Accelerate AGI to benefit humanity.
Joined January 2024
- Tweets 518
- Following 276
- Followers 2,612
- Likes 988
130 Photos and videos
Pinned Tweet
Apr 24
Whale is finally here 🐳
MoE · 1M context · 3 reasoning modes
@deepseek_ai V4 series now available on SiliconFlow with day-0 support：
⚡ DeepSeek-V4-Pro: $0.145 / $1.74 / $3.48 per 1M tokens
🚀 DeepSeek-V4-Flash: $0.028 / $0.14 / $0.28 per 1M tokens
🤖 Best open-source model for Agentic Coding, outperforms Sonnet 4.5 & approaches Opus 4.6
🌍 World knowledge that rivals frontier closed-source models
🧮 #1 open-source on math, STEM & competitive coding — matches Opus 4.6 & Gemini 3.1 Pro
Try it now ⬇️
6
2
18
13,098
Jun 11
@NousResearch has shipped Hermes Agent Desktop — and it's now even easier to use frontier open-source models through @SiliconFlowAI 🔥
→ One click to switch models anytime — DeepSeek-V4, GLM-5.1, Kimi-K2.6, MiniMax-M3, and more, all on SiliconFlow
... ...
Full guide to start your Hermes trip with SiliconFlow 👇🧵
3
8
555
Jun 11
Here's a full step-by-step guide to get you started with Hermes Agent SiliconFlow:
📖 How to use Hermes Agent with SiliconFlow APIs:
docs.siliconflow.com/en/user…
🤖 Deploy an AI assistant on Discord using Hermes Agent:
docs.siliconflow.com/en/user…
1
4
248
Jun 11
Everything you love with Hermes stays the same, now with a more accessible GUI on macOS, Windows, and Linux.
More info from @NousResearch 👇
x.com/NousResearch/status/20…
Jun 2
The next evolution of Hermes Agent is here!
Introducing Hermes Desktop: everything you love about Hermes, now native on your machine.
First demoed in Jensen's GTC keynote, it's now in public preview.
2
196
Introducing Write Gate in Hermes Agent.
Now you have the capability to be able to approve/deny memory updates, skill updates, and skill creation with the same familiar mechanisms as approving dangerous commands.
If you are using a small model that doesn't always recognize what it learned, a secure environment that needs gating before things that can affect operations occurs, or just want to be more involved in the self improvement process of your Hermes Agent, now you have full control!
This will be included in the next major release version, but you can run `hermes update` now to access early!
70
56
788
117,406
Jun 10
If you need one model for agents, long context, and multimodal inputs — this is it.
Meet @GoogleDeepMind 's Gemma 4 12B on SiliconFlow 🔥
💰Input / Output: $0.1 / $0.3 per 1M tokens on SiliconFlow
🛠️ 262K Context | Built-in Thinking | Native Tool Calling | 140 Languages
✨ Encoder-free architecture: vision and audio inputs flow directly into the LLM backbone, reducing process latency
🧠 12B Size, 26B Brain: nearing Google's 26B performance, excel at multi-step reasoning and agentic workflows
Try it on SiliconFlow ⬇️
4
2
14
1,378
V4-Pro (quality) V4-Flash (speed)
2 lines of config to bring the Best price/perf DeepSeek combo in your terminal
@goodhunt's CodeWhale — the terminal coding agent built for @deepseek_ai V4 —
now includes SiliconFlow as a built-in provider🔥
Here's what you're actually getting:
→ Stream Reasoning: See the thinking, not just the answer.
→ Auto-Routing: Switches model thinking depth by task complexity.
→ Zero Drift: A written Constitution ranks authority for each turn, keeps V4 oriented.
→ Self-Improving: V4 helped write its own harness, and as the harness improves, every session is stronger.
Step-by-step guide 🧵👇
2
30
3,000
SiliconFlow retweeted
Jun 7
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
1,785
1,368
19,557
8,291,619
DeepSeek at #1 on @OpenRouter token share — 4 weeks running
And we're proud to be powering a big slice of it
You can find the complete @deepseek_ai lineup on @SiliconFlow:
→ V4 Pro & Flash ( best price/performance 🔥)
→ V3.2 · V3.2 Exp · V3.1 · V3.1 Terminus · V3 0324 · R1 0528
2
3
621
You can now bring your SiliconFlow balance into @OpenRouter via BYOK🚀
Once connected:
- Your SiliconFlow balance is used first
- Billing and rate limits stay in your SiliconFlow account
- OpenRouter fallback boosts reliability
✨ Bonus from OpenRouter: 0 platform fees on your first 1M BYOK requests/month
1
251
Let's build today with DeepSeek🔥
siliconflow.com/models/deeps…
145
Post-training is having a moment — Nex-N2-Pro from neolab @NexEcosystem proves it.
Built on Qwen3.5-397B-A17B, delivers GPT-5.5 and Claude Opus 4.7–level performance.
🎉 T 0 Support on SiliconFlow · Free for First 2 Weeks
N2-Pro: 397B MoE / Reasoning Model / 262K context / VLM
→ Auto-adjusts reasoning depth, 30–50% fewer thinking tokens, no performance trade-off
→ SOTA performance on Terminal Bench 2.1, GDPVal, SWE-Verified
→ Excels at agentic coding, deep search, tool use
→ Plug-and-play with Claude Code, Cursor, OpenClaw, etc.
Try it on SiliconFlow ⬇️
8
5
32
6,102
More Info
x.com/nexecosystem/status/20…
Jun 4
📢 Nex-N2 is here!
A family of agentic models that doesn't just think, it acts!
Coding, search, tool use. All fused into a single agentic reasoning loop.
- Adaptive Thinking, auto-scales reasoning depth per step. Saves ~20% tokens, zero performance loss.
- Coherent Thinking, one thinking paradigm across search, coding, and tool use. No more fragile mode-switching.
🏆 Result: Tier-1 open-source performance on SWE-bench, Terminal-Bench, GDPval, and more, tracking GPT-5.5 and Opus 4.7.
🎉 Open-weight. Try it now.
🔗 nex-agi.com/
📦 huggingface.co/nex-agi/Nex-N…
modelscope.cn/models/nex-agi…
github.com/nex-agi/Nex-N2
2
550
SiliconFlow retweeted
Jun 3
Meet Gemma 4 12B!
A unified, encoder-free multimodal model designed to bring high-performance intelligence directly to your laptop, and released under an Apache 2.0 license.
Bridging the gap between edge efficiency and advanced reasoning. Here is what’s new with Gemma 4 12B: 👇
404
1,789
12,364
3,174,592
@karpathy 's llm-wiki hit 5,000 stars in weeks.
The idea: stop re-discovering knowledge every session. Let an LLM build and maintain a wiki that gets smarter every time you use it.
Here's how to build your own with @opencode @justsisyphus OMO SiliconFlow 🧵
3
4
62
23,129
How this stack works:
→ @opencode browses the web via Chrome automation — reads pages, extracts entities & concepts, writes cross-linked markdown into your Obsidian vault automatically
→ @justsisyphus oh-my-openagent routes each task to the right model — orchestration, deep reasoning, fast search, all handled without manual juggling
→ @SiliconFlowAI 200 frontier models, DeepSeek V4/GLM-5.1/Kimi2.6/M3 etc., one API key
One ulw command scaffolds the entire wiki structure. Your knowledge compounds every time you use it.
1
2
1,887
Follow the full step-by-step guide to build your personal wiki knowledge base⬇️
docs.siliconflow.com/en/user…
1
2
1,604