Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Introducing Respan AI Gateway. The world’s first AI gateway with built-in observability, evals, and prompt optimization. Access 1,000+ models through one endpoint, with the production layer teams need beyond routing.

Respan

3,172 subscribers

850,476 Aufrufe • vor 4 Monaten •via X (Twitter)

Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

42 Kommentare

Profilbild von Respan

Respanvor 4 Monaten

1/ Observability + evals + prompt optimization When an LLM call goes wrong, the answer should not be “check four different tools and guess.” Respan shows the trace, cost, latency, eval result, and prompt feedback in one place, so teams can understand what happened and improve the next call.

Profilbild von Respan

Respanvor 4 Monaten

2/ Limits + monitors Nobody wants to find out about runaway usage from the invoice. Set limits, track spend, and get alerts before your LLM bill becomes the team’s new horror story.

Profilbild von Respan

Respanvor 4 Monaten

3/ Built-in reliability Providers fail. Requests timeout. Rate limits happen. Respan keeps traffic moving across providers so one outage does not take your product down with it.

Profilbild von Respan

Respanvor 4 Monaten

4/ No token markup No weird tax on top of usage. Provider discounts are passed directly to customers, so teams can choose based on cost, latency, reliability, and performance. Try:

Profilbild von Respan

Respanvor 4 Monaten

5/ Claude Fable 5 is live on Respan!

Profilbild von Octolane · Revenue Superintelligence

Octolane · Revenue Superintelligencevor 4 Monaten

We live @RespanAI!!! Congratulations on the launch!!!

Profilbild von Respan

Respanvor 4 Monaten

thanks a lot!

Profilbild von Aman

Amanvor 4 Monaten

LFG!!!!!!!

Profilbild von Siddharth Deswal

Siddharth Deswalvor 4 Monaten

We recently had the Claude API fail in production, and had to scramble to switch to the fallback. Glad you guys have built this in the product!

Profilbild von Coffee with One 🇺🇸

Coffee with One 🇺🇸vor 4 Monaten

Congratulations @RespanAI team, let’s go!! This was much needed 🚀🚀🚀

Profilbild von Denise Teng

Denise Tengvor 4 Monaten

lfg!🚀

Profilbild von Aman

Amanvor 4 Monaten

excited to see what people build with it

Profilbild von Frank Chen

Frank Chenvor 4 Monaten

Really useful to monitor AI cost!

Profilbild von Sadok

Sadokvor 4 Monaten

Built-in evals saves the headache

Profilbild von Dawson Chen

Dawson Chenvor 4 Monaten

Sounds very useful! Congrats on the launch guys!

Profilbild von Jisong

Jisongvor 4 Monaten

congrats!!!

Profilbild von Evan

Evanvor 4 Monaten

🚀

Profilbild von Mitch Radhuber

Mitch Radhubervor 4 Monaten

🔥🔥🔥 congrats on the launch!

Profilbild von Richard Zhang

Richard Zhangvor 4 Monaten

Super useful. Congrats to the whole team! 👏

Profilbild von Kathryn

Kathrynvor 4 Monaten

🚀🚀🚀

Profilbild von Barun

Barunvor 4 Monaten

🔥🔥🔥

Profilbild von Varunram Ganesh

Varunram Ganeshvor 4 Monaten

Congrats on the launch!

Profilbild von Sai

Saivor 4 Monaten

Really useful especially with Google AI studio

Profilbild von Alex Liu

Alex Liuvor 4 Monaten

If you tired of managing so many keys or accounts of different providers, just try the gateway.

Profilbild von Islam Assanov

Islam Assanovvor 4 Monaten

@Andydy42 🔥

Profilbild von Tony Xavier

Tony Xaviervor 4 Monaten

Congrats!!

Profilbild von Shivay Lamba

Shivay Lambavor 4 Monaten

congrats on the launch!

