AkashML

Inference without the cloud tax.

Open models. Open pricing. Powered by decentralized supercloud @akashnet.

[AkashML @akashnetAI]

Never let token limits interrupt your workflow again.

Developers who keep getting cut off mid-session can now hot swap to AkashML.

Choose from DeepSeek V4 Flash, Kimi K2.6, or Qwen3.5 35B A3B and get back to building in minutes.

First 10 builders to make the switch and reply to this tweet with their experience get $100 in credits.

Get started → https://t.co/CI7mCy9eEr

[AkashML @akashnetAI]

AkashML is the launch partner for @Architect_Fi’s Liquid Inference.

Every prompt is auctioned, and providers compete on price. The request routes to the lowest offer that meets the buyer’s rules.

OpenAI and Anthropic SDKs are compatible with one API key, where the price is locked before the first token.

Decentralized GPUs are now in a live inference market.

[Brett Harrison @BrettHarrison]

Introducing Liquid Inference by Architect, a new LLM model router where inference providers compete dynamically to offer lowest-cost tokens. Providers onboard in minutes, not weeks. Buyers have full price visibility and receive 20% of referred fees in free inference. More info:

Liquid Inference can be used in place of any OpenAI or Anthropic API-compatible backend. Behind it, our team has leveraged our experience trading and building financial exchanges to create real-time two-sided price discovery for inference. Benefits for buyers and providers:

INFERENCE BUYERS

• Fully compatible with agentic coding tools: Claude Code, Codex, OpenCode, Cursor, Pi, Cline, and many more. Full multi-modal support.
• Hundreds of open- and closed-weight models. Create routing rule presets or use our Auto routing algorithms.
• Providers compete dynamically on price for every prompt, offering the lowest marginal cost.
• Sign up for free with email, first 500 users get $20 of free inference.
• Receive 20% of referred fees as free inference, 10% for second-level referrals.

INFERENCE PROVIDERS

• Onboard through the Liquid Inference app. We verify new providers in minutes, not weeks.
• All prompts are OpenAI API standard. Simple REST/Websocket API to register models and quotes.
• Update quotes dynamically based on your own costs. Monetize GPU capacity only when you want.
• Standardize payouts via Stripe, full itemized records of all jobs performed.

[Akash Network @akashnet]

New load balancer went live for AkashML. It keeps capacity saturated across all available GPUs hosting the model.

Yesterday: AkashML served 25.6B tokens as a dominant provider for gpt-oss-120b.

Traffic on OpenRouter is earned. The more performant endpoint serves the tokens.

[AkashML @akashnetAI]

AkashML processed over 536 billion tokens in August, our biggest month ever

[AkashML @akashnetAI]

↓ Get started with GLM 5.3 on AkashML

https://t.co/q8tm7KHumn

[AkashML @akashnetAI]

GLM 5.3 is live on AkashML

The https://t.co/8z1LQyIKMJ’s flagship 753B MoE is built for complex coding and long-horizon agentic work; holds tool use consistent across multi-step development workflows, with 1M native context.

[AkashML @akashnetAI]

We processed over 34 billion tokens yesterday with majority of them for Qwen 3.6 35b, setting a new record

[AkashML @akashnetAI]

Qwen 3.8 27B is live Openrouter with AkashML as the first provider

→ https://t.co/VJ8tf8pwny

[AkashML @akashnetAI]

AkashML processed over 400 billion tokens in July

[AkashML @akashnetAI]

NEW: Cache Pricing is now available on AkashML, along with limited time discounts for Deepseek V4 Flash and GLM 5.2

[AkashML @akashnetAI]

Can vouch that affordable fast inference is in high demand.

The chart for AkashML has been steadily increasing just in the past two months.

Today looks primed for a new ATH.
All powered by @akashnet.

[Algod @AlgodTrading]

Demand for inference is about to sky rocket, cost of intelligence becoming much more economical

It’s just the beginning

[Akash Network @akashnet]

Washington Post published a story about how @gregosuri cut his AI costs significantly by switching to @akashnetAI

→ https://t.co/wqgrSDpRAq

[Greg Osuri 🇺🇸 @gregosuri]

.@akashnetAI also seeing incredible growth, with 13B daily tokens processed on an average for the past 7 days

[AkashML @akashnetAI]

AkashML processed over 10 billion tokens today, setting a new record with usage

[AkashML @akashnetAI]

GLM-5.2 is now available on AkashML.

744B MoE, 40B active parameters, 1M token context.
Trails Opus 4.8 by 1% on FrontierSWE and edges out GPT-5.5. Works with OpenCode, Claude Code, and any OpenAI-compatible harness out of the box.

Try it now: https://t.co/CHJoWarkx0

[Akash Network @akashnet]

Kimi 2.7 now available on @akashnetAI with near Fable-Class benchmarks.

Tuned specifically for agentic coding, OpenRouter and connected Claude Code users can now test drive the latest from Moonshot AI with AkashML.

Not yet connected? Details 👇

[Greg Osuri 🇺🇸 @gregosuri]

.@akashnetAI processed over 7 billion tokens yesterday, a new ATH and has been consistently processing over 5 billion tokens everyday on an average.

Another proof point that Inference on decentralized compute is works great at scale.

[AkashML @akashnetAI]

@vakaytion @akashnet 💅

[Sandeep Narahari @waiting4ragi]

Its really working soo good

Claude Code <> @akashnetAI - Kimi 2.6

I built an CLI tool to deploy app on using console APIs of @akashnet

Opensource models will win