←
Infron666 posts
Infron avatar

Infron

@InfronAI

AI inference for growing businesses—from serverless APIs to custom inference solutions. 400+ models. 99.9% SLA. 24/7 technical support

◷ Joined June 2025▧ 342 Photos and videos
Infron avatar
Infron@InfronAI·Jul 30

Really glad to be working with @alibaba_cloud. Looking forward to what we build together from here, and to giving our clients a better and more rigorous service!

AI models evolve weekly. Your infra shouldn't have to. With Alibaba Cloud, @InfronAI scales open-source models like Qwen with dedicated capacity across 5 global regions, provisioned in days with verifiable placement. Read now: click.alibabacloud.com/m/200… #Qwen #AI #LighthouseCustomerStories

0:25
Infron avatar
Infron@InfronAI·11h

61 audio models just landed on Infron. 38 text-to-speech. 17 speech-to-text. 6 realtime voice models. From voiceovers and transcription to live voice agents, with models from OpenAI, ElevenLabs, Google, Qwen, MiniMax and more. infron.ai/models?utm_source=…

Post attachment
Infron avatar
Infron@InfronAI·16h

We're happy to announce our @coinbasebiz integration! You can now buy Infron credits with stablecoins and use them across models from multiple providers through one API. Thanks to the Coinbase Business team for working with us! infron.ai

Post attachment
Infron avatar
Infron@InfronAI·16h

Excited to bring stablecoin payments to @InfronAI with @CoinbaseBiz. You can now top up your Infron credits with stablecoins and access AI models from multiple providers through one API. PI.

Top up AI credits with stablecoins on @InfronAI. Powered by Coinbase Business. No limits. Global. Instant. Permissionless.

Post attachment
Infron avatar
Infron@InfronAI·Nov 16

Use cases to test👀 Try a real, authorized edge-case workflow: review a sensitive bug report, analyze an image-heavy support case, or work through a long document and tool sequence. Send the same task to both Hy4 routes. Does either refuse, miss a step, or change the quality of the result?

Infron avatar
Infron@InfronAI·Nov 16

What is different? The distinction is the refusal behavior: Silk Compute describes Hy4 Uncensored as an abliterated Hy4 build with that behavior removed. The 1M-token context, image input, streaming, and tool calling come from the Hy4 family. They aren't exclusive to the Uncensored variant.

Infron avatar
Infron@InfronAI·Nov 16

Hy4 Uncensored is live on Infron. 🔐 What changes when a model's refusal behavior is removed? Run the same prompt through `tencent/hy4` and `tencent/hy4-uncensored` via one API. Compare the answers yourself. infron.ai/models/tencent/hy4…

Post attachment
Infron avatar
Infron@InfronAI·Nov 16

Qwen4-Max is now live on Infron. ✨ Bring Qwen’s new flagship model into your coding, reasoning, and agent workflows through one API. Launch offer: 40% off Qwen4-Max on Infron. Explore models: infron.ai/models?utm_source=… #infrondiscounts #AI #Developers

Post attachment

📢 Meet Qwen4-Max, your new AI teammate for work, creativity, and discovery! Qwen4-Max is built on a new MoE architecture with native vision and a 1M-token context window. Highlights: - Outperforms Qwen3.8-Max with up to ~50% fewer tokens, while average cost per task drops over 60% in our internal evaluation. - Advances real-world productivity through greater proficiency with professional tools, stronger long-horizon execution, and higher-quality deliverables. - Handles real tasks, including 3D modeling, game development, manufacturing, finance, law, healthcare, and frontier scientific discovery. - $1.5/M tokens for input, $4.5/M tokens for output, and $0.075/M tokens for implicit caching — all lower than Qwen3.8-Max, with implicit caching down by 70%. The API is live on QwenCloud. You can also try Qwen4-Max on Qwen Studio, QwenWork and Qoder. Start building today! 🚀 - Blog: qwen.ai/blog?id=qwen4-max - API: qwencloud.com/models/qwen4-m… - Token Plan: qwencloud.com/pricing/token-… More to come! The open weights of smaller Qwen4 models will be released. Stay tuned. 👀

Post attachment