Inference without the cloud tax. Open models. Open pricing. Powered by decentralized supercloud @akashnet.
- Tweets 96
- Following 4
- Followers 3,561
- Likes 87
Pinned Tweet
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 → playground.akashml.com/docs/…
16
19
79
14,837
GLM 5.3 is live on AkashML
The Z.ai’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.
3
5
34
10,714
↓ Get started with GLM 5.3 on AkashML
akashml.com/models/glm-5.3
1
284
We processed over 34 billion tokens yesterday with majority of them for Qwen 3.6 35b, setting a new record
2
13
89
30,824
Qwen 3.8 27B is live Openrouter with AkashML as the first provider
→ openrouter.ai/qwen/qwen3.8-2…
5
11
78
13,715
NEW: Cache Pricing is now available on AkashML, along with limited time discounts for Deepseek V4 Flash and GLM 5.2
7
35
9,221
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.
Demand for inference is about to sky rocket, cost of intelligence becoming much more economical
It’s just the beginning
7
10
44
6,186
AkashML retweeted
Washington Post published a story about how @gregosuri cut his AI costs significantly by switching to @akashnetAI
→ washingtonpost.com/technolog…
6
34
162
16,697
AkashML retweeted
.@akashnetAI also seeing incredible growth, with 13B daily tokens processed on an average for the past 7 days
Washington Post published a story about how @gregosuri cut his AI costs significantly by switching to @akashnetAI
→ washingtonpost.com/technolog…
7
26
135
6,604
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: akashml.com/models/glm-5.2
2
6
55
10,775
AkashML retweeted
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 👇
19
55
286
17,170
AkashML retweeted
.@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.
5 billion tokens a day is the new norm for @akashnetAI -- a new ATH yesterday
Its incredible what you can achieve by abstracting away crypto rails.
Users of have no idea they're using $AKT to host on Akash -- things just happen in the background -- as it should be.
24
42
247
21,320
AkashML retweeted
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
Update ~/.claude/settings.json with these settings to use Akash ML with your Claude code.
Takes less than a minute.
4
7
63
2,813
AkashML retweeted
@akashnet is crushing it on @OpenRouter via @akashnetAI.
In less than 2 months, the growth has been incredible.
Yesterday alone, usage reached 6.58B tokens, new ATH.
openrouter.ai/provider/akash…
2
10
66
21,370
AkashML retweeted
$AKT @akashnet
AkashML is having a strong increase in OpenRouter traffic
Here are some stats:
- 50B+ tokens processed per month on OpenRouter
- Multiple days already hitting 5B+ tokens/day
- Multi-model demand (DeepSeek V4, Kimi 2.6, Qwen)
This is not random -> it is recurring organic inference demand flowing straight to decentralized GPUs
Powered by @akashnetAI
2
7
82
1,798