for those who take the leap towards production AI
SF, BLR
- Tweets 1,507
- Following 1,162
- Followers 1,998
- Likes 1,378
Pinned Tweet
We just raised our $15M Series A to scale our unified control plane for production AI.
AI is now mission-critical infrastructure, and we’re building the reliability layer so it never breaks.
Thanks to our investors @ElevCap + @lightspeedvp
portkey.ai/blog/series-a-fun…
14
10
34
5,517
📢 Exciting News!!
Portkey is now natively integrated with @llama_index! 🎉
Building resilient and production-ready LLM apps has just become extremely easy 💆
Portkey adds 4 core production capabilities to any Llamaindex app: ⬇️
2
5
31
9,690
📸LLMs in Prod: Embeddings for RAG
Portkey 🤝 @neondatabase with @NirantK and @_raoufai
ALT LLMs in Prod with Portkey
1
2
25
2,019
🚨Benchmarks are essential - but what happens when models hit production?
We've spent the last year analyzing how LLMs perform in-production across:
• 2Tn+ Tokens 🔥
• 90+ regions
• 1,600+ models
650+ orgs trust Portkey—but what's really working in production? The answers might surprise you.
1
10
21
2,095
✨LLMs in Prod Day 1: Provider Trends Unveiled
Who’s dominating? Who’s growing the fastest? And what’s really changing in the AI ecosystem?
We analyzed 2 trillion tokens worth of our production data to uncover trends that might surprise you. Let’s get into it. 👇
1
10
20
5,124
Now Presenting: AmulGPT - put in a news article and get one of those classical Amul topical ads!
Featuring @swyx in the house!
🚨 Bangalore! Emergency Hackathon. Tomorrow.
Elite builders. OpenAI's latest. (scary) Limited spots.
Food, credits (and sleep) - on us.
Go: lu.ma/dtv2l6o0🏃
2
4
22
3,121
📊 OpenAI vs Azure OpenAI: The Production Face-off
We analyzed billions of production requests to answer one question: Which platform should you actually build on?
The data might surprise your entire engineering team 👇
2
4
20
6,313
🚀New Guide on the Portkey Blog: DSPy in Production
- by @ganarajpr, based on his talk at the LLMs in Prod BLR meetup.
Learn how to leverage DSPy by @lateinteraction to tackle real world challenges, optimize AI pipelines, and revolutionize e-commerce operations.
Read it now: portkey.wiki/dspy-blog-x
8
18
2,266
Over *$8 Million USD* in committed investments & credits are available for early-stage AI startups today.
But where can you find them?
We scoured the depths of internet (and Twitter) to compile just that!
🥁 Introducing.. The AI Grants Finder
1
5
18
3,536
Is it ok to ship something new on a Saturday?
Portkey now supports models hosted on Groq's super fast LPUs!
10
2
16
5,465
🚀 Portkey now natively integrates with Tembo to conduct vector searches on Postgres
Use multiple LLM providers to create embeddings on @tembo_io - without changing your setups
Try it out: tembo.io/docs/product/stacks…
1
3
16
1,105
Portkey integrations ranked by awesomeness:
#1 @vercel (@jaredpalmer et al)
#2 DSPy (@lateinteraction et al)
#3 Instructor (@jxnlco)
#4 @promptfoo (@iwebst)
#5 @phidatahq ( @ashpreetbedi)
#6 @ControlFlowAI (@AAAzzam)
#7 @tembo_io (@rywalker)
..and 40 odd more.
Portkey is now a first class provider in the @vercel AI SDK.
When should you use Portkey's AI gateway with the AI SDK?
1. You're routing requests to multiple models & providers.
2. You're going to production and need metrics on cost, performance and accuracy
3. You want to build & manage on-line guardrails without adding latency
4. You have multiple teams building with AI and need to manage usage and budgets.
1
3
14
1,199
🔥 @OpenAI's DevDay brings Prompt Caching for their most famous models.