Profilbild von Ruiqing Yu | Building Product @ Respan(KeywordsAI)

Ruiqing Yu | Building Product @ Respan(KeywordsAI)vor 4 Monaten

We launched! Proud to have worked on this with the team 🚀

Profilbild von Dylan

Dylanvor 4 Monaten

🔥

Profilbild von Parasail

Parasailvor 4 Monaten

Let's go! Congrats team on the launch.

Profilbild von Respan

Respanvor 4 Monaten

🙌🙌🙌

Profilbild von Aaliya

Aaliyavor 4 Monaten

A unified AI gateway like this makes managing multiple models and providers far more practical for production systems.

Profilbild von Vickie Wan

Vickie Wanvor 4 Monaten

congrats on the launch team🚀

Profilbild von Yuqi Hou

Yuqi Houvor 4 Monaten

Let’s chat about @gmi_cloud can get included in this :)

Profilbild von Respan

Respanvor 4 Monaten

@gmi_cloud Would love to. Really excited to have you guys!

Profilbild von sabir hussain

sabir hussainvor 4 Monaten

How does it handle latency across 1,000+ models?

Profilbild von Ayush

Ayushvor 4 Monaten

Congrats guys! Cant wait to try

Profilbild von Dave Fellows

Dave Fellowsvor 1 Monat

Would be great if you guys had a cheaper paid tier. $249 is a big jump up from free if you only need a little bit more than the free tier offers. Shame, as the platform looks great and we'd love to use it but just too expensive on top of everything else.

Profilbild von Michelle Marcelline

Michelle Marcellinevor 4 Monaten

Congrats on the launch!

Profilbild von ahnaf

ahnafvor 4 Monaten

can i get usage metrics through apis?

Profilbild von Alexander

Alexandervor 4 Monaten

congrats on the launch!

Profilbild von Ethan Jiang

Ethan Jiangvor 4 Monaten

this looks amazing

Ähnliche Videos

Introducing the World’s First Full Agentic Download Agent and Genspark AI Drive! 🚀😀 Download Anything with One Prompt.

Introducing the World’s First Full Agentic Download Agent and Genspark AI Drive! 🚀😀 Download Anything with One Prompt.

Eric Jing

107,739,280 Aufrufe • vor 1 Jahr

We just built the #1 tool every AI team wants. Introducing Merge Gateway: LLM routing, fallback, cost guardrails, and security, all in one place. Everyone gets $10 free LLM usage on us to try it out. RT+ comment “Gateway” → we’ll double your credits.

We just built the #1 tool every AI team wants. Introducing Merge Gateway: LLM routing, fallback, cost guardrails, and security, all in one place. Everyone gets $10 free LLM usage on us to try it out. RT+ comment “Gateway” → we’ll double your credits.

Shensi Ding

100,492 Aufrufe • vor 6 Monaten

Introducing the new AI first vibe coding experience in Google AI Studio! Built to take you from prompt to production with Gemini, and optimized for AI app creation. Start building AI apps for free : ) More updates and features to come!

Introducing the new AI first vibe coding experience in Google AI Studio! Built to take you from prompt to production with Gemini, and optimized for AI app creation. Start building AI apps for free : ) More updates and features to come!

Logan Kilpatrick

1,582,476 Aufrufe • vor 11 Monaten

Introducing Smart Routing in Unity AI Gateway. Stop overpaying for AI. Smart Routing matches each coding task to the right model and harness based on what the task needs, so higher-cost models can differentiate on intelligence while lower-cost models differentiate on cost and performance. Match frontier quality and cut task costs by 30%+.

Introducing Smart Routing in Unity AI Gateway. Stop overpaying for AI. Smart Routing matches each coding task to the right model and harness based on what the task needs, so higher-cost models can differentiate on intelligence while lower-cost models differentiate on cost and performance. Match frontier quality and cut task costs by 30%+.

Databricks

126,674 Aufrufe • vor 2 Monaten

Goodbye NotebookLM. Introducing the World’s First Full Agentic AI Pods - Generate Any Professional Podcasts with One Prompt! Free to Use for Everyone!

