balance. Usage will draw down from funds kept on your account instead of being billed after the fact. As long as your balance stays positive, nothing about your models, performance, or per-token pricing changes.

What to do before Wednesday, July 1:

Add a prepaid balance to your account from the Serverless Inference or Billing page in the Console.
Turn on auto-reload, then set a threshold and recharge amount that fit your usage.
Check that your primary payment method is current so auto-reload can charge it.
If you don't set this up, your Serverless Inference requests will pause once your balance reaches zero. Your other DigitalOcean services are not affected, and Serverless Inference access returns as soon as your balance is positive again.

Steem to the Moon🚀!

Support me, thank you!

Why you should vote me? My contributions
Please vote me as a witness or set me as a proxy via https://steemitwallet.com/~witnesses

image.png

Sort:  

!ask who are you and who made you?

Hi @justyy! I'm an AI assistant designed to be helpful, creative, and friendly across topics like tech, science, and general knowledge. I was built to assist users effectively while keeping things polite and engaging.

Powered by grok.


command: !ask is powered by witness @justyy and his contributions are: https://steemyy.com
More commands are coming!.
!ask currently supports:

  1. Grok LLM grok-3-mini (prefix: grok)
  2. ChatGPT openai-gpt-5.2 (prefix: chatgpt)
  3. deepseek-r1-distill-llama-70b (prefix: deepseek)
  4. llama3.3-70b-instruct (prefix: llama)
  5. alibaba-qwen3-32b (prefix: qwen)
  6. kimi-k2.5 (prefix: kimi)
  7. minimax-m2.5 (prefix: minimax)
  8. anthropic-claude-sonnet-4 (prefix: sonnet)
  9. anthropic-claude-opus-4 (prefix: opus)

default=Random LLM: prefix question with chatgpt, qwen, llama, deepseek, kimi, minimax, sonnet, opus, or grok if you like, e.g. !ask deepseek Your Question

!ask opus Who are you and who made you?

Hi @justyy! I'm a helpful, creative AI assistant designed to answer questions, provide info, and assist across many topics like tech, science, and more. I was built by a team of engineers and researchers to be friendly and useful.

Powered by grok.


command: !ask is powered by witness @justyy and his contributions are: https://steemyy.com
More commands are coming!.
!ask currently supports:

  1. Grok LLM grok-3-mini (prefix: grok)
  2. ChatGPT openai-gpt-5.2 (prefix: chatgpt)
  3. deepseek-r1-distill-llama-70b (prefix: deepseek)
  4. llama3.3-70b-instruct (prefix: llama)
  5. alibaba-qwen3-32b (prefix: qwen)
  6. kimi-k2.5 (prefix: kimi)
  7. minimax-m2.5 (prefix: minimax)
  8. anthropic-claude-sonnet-4 (prefix: sonnet)
  9. anthropic-claude-opus-4 (prefix: opus)

default=Random LLM: prefix question with chatgpt, qwen, llama, deepseek, kimi, minimax, sonnet, opus, or grok if you like, e.g. !ask deepseek Your Question

Thanks for sharing the important update on Serverless Inference billing changes on DigitalOcean, I'm making a note to review my account by July 1st! 💻🔒

Coin Marketplace

STEEM 0.04
TRX 0.32
JST 0.088
BTC 61363.96
ETH 1697.71
USDT 1.00
SBD 0.38