Here's everything you need to know about it -
2
2
15
955
when we were cutting cake to mark one year of Portkey, Stripe pinged with our biggest customer payment yet.
timing so good, it felt scripted xD
4
15
1,417
Live Now: LLMs in Production Event from SF! 🌟
We're kicking off an insightful evening exploring production-specific questions and issues on scaling LLM apps!
Link to join the livestream in the next tweet! ↓
feat. @lightspeedvp @databricks @llama_index @getpostman @yi_ding @jumbld @sandeep_kri @dkhare @RajaswaPatil
1
4
14
4,479
In August, @PortkeyAI crossed 2 Billion total requests processed through our platform 💥
(this number was 0 last year!)
We're humbled to be production partners for thousands of leading AI companies around the world, like @getpostman @quizizz @italic @Pepper_Content @thenaplatform @MultiOn_AI @springroleinc @psl and many more.
Here's a quick recap on everything that's new at Portkey this month👇
1
4
14
3,771
Thrilled to talk about Portkey's @F5 partnership at the @RSAConference!
There is not a year in the past 8 years that I have not used nginx
With the Portkey AI gateway, the best platform teams are at the best position for AI too :)
Pro tip: Lua unlocks the unlimited nginx power
1
1
13
804
Adding search to your queries is a huge advantage.
It gives you higher-quality data, more relevant results, and lets you serve responses grounded in real-world facts, making your AI feel smarter, more accurate, and truly useful.
🚀 Portkey now integrates with @ExaAILabs to bring this capability to your app, enabling you to:
✅ See which requests used Exa
✅ Track token usage for search context
✅ Compare responses with and without search context
Check out the demo below 👇
1
2
10
3,740
New York, you can't miss this.
Catch @jumbld and @ayushgarg_xyz in the first ever LLMs in Prod meetup on the east coast.
We'll be sharing our hard won lessons in shipping AI apps to production.
Limited seats. Please register soon! Link ↓
1
4
12
894
Happy to confirm this! We've observed millions of Gemini 1.5 Flash requests over the last 3 months, and the latency has steadily dropped 3x
We just shipped a series of changes which have significantly improved the Gemini 1.5 Flash latency (>3x reduction) and output tokens per second (>2x more)⚡️🚢
13
824
.@jumbld is live on India's national broadcaster, discussing India's efforts towards Gen AI and how Portkey is empowering AI innovation!
1
12
4,260
🔥 We’re LIVE on Product Hunt! 🔥
Meet Prompt Engineering Studio—the easiest way to build, test, and deploy AI prompts at scale.
✅ Test & Compare 1600+ AI models
✅ Version control & collaboration
✅ Portkey's Gateway integration
Try it now & show some love by upvoting! 👇
3
1
12
1,945
🚨 Heads Up: Major Update from OpenAI! 🚨
Starting Jan 4, say goodbye to 33 models, including the iconic text-davinci-003 (aka GPT-3). This is the largest model sunset at OpenAI yet! 🌆
What's changing? Read on! ⬇️ 1/3
1
2
12
1,497
Billions of tokens. 200+ LLMs. 5,000 Github stars.
Behind these numbers lies a story waiting to be told.
Join Portkey's CEO @jumbld at the Bangalore Gen AI Meetup, as he unveils the lessons learnt building a massive-scale OSS AI gateway — a critical component in unlocking the true potential of generative AI.
Fri, 14 June, 6:30 PM • dub.sh/blr-gen-ai
11
928
🔊 Sound on
BIG Update to Portkey — the URL slugs for all pages are now ✨clean✨
but there's more 👇
9
2,207
A visit to the Portkey booth comes with serious perks
ᕕ( ᐛ )ᕗ
Are we seeing you @Magicball_dev?
3
11
542
New Portkey + @langchain Cookbooks ✨ thanks to @yujian_tang!
