Numes (@Numes_ai) header
Numes (@Numes_ai) profile picture

An open marketplace for the world's AI compute

Joined November 2026
Photo by Numes (@Numes_ai)Photo by Numes (@Numes_ai)Photo by Numes (@Numes_ai)Photo by Numes (@Numes_ai)Photo by Numes (@Numes_ai)Photo by Numes (@Numes_ai)Photo by Numes (@Numes_ai)
$0 per token. Frontier open-source models. Welcome amazee, our first partner. For a limited time, they're serving these on Numes for free: • Kimi K3.1 Pro • GLM 5.3 • DeepSeek V4.1 Flash • Nemotron 3 Ultra Live now at numes.ai
18
6
3
80
23,322
Numes welcomes @PPQdotAI as a provider. You can now pay for AI models on Numes with Bitcoin: 183 models from OpenAI, Anthropic, Google, xAI, DeepSeek, Kimi and more. 🔥 PPQ models are below the market rate for a limited time!
3
6
32
1,402
We're celebrating our launch with free models. - Kimi K3.1 Pro - GLM 5.3 - GLM 5.3 Flash - DeepSeek V4.1 Flash - Nemotron 3 Ultra No strings attached. No credit card needed. Works in every coding agent. Hosted by amazee.
14
9
2
160
9,079
Oops, we just doubled our rate limits again. Retweet and we might increase it even more 😊
We just increased the rate limits of our free models by 4x... let's melt those GPUs 🔥
19
58
2
261
8,501
Our free models now have a ":free" tag so you don't accidentally pay for a fallback model. Please update your harnesses and let's melt those GPUs 🔥
8
4
138
4,025
We just increased the rate limits of our free models by 4x... let's melt those GPUs 🔥
44
50
11
1,070
63,461
Qwen4 Max is now available on Numes
4
1
11
2,110
a minute of agent traffic on Numes, drawn as a Command & Conquer battle every unit is a request, every barracks a model, the GPUs are the fortress live: numes.schnitzel.world/?ref=x…
3
3
2
44
5,555
what agents pick on our Numes endpoint, requests since Nov 3: GLM 5.3 @Zai_org: 618k Kimi @Kimi_Moonshot: 495k DeepSeek V4.1 Flash @deepseek_ai: 285k uncensored builds included. GLM has the most requests, DeepSeek the longest prompts
3
3
1
19
16,291
yesterday was our biggest day on Numes so far: 368k requests and 38B tokens, almost double the day before 11 days in: 1.40M requests and 157B tokens Kimi K3.1 Pro, GLM 5.3 and DeepSeek V4.1 Flash, free right now: numes.ai
11
7
2
90
10,010
free Kimi K3.1 Pro, GLM 5.3 and DeepSeek V4.1 Flash in @opencode, two commands: curl -fsSL numes.ai/install | sh numes run opencode same for Pi from @earendilworks: numes run pi the free models run on our GPUs at amazee.ai
8
13
87
7,286
Kimi K3.1 Pro by @amazeeai is available for free on Numes. And now faster than ever before! 🔥
Kimi K3.1 Pro on Numes was too slow last week: 4-8 tok/s and 9-29 s to the first token last 24h: 26 tok/s and 3 s Kimi got more GPUs, and we retired models few people used. Token Factory moves GPUs between models by itself
1
8
1,380
the median request we get through Numes: 70,497 tokens in, 182 out 38% of requests are over 100k tokens that's coding agents re-reading their context every turn. a chat app looks nothing like this
1
7
825
Some prompts are too private to share. End-to-end encrypted models are now on numes.ai. Your prompt is encrypted on your device and decrypted only inside the GPU that runs the model. Not even we can read it.
6
13
3
96
12,611
Strong start. Numes has served 200B free tokens so far. Free models right now: - Kimi K3.1 Pro - GLM 5.3 - DeepSeek V4.1 Flash Just sign up and create an API key. No credit card or personal information needed. Let's melt some GPUs today!
1
4
2
28
6,233
Numes retweeted
anyone with a spare GPU can sell here, paid per request. curious how low prices go once a few thousand plebs plug in 👀
Numes is live. An open marketplace for the world's AI compute. numes.ai
1
1
5
121
Kimi K3.1 Pro, GLM 5.3, and DeepSeek V4.1 Flash are now free on Numes.
4
3
1
35
6,230
Numes is live. An open marketplace for the world's AI compute. numes.ai
17
12
4
108
12,513