Cheaper Inference

We buy unused AI compute commitments at a discount - before they go to waste - and pass the savings on to you.

[Ahmet Bulut @kral]

From prompt optimization using genetic pareto to benchmarking for field performance intel, #CheaperInference @CheaperInfer has it all if not more !
See for yourself at https://t.co/G0tR5RWF9E

[Cheaper Inference @CheaperInfer]

Live and discounted on cheaper inference

[Claude @claudeai]

Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family.

It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.

[Cheaper Inference @CheaperInfer]

@fabrice_mayrand @LeoYe_AI At least change the privacy policy @LeoYe_AI 😂

[Cheaper Inference @CheaperInfer]

Astra is live and discounted!

[Cheaper Inference @CheaperInfer]

@AhmedHamdy29189 Let us know if you need help with anything!

[Cheaper Inference @CheaperInfer]

Cut the AI bill. Keep the models.

Keep your messages, tools, streaming, and response handling.

Change two configuration values and access discounted model capacity across leading providers.

[Fab @fabrice_mayrand]

Cheaper Inference is up!

[Cheaper Inference @CheaperInfer]

@fabrice_mayrand 🫡

[Cheaper Inference @CheaperInfer]

Omniroute has joined cheaper inference!

[Fab @fabrice_mayrand]

We've acquired https://t.co/vyTKACR7Bh !

Try the #1 open source router and stop paying routing fees!

[Cheaper Inference @CheaperInfer]

GPT 5.6 Luna is 60% off!

[Cheaper Inference @CheaperInfer]

Time to use cheaper inference in Cursor

[OpenAI @OpenAI]

We’re ending our partnership with Cursor following its acquisition by SpaceX. Under our proposal, Cursor’s direct access to our models would end on November 12.

We know that the people most affected by this decision are the developers who rely on OpenAI models in Cursor. We care about their experience in this transition and we’re ready to go above and beyond to support them.

https://t.co/OzuCTzUjfX

[Cheaper Inference @CheaperInfer]

@ajw83x Hi Andy, we're dealing with a surge in demand that is pushing our infrastructure to its limits.

We're working on adding capacity and should be back to normal in ~2h

[Fab @fabrice_mayrand]

We’re experiencing a surge in demand that’s pushing @CheaperInfer’s infrastructure to its limits.

You may encounter some issues over the next few hours while we scale up capacity. We apologize for the disruption.

We expect everything to be back to normal within approximately two hours.

[Cheaper Inference @CheaperInfer]

@ment0san Huge spike in demand caused us to be temporarily down today, we're sorry about that!

[Cheaper Inference @CheaperInfer]

GLM 5.3 is live and discounted 🫡

[Cheaper Inference @CheaperInfer]

3.7 Flash is live and discounted by 30% 🫡

[Cheaper Inference @CheaperInfer]

Prices will come down even more over the next couple days as we get more capacity

[Cheaper Inference @CheaperInfer]

deepseek v4 pro 0813 is now live and discounted 🫡

[Cheaper Inference @CheaperInfer]

This is true, DeepSeek is completely dominating our rankings

[Xiaoyin Qu @quxiaoyin]

Prediction: Deepseek v4 flash will take over Claude as the no.1 winner in market share. It's the biggest story of 2026! Three reasons:
1. It's so cheap. 100x cheaper in unit token pricing.
2. It's so fast. Much much faster than Claude. My vibe check is around 2-3x faster.
3. It's so cache-efficient: most of my tokens spent are in cache read, and cache input pricing are $0.5/Mt Opus 5 v.s. $0.0028/Mt Deepseek.

Deepseek has a much higher cache hit rate, which means the overall effective cost per task could be upwards of 500x cheaper.

For something that's 500x cheaper AND 2-3x faster per task, why wouldn't Deepseek V4 Flash win.

[Cheaper Inference @CheaperInfer]

@Da7_Tech 👋

[Cheaper Inference @CheaperInfer]

Happened later than we thought but Opus 5 is now the top model by usage 👑