Goodbye NotebookLM. Introducing the World’s First Full Agentic AI Pods - Generate Any Professional Podcasts with One Prompt! Free to Use for Everyone!

Eric Jing

8,093,558 Aufrufe • vor 1 Jahr

Introducing the NEW WaveSpeedAI The ultimate AI media platform Now with AI Generator: image · video · audio · avatars · 3D Everything you need to create in one place Built for creators, developers, and teams

Introducing the NEW WaveSpeedAI The ultimate AI media platform Now with AI Generator: image · video · audio · avatars · 3D Everything you need to create in one place Built for creators, developers, and teams

WaveSpeedAI

13,711 Aufrufe • vor 6 Monaten

Agents on OpenClaw🦞 can run commands and act autonomously, one bad prompt and they could leak your production API keys. That’s why we built the control layer: introducing - the Endpoint Detection & Response platform built specifically for AI Agent Security. <20 seconds setup. Logs every action. Enforces policy before execution. Installation instructions below.

Agents on OpenClaw🦞 can run commands and act autonomously, one bad prompt and they could leak your production API keys. That’s why we built the control layer: introducing - the Endpoint Detection & Response platform built specifically for AI Agent Security. <20 seconds setup. Logs every action. Enforces policy before execution. Installation instructions below.

Cantina 🪐

13,613 Aufrufe • vor 7 Monaten

A real agentic workflow: Prompt → Service Discovery → Autonomous Payment → Task Execution. With the AEON AI Gateway and OKX Agentic Wallet OKX Wallet, AI agents can securely pay for the services they need using onchain wallets, unlocking seamless access to AI tools, APIs, and x402-enabled resources. Watch it in action. 👇

A real agentic workflow: Prompt → Service Discovery → Autonomous Payment → Task Execution. With the AEON AI Gateway and OKX Agentic Wallet OKX Wallet, AI agents can securely pay for the services they need using onchain wallets, unlocking seamless access to AI tools, APIs, and x402-enabled resources. Watch it in action. 👇

AEON.XYZ

15,489 Aufrufe • vor 2 Monaten

Why use multiple AI platforms when RoamAI gives you everything in one place? Create stunning AI images with the world’s hottest AI models through one seamless platform, one account, and one balance.

Why use multiple AI platforms when RoamAI gives you everything in one place? Create stunning AI images with the world’s hottest AI models through one seamless platform, one account, and one balance.

Roam

13,973 Aufrufe • vor 4 Monaten

Respan Launch Week, Day 2: Evals Evals are one of the hardest parts of building AI applications. It is not because teams cannot run them. It is because they are hard to structure, hard to compare, and even harder to improve over time. So teams end up guessing. Did this prompt actually get better? Is this model really an improvement? We built Evals in Respan to make this systematic. You define: - what you want to test, such as prompts, models, or configs - the dataset, from production logs or test cases - the evaluators, whether LLM, code, human, or a mix Then you run experiments and compare results side by side. Same inputs. Same evaluation. Clear answers. No more guessing. Start running your first eval.

Respan Launch Week, Day 2: Evals Evals are one of the hardest parts of building AI applications. It is not because teams cannot run them. It is because they are hard to structure, hard to compare, and even harder to improve over time. So teams end up guessing. Did this prompt actually get better? Is this model really an improvement? We built Evals in Respan to make this systematic. You define: - what you want to test, such as prompts, models, or configs - the dataset, from production logs or test cases - the evaluators, whether LLM, code, human, or a mix Then you run experiments and compare results side by side. Same inputs. Same evaluation. Clear answers. No more guessing. Start running your first eval.