See how easy it is to start making your Langchain agents reliable, cost-efficient, and production-grade using Portkey:
Explore the Cookbooks:
- Portkey + OpenAI + The Milvus Project RAG Agent: github.com/ytang07/ai_agents…
- Portkey + OpenAI Complex Calculator Agent: github.com/ytang07/ai_agents…
Thanks @yujian_tang 💙
2
11
650
While @AnthropicAI 's Claude Sonnet 3.5 has seen very quick adoption in production, @GoogleDeepMind just released the new Gemini 1.5 Pro experimental (0801) model which is now ranked #1 on the LMSYS Chatbot Arena leaderboard, neck-and-neck with GPT-4 and Claude 3.5 Sonnet!
The competition among large LLMs is intensifying, with recent releases like Mistral Large 2 and Llama 3.1 405B adding to the excitement!
Supported in the Portkey AI Gateway within 24 hours!
1
2
11
550
Streaming from cache is now live and is supported in these 3 portkey routes:
/v1/chat/completions,
/v1/completions and
/v1/prompts/:id/completions.
available across all providers.
We also cache function streaming calls now!
10
1,449
🚀 Last week, we had an absolute blast co-hosting the AI Agents: Inter-continental Hackathon with @meetaugustai at their BLR Chapter!
24 hours of pure innovation, collaboration, and building the future of AI agents.
A massive shoutout to all the participants, our co-hosts- @SarvamAI , @e2enetworks Microsoft for Startups , @Composio, and @5C_Network, for making this a memorable event.
✨Special thanks to @anuruddh_m and @somnathsandeepp, for hosting and to everyone who joined us!
📸:
1
2
10
1,316
cool portkey user doing very cool things 👇
You can now add @stripe payments to your Create app
• add in 2 mins. it's seamless.
• prompt how it should work
• turn your app into your next revenue stream
Launch your product. Get rich (maybe)
Comment 💸 and we'll help you get your first MRR
1
1
10
463
🚀 Announcing @OpenWebUI + PortkeyAI integration
Open WebUI (45k+ ⭐) is one of the community's most loved open-source ChatGPT clones.
Here's how Portkey is making it simple, secure, and scalable...🧵
1
10
1,356
We are open sourcing our Guardrails on the Gateway framework today.
But why is this important?
We built the gateway to bring some uniformity to so many LLM APIs that are out there, and added fallbacks, load balancing to make the routing more reliable.
That was a good start! (got us some github stars)
..but for production reliability, it was not enough.
We're launching our open-source AI guardrails framework on our AI gateway today.
Been building it with inputs from 600+ teams who use the gateway in production and have collectively made 1.4 billion API requests on our hosted platform itself!
trying our luck with an HN launch once more -> and would really appreciate support, feedback and questions. :D
our opinions on the approach of Guardrails + Gateway below ⬇️
ALT hacker news launch for Portkey's AI guardrails
1
2
10
957
Our LLMs in Prod server is about to hit 200 members! 🎉
To celebrate, we are giving limited edition Portkey merch to the 200th new member - which includes the apocryphal Yud t-shirt, and more.
Who will be the lucky 200th? RT for karma!
➡️ discord.gg/9s46U9YHNw
1
4
10
882
Capturing a special moment from our community! 📸
Mohamed shared some fantastic feedback about our features at Portkey - from seamless integrations to our game-changing analytics, it's feedback like this that keeps us going 🚀
1
2
10
1,156
Over the last 8 months, Portkey has processed a total of 300 Billion+ tokens across 100+ LLMs
Every day, more and more of our customers are taking their LLM apps to production using Portkey
And this is just the start.
2
10
1,413
🚀 We've put together a cookbook on using @GroqInc - fast LLM inference with Portkey's production-ready features.
Here's what's inside:
• Deep dive into advanced routing capabilities
• Real-world examples of semantic caching
• Observability suite with 42+ metrics
• Production-grade reliability features
The best part? it takes 2 lines to get started
Perfect for teams already loving Groq's sub-100ms responses who want enterprise-grade control.
2
2
10
2,446
✨How are companies actually deploying LLMs in production?
