Openmayhem

Opensource inference & workflow router

[Openmayhem @openmayhem_ai]

Turn your spare compute into revenue

If your devices aren't earning for you, they're losing you money.

Become a provider on OpenMayhem and serve AI models & ComfyUI workflows p2p.

Choose what you want to provide and the minimum price you’ll serve it

▶️ https://t.co/h77aaiLDGV

[Openmayhem @openmayhem_ai]

@fitzyOG

[Openmayhem @openmayhem_ai]

News: Latest OpenMayhem now supports Krea 2!

Krea 2 is an extremely popular workflow for image generation. We support many LoRas and fine-tune settings out of the box.

Check it out in OpenMayhem Studio -> Media.

Works great on RTX consumer machines (Linux/Windwos), as well, so you can start providing Krea 2 & earn with OpenMayhem.

[Openmayhem @openmayhem_ai]

Start earning on Openmayhem in a few simple steps:

1) find your device on the checker tool
2) see which models are a good fit
3) decide which model to serve
4) connect as a provider
5) start earning when your capacity is used.

Get started here:
💻 https://t.co/h77aaiL5Rn

[Openmayhem @openmayhem_ai]

The headline here is ~85% discount on Qwen3.8-27B usage.

but it also highlights something deeper:

we enable open inference markets, where independent providers set the price they're willing to serve models at.

more providers → more intelligence liquidity → greater price competition → continuous market-driven price discovery.

Start saving now 🔽
https://t.co/1qhSI3ILBS

[Openmayhem @openmayhem_ai]

We just released the Qwen 3.8 27B market with initial pricing: 5c per 1M in, 35c per 1M out.

Prices are adjustable based on market demand and may fluctuate over time.

How the initial pricing compares, see below.

[Openmayhem @openmayhem_ai]

$500 FREE Openmayhem API Credits!

First 100 users receive $5 to use across all inference and ComfyUI workflows

Provider supply is still early, so if the model or workflow you need isn’t being served yet, why not become a provider and start earning from the demand

Claim here 🔽

https://t.co/39NpYopEGk

[Openmayhem @openmayhem_ai]

There are now TWO ways to try OpenMayhem for free:

1) Enter the Playground (below) and try the Chat, Image, Music & Speech models

2) Claim your free $5 of Credits that can be used for any model either within the ‘Models’ section, or via our API

Visit https://t.co/rGOaWy5teY 💻

[Openmayhem @openmayhem_ai]

While Astra & SOL now are heavily nerfed and prompt tokens being burned at a fast pace, we have created a free and open inference & workflow market.

Become a provider on OpenMayhem and earn. Now is the perfect time.

[Openmayhem @openmayhem_ai]

Next step is to support big boys like DeepSeek on https://t.co/1jep0UzYLr and onboard the first data-center tier routing providers.

[Openmayhem @openmayhem_ai]

While Astra & SOL now are heavily nerfed and prompt tokens being burned at a fast pace, we have created a free and open inference & workflow market.

Become a provider on OpenMayhem and earn. Now is the perfect time.

[Openmayhem @openmayhem_ai]

More reasons to provide intelligence on https://t.co/KYF2r0fFLB

We just released OpenMayhem Studio - A fully-blown browser chat & media suite for everyone.

Studio enables you to chat, code, create images, videos, music, voice & more - from all available providers!

You'll have full cost-control over every single aspect, and it's probably the most cost-effective solution out there.

And the best is: We don't store your conversations. They stay in your browser, on your device.

Try it out with your $5 free credits!

[Openmayhem @openmayhem_ai]

@fitzyOG @ComfyUI We just released Openmayhem Studio.

$5 free Credit still available to try it out as a user 👇
https://t.co/7T2rjQzcpN

[Openmayhem @openmayhem_ai]

More reasons to provide intelligence on https://t.co/KYF2r0fFLB

We just released OpenMayhem Studio - A fully-blown browser chat & media suite for everyone.

Studio enables you to chat, code, create images, videos, music, voice & more - from all available providers!

You'll have full cost-control over every single aspect, and it's probably the most cost-effective solution out there.

And the best is: We don't store your conversations. They stay in your browser, on your device.

Try it out with your $5 free credits!

[Openmayhem @openmayhem_ai]

@TRACaveMan Sadly, iPads are not supported for such AI inference tasks.

[Openmayhem @openmayhem_ai]

Turn your spare compute into revenue

If your devices aren't earning for you, they're losing you money.

Become a provider on OpenMayhem and serve AI models & ComfyUI workflows p2p.

Choose what you want to provide and the minimum price you’ll serve it

▶️ https://t.co/h77aaiLDGV

[Trac Network @TracNetwork]

Datacentre-scale OpenMayhem providers could drive huge volumes of verifiable economic activity through @TracNetwork

At scale, millions of AI inference events could be occurring, continuously producing signed receipts & settlement state that's cryptographically evidenced on Trac.

[Openmayhem @openmayhem_ai]

@fitzyOG

[Openmayhem @openmayhem_ai]

Next step is to support big boys like DeepSeek on https://t.co/1jep0UzYLr and onboard the first data-center tier routing providers.

[Chubby♨️ @kimmonismus]

DeepSeek just released V4.1-Flash with a new architecture, six weeks after its July V4-Flash update.

July’s release improved post-training while keeping the architecture unchanged. (Same with GLM-5.3/Flash) V4.1 introduces a Causal Encoder–Decoder architecture with native visual understanding.

DeepSeek reports:
- 552B MoE parameters, with 8B active during input processing and 16B during output generation.
- KV-cache requirements cut to ¼ of the HBM and ⅛ of the SSD storage versus the previous generation.
- Lower API prices.

These are *significant* jumps in just a few weeks with post training.

This is the new reality we have to adapt to: weekly releases with significant improvements.

The company says Flash now beats V4-Pro on capability, cost and speed. Starting September 14, V4-Pro API requests will temporarily route to V4.1-Flash until V4.1-Pro arrives.

[Openmayhem @openmayhem_ai]

@memeclubhq 🫡

[Openmayhem @openmayhem_ai]

More reasons to provide intelligence on https://t.co/KYF2r0fFLB

We just released OpenMayhem Studio - A fully-blown browser chat & media suite for everyone.

Studio enables you to chat, code, create images, videos, music, voice & more - from all available providers!

You'll have full cost-control over every single aspect, and it's probably the most cost-effective solution out there.

And the best is: We don't store your conversations. They stay in your browser, on your device.

Try it out with your $5 free credits!

[Openmayhem @openmayhem_ai]

There are now TWO ways to try OpenMayhem for free:

1) Enter the Playground (below) and try the Chat, Image, Music & Speech models

2) Claim your free $5 of Credits that can be used for any model either within the ‘Models’ section, or via our API

Visit https://t.co/rGOaWy5teY 💻

[Openmayhem @openmayhem_ai]

@PetrusMinor @TracNetwork You would use this mostly with our API and connect with an agent of your choice. The web-chat is coming soon!

[Openmayhem @openmayhem_ai]

$500 FREE Openmayhem API Credits!

First 100 users receive $5 to use across all inference and ComfyUI workflows

Provider supply is still early, so if the model or workflow you need isn’t being served yet, why not become a provider and start earning from the demand

Claim here 🔽

https://t.co/39NpYopEGk