Respan

127,680 Aufrufe • vor 5 Monaten

Nuwa AI has been building across multiple fronts — and here’s how it all fits together ↓ Main platform 1⃣Nuwa Gateway One gate to all AI models — pay per use, powered by crypto. → Core infrastructure 2⃣x402x — programmable onchain actions, agent execution & gasless payments → Applications built on x402 3⃣ — the first gasless, approval-less swaps → 4⃣ — AI agents executing x402 Actions → Agent-native experiments 5⃣AI Poker Arena — autonomous agents playing poker → Nuwa started with the AI Gateway, then built x402x as the underlying execution and payment layer. Apps and experiments extend from that foundation. We ship in public and scale what gains real momentum. More to come 🔥

Nuwa AI has been building across multiple fronts — and here’s how it all fits together ↓ Main platform 1⃣Nuwa Gateway One gate to all AI models — pay per use, powered by crypto. → Core infrastructure 2⃣x402x — programmable onchain actions, agent execution & gasless payments → Applications built on x402 3⃣ — the first gasless, approval-less swaps → 4⃣ — AI agents executing x402 Actions → Agent-native experiments 5⃣AI Poker Arena — autonomous agents playing poker → Nuwa started with the AI Gateway, then built x402x as the underlying execution and payment layer. Apps and experiments extend from that foundation. We ship in public and scale what gains real momentum. More to come 🔥

Nuwa AI | x402x Protocol

12,383 Aufrufe • vor 10 Monaten

$ aix built a CLI with AI SDK/Vercel AI Gateway ▪️ Thinking text animation in ANSI ✨ ▪️ Set `AI_GATEWAY_API_KEY` and works ▪️ 100s of models (e.g.: `-m openai/gpt-4o`) It's like a mini-`claude`, purpose built for quickly running commands. Has some nice safety measures built-in. Used this as my learning exercise for the AI Gateway, which was absolutely delightful… I'm a fan 😁

$ aix built a CLI with AI SDK/Vercel AI Gateway ▪️ Thinking text animation in ANSI ✨ ▪️ Set `AI_GATEWAY_API_KEY` and works ▪️ 100s of models (e.g.: `-m openai/gpt-4o`) It's like a mini-`claude`, purpose built for quickly running commands. Has some nice safety measures built-in. Used this as my learning exercise for the AI Gateway, which was absolutely delightful… I'm a fan 😁

Guillermo Rauch

53,688 Aufrufe • vor 1 Jahr

I built an infinite AI chess game, powered by: ▪️ AI SDK for a single DX to all frontier models ▪️ AI Gateway for seamless access with 1 API key ▪️ Workflow to keep the game going forever Right now Anthropic is playing OpenAI:

I built an infinite AI chess game, powered by: ▪️ AI SDK for a single DX to all frontier models ▪️ AI Gateway for seamless access with 1 API key ▪️ Workflow to keep the game going forever Right now Anthropic is playing OpenAI:

Guillermo Rauch

246,393 Aufrufe • vor 9 Monaten

The World’s First Truly Decentralized ChatGPT right at your fingertips: Community-hosted DeepSeek Running on Blockchain-powered AI Terminal! (1/n) Today, ChainOpera AI is proud to make history: we’ve launched the world’s first end-to-end five-layer decentralized AI stack — live in an iOS app ( giving users free access to models like DeepSeek-R1 and diverse community-built Agents. From prompt to response, human language tokens and crypto tokens flow through five layers: App, Agent, Model, GPU, and AI Chain + Smart Contracts. ChainOpera brings true decentralization to every layer — opening the AI ecosystem to users, model builders, agent devs, GPU providers, and data contributors to participate and earn.

The World’s First Truly Decentralized ChatGPT right at your fingertips: Community-hosted DeepSeek Running on Blockchain-powered AI Terminal! (1/n) Today, ChainOpera AI is proud to make history: we’ve launched the world’s first end-to-end five-layer decentralized AI stack — live in an iOS app ( giving users free access to models like DeepSeek-R1 and diverse community-built Agents. From prompt to response, human language tokens and crypto tokens flow through five layers: App, Agent, Model, GPU, and AI Chain + Smart Contracts. ChainOpera brings true decentralization to every layer — opening the AI ecosystem to users, model builders, agent devs, GPU providers, and data contributors to participate and earn.