We went beyond the hype and analyzed 2T+ tokens to understand the real patterns when deploying LLMs in production - from provider dynamics to performance metrics.
Link to Report in🧵
1
2
10
662
🔥 Day 0 support for the new gpt-4o-2024-08-06 model on Portkey!
It's 50% cheaper on inputs and 33% cheaper on outputs.
Try it out now! 👇
1
10
327
🚨 Bangalore! Emergency Hackathon. Tomorrow.
Elite builders. OpenAI's latest. (scary) Limited spots.
Food, credits (and sleep) - on us.
Go: lu.ma/dtv2l6o0🏃
1
2
10
3,836
.@MistralAI just released Codestral Mamba, a revolutionary 7B parameter coding model based on the Mamba architecture.
With linear time inference, 256k token context, and Apache 2.0 license, it's set to transform code generation.
Try out the Codestral Mamba model using Portkey! 👇
1
2
8
447
That’s a wrap for Portkey's AWS re:Invent meetup! 🎉
We had the privilege of hosting Samay Kohli (Co-foudner @GoGreyOrange), Arjundas from @FreshworksInc , @dip_ak from @grackerAI, and @pratyushkukreja Scrut Automation.
If you're looking to build production-ready AI systems, reach out to @jumbld attending the AWS re:invent'24
6
8
394
We just launched Model Catalog!!
If your org has multiple teams building with LLMs, this is the control layer you’ve probably been missing.
🧵
2
6
9
1,733
Ever stumbled upon a buggy request in your logs and wished you could instantly rerun it to fix it?
Say Hello to Log Replays! 🔄
With Log Replays, you can open the full request in a fresh prompt playground straight from your logs — easily replay the buggy request and edit it right there until it works
2
8
1,555
If you're looking for an easy way to switch to the latest OpenAI embedding models, configs are a great way to do that.
You can switch to the latest models without touching your codebase. Also lets you try multiple models in parallel as you experiment.
We call this #ForwardCompatibility in Portkey.
4
370
Azure OpenAI has seen a 50% surge in customers as enterprises are scaling GenAI across teams and products.
But growth brings operational problems. The biggest one? Cost attribution.
How do you track spend per app, team, or user?
Some teams split into multiple subscriptions. Others consolidate and lose visibility.
Portkey solves this problem by integrating with @Azure's full AI stack, giving you detailed visibility into usage and costs, down to the user level.
See how we integrate with the whole stack here - portkey.ai/docs/integrations…
1
9
1,794
We analyzed 2+ trillion tokens processed across 650+ organizations on our AI Gateway.
To uncover trends, we categorized token usage into 8 token buckets for you:
• Basic Questions (0-100)
• Email Drafts (100-500)
• Detailed Explanations (500-1k)
...all the way to 50k+ tokens representing full codebase ingestion, legal doc reviews etc.
The results? A revolutionary shift in how LLMs are being used in production:
• Short, simple use cases are declining.
• Complex workflows are booming.
Here’s what the data reveals—[Part of LLMs in Prod series]: 🧵
2
4
9
698
Attention Isn't All You Need
Mamba: A New Approach to LLMs. This State Space Model achieves Transformer-level performance with RNN-like efficiency.
@MistralAI 's Codestral Mamba, with just 7B parameters, outperforms many larger, widely-used LLMs.
We've done a deep dive to unravel Mamba's potential:
portkey.sh/mamba
1
1
8
423
Claude 3.5 Sonnet has revolutionized AI this year, but our analysis of billions of AI requests reveals something unexpected:
@awscloud Bedrock is outperforming @AnthropicAI in its own API by 26% in reliability.
What is better for your app? Let's find out 👇
1
2
8
697
Level up your @vercel chatbots with Portkey's conditional routing config! 🚀
🌍 Route requests based on user type, data sensitivity, or any custom condition.
Switch models on-the-fly, handle traffic spikes, and ensure compliance effortlessly.
Check out the code:
Paid users ➡️ OpenAI
Free users ➡️ Anthropic
1
8
450
happening tomorrow!!
register if you haven't already: home.mlops.community/public/…
@mlopscommunity @retrovrv
MCP is here. Or is it? 👀
@retrovrv will be looking at where things actually stand at the Agents in Production conference (virtual) on July 17.
He’ll be joining peers from Microsoft, Palona, HP, Baseten, Stanford, and more.
@mlopscommunity
4
8
440
🚨 LLMs in Production: Day 3
“Hope isn’t a strategy.”
When your LLM provider goes down—and trust us, it will—how ready are you?
Today, we’re sharing fresh data from 650+ orgs on LLM provider reliability, downtime strategies, and how to keep things running smoothly (while cutting costs).
A thread on surviving (and thriving) in prod 👇
1
2
8
1,880
"Easy to use, easy to navigate... we could see the value immediately. Having all the LLMs together, logs, and latency data helps us identify issues much faster!"
- @orask, CTO of @XP3co
AI Gateway coupled with Observability is game-changer for productionizing AI
Hear from Oras directly 👇
3
7
363
2025 might be the "Year of AI Agents", but are they ready for real production use?🤔
We’re heading to @Magicball_dev to answer that, share some hot takes on AI agent infra, and hand out a few cool goodies ┏(・o･)┛
Come, say hi!
@retrovrv @siddhxrth10 @DrishtiShah7
3
4
8
699
The Latency Showdown:
p95 Latency for GPT-4o: OpenAI ~3s, Azure ~5s
But here's the real story:
OpenAI: Consistent latency
Azure: High variability
For production, predictability > raw speed
Azure’s quietly closing the gap, while OpenAI stumbled last month.
1
8
422
Vercel AI SDK has revolutionized AI app development, but the journey from prototype to production remains complex. Portkey addresses the critical gaps in this transition.
(A thread 🧵)
1
1
8
707
Anthropic: Fastest Growing Provider of 2024
• 61% monthly growth in requests
• 22% monthly growth in organizations
Anthropic has been on fire. Every time they launch a new Claude model (like Sonnet 3.5, Haiku-3.5), we see big adoption spikes: model releases matter.
Anthropic is used by 23% of Portkey orgs, cementing itself as OpenAI’s biggest rival
1
8
5,617
Celebrating (big) little wins 🏆
If you are a big tech, big pharma, big bank, or big (x), it's time to bring your engineering team to @PortkeyAI and take your Gen AI POCs to production.
Just DM @jumbld to learn how we can help 🤝
1
6
239
Team @PortkeyAI's been busy lately:
✔️ Now processing 10B+ LLM tokens *every day*
✔️ Added open source guardrails for enforcing real-time LLM behavior
✔️ Improved routing, tracing, and governance features
✔️ New integrations with @vercel, @phidatahq, @crewAIInc, and many more
Want to learn more? We'll be at the @Magicballai event this Monday. Stop by our booth to chat about how Portkey can support your AI apps - and pick up some goodies while you're there!
Join us: lu.ma/3ce0qjhd
2
8
491
✨Portkey is now a native provider in the @vercel AI SDK!
Build lightning-fast GenAI apps with Vercel, while ensuring they're robust with Portkey's powerful features.
Check out the docs: docs.portkey.ai/docs/integra…
Thanks @lgrammel for helping with this integration!
1
2
8
1,020
Excited to share insights on the emerging AI Gateway pattern at AI Tinkerers Bangalore tomorrow!
RSVP: bangalore.aitinkerers.org/p/…
Quality of demos at tomorrow's second AI Tinkerers Bangalore is 🤯 -- don't sleep on India for GenAI 🇮🇳 🚀
1
8
665
Today is a special day - we raised $3M
But something more important happened: @isro's Chandrayaan3 became the only mission in the world to land on moon’s south pole🌖
As we build a world-class LLMOps platform out of India, we take immense inspiration from what ISRO has achieved
3
1
8
404
vim 2024.txt
- respawn on github
- open source core of portkey
- get to 6,700 stars
- become *the* AI Gateway
- continue_building.jpg
- launch guardrails on the gateway
- partner with SOTA guardrail platforms
- do events around the world 🇺🇸🇮🇳🇶🇦🇳🇱🇸🇬🗽🌉
- build strong community with kind contributors
- first payment on Stripe 😭
- get even kinder customers who bet on us big time
- first enterprise payment 💸
- a lot of 🍻 & 🏸 in between
- continue_building.jpg
- onboard the world's largest tech, pharma, insurance, consulting companies
- *actual* growing pains now
- build governance, SSO, SCIM, and the whole nine yards
- get to supporting 250+ LLMs
- process over 2 TRILLION requests on the Gateway just this year
- launch prompt[dot]new
- continue cooking newer APIs & features
- ready to launch MCP client & Model Catalog in a few days
- build repeatable motion to $10M ARR 💪
- it's literally day 0 still
- 2025_is_looking_good.txt
:wq
2
2
8
423
Always fun to see Portkey in the hands of builders!
@mattblake_uk at Planet No Code just shared a walkthrough of how he’s using Portkey with Bubble — from setup to routing and tracking usage + spend
Here’s a quick snippet from the video 👇
If you're building AI apps & want clean observability without backend glue, it's worth checking out ->
piped.video/XJzjel6-VbY?feature…
1
8
310
🚀 AI Devs! Don't miss this:
@jumbld in conversation with @yujian_tang on "Enforcing real-time LLM behavior with Guardrails on the Gateway"
Learn how to
→ Build secure, robust AI apps
→ Prevent hallucinations
→ Implement effective guardrails
👇 Registration link below:
1
2
8
348
Happening now: @ojasvi_yadav at the Portkey office talking about EDA for multi-agent architecture
2
8
861
Potterverse unite! 🪄
Thrilled to share the @PatronusAI's industry-leading evaluators for retrieval accuracy, hallucination detection, toxicity, and much more — are now available on Portkey Gateway.
1. Add your Patronus API key to Portkey
2. Define Guardrail checks & set actions
3. Start making your requests with guardrails built in
That's it! It's incredibly easy, and free to get started with!
Introducing @PatronusAI + @PortkeyAI 🚀
@PortkeyAI is the leading open source AI gateway. It’s blazing fast and supports over 200+ LLMs. Today, you can use Patronus evaluators all within Portkey ✨
1
2
7
745
🚀. @OpenAI just dropped its new O1 model. Here's everything you need to know about it
🧵 Thread:
1
2
7
1,437
A massive thank you to @meronogbai & Luke Vanagas for their recent contributions to the Gateway!
Meron's contribution adds support for multiple user messages with Google Gemini, and Luke's implementation of Anthropic's input_tokens and output_tokens response params allows accurate usage tracking
Every commit, every line of code brings us closer to a truly unified AI Gateway 💪
2
7
465
Portkey x Qdrant Integration is Live! 🎉
You can now connect @qdrant_engine with Portkey. With this integration, you get:
• Unified API - Call Qdrant alongside your LLMs with Portkey's unified API
• Virtual Keys - Manage your API keys effortlessly
Streamline your AI workflows today! Link to docs 👇
1
7
221
Six Agent Frameworks, Twenty Six Cookbooks, AI Governance, and more - this was our month of June at Portkey 👇
1
2
7
518
What happens when you combine Portkey’s Universal LLM API with @arizeai's tracing & evals?
A faster way to test, compare, and pick the right model without rebuilding your stack.
In this new cookbook, different LLMs go head-to-head. Portkey handles the routing, Arize does the scoring.
Check it out - portkey.ai/docs/guides/integ…
1
1
7
272
Guardrails on the Gateway just got a power up!
Congratulations to the @PatronusAI team ✨
1/ Introducing the Patronus API: powerful AI evaluation models to accelerate your AI