ChainOpera AI

589,993 Aufrufe • vor 1 Jahr

Today we're launching Brief into open beta. Your AI Product Navigator. The product layer for AI-powered teams. Built with 100+ teams shipping with agents.

Today we're launching Brief into open beta. Your AI Product Navigator. The product layer for AI-powered teams. Built with 100+ teams shipping with agents.

drew dillon

1,246,325 Aufrufe • vor 5 Monaten

Just shipped: the world’s first AI meeting notetaker on Apple Watch! Genspark auto-captures notes on Watch, iPhone, and Android—and integrates with AI Slides, AI Sheets, and AI Docs. The future of work is done with one prompt.

Just shipped: the world’s first AI meeting notetaker on Apple Watch! Genspark auto-captures notes on Watch, iPhone, and Android—and integrates with AI Slides, AI Sheets, and AI Docs. The future of work is done with one prompt.

Eric Jing

2,527,102 Aufrufe • vor 1 Jahr

Introducing the Jev completions API and Jev Playground. Replace your outdated LLMs with the future of text generation. Also, Jev is now available in our AI gateway, have fun!

Introducing the Jev completions API and Jev Playground. Replace your outdated LLMs with the future of text generation. Also, Jev is now available in our AI gateway, have fun!

Alexandre Pesant

62,103 Aufrufe • vor 21 Tagen

WHERE THE ENTERPRISE AI STACK IS BEING BUILT 1. $PLTR building the orchestration layer of the AI economy through the control systems enterprises need before models can take real-world actions backed by a Rule of 40 score of 127 2. $CRWD, $PANW, $ZS & $RBRK building the security layer of the AI economy across endpoint, identity, Zero Trust & cyber recovery as every new agent, machine identity & AI-generated workflow expands the attack surface 3. $NET building the connectivity layer of the AI economy through the internet control plane that agents, APIs & inference traffic must move across in real time, with Cloudflare sitting behind over 20% of the web 4. $SNOW & $MDB building the data layer of the AI economy through the clean, structured, production-grade enterprise data systems that make AI usable inside real applications and workflows

WHERE THE ENTERPRISE AI STACK IS BEING BUILT 1. $PLTR building the orchestration layer of the AI economy through the control systems enterprises need before models can take real-world actions backed by a Rule of 40 score of 127 2. $CRWD, $PANW, $ZS & $RBRK building the security layer of the AI economy across endpoint, identity, Zero Trust & cyber recovery as every new agent, machine identity & AI-generated workflow expands the attack surface 3. $NET building the connectivity layer of the AI economy through the internet control plane that agents, APIs & inference traffic must move across in real time, with Cloudflare sitting behind over 20% of the web 4. $SNOW & $MDB building the data layer of the AI economy through the clean, structured, production-grade enterprise data systems that make AI usable inside real applications and workflows

Shay Boloor

399,438 Aufrufe • vor 5 Monaten

Stop stitching vendors together to run open models in production. Fireworks AI on Microsoft Foundry is GA. One endpoint. Enterprise SLAs. Zero setup. Build your next production workload with Fireworks AI on Foundry:

Stop stitching vendors together to run open models in production. Fireworks AI on Microsoft Foundry is GA. One endpoint. Enterprise SLAs. Zero setup. Build your next production workload with Fireworks AI on Foundry:

Microsoft Azure

14,164 Aufrufe • vor 4 Monaten

☁️ Introducing the Helicone AI Gateway, *now on the cloud* Pass-through billing. Bring your own key. 1 API 100+ models 0% markup 99% uptime And yes, it’s fully open source. Here’s how it works 👇

☁️ Introducing the Helicone AI Gateway, now on the cloud Pass-through billing. Bring your own key. 1 API 100+ models 0% markup 99% uptime And yes, it’s fully open source. Here’s how it works 👇

Justin Torre

35,228 Aufrufe • vor 1 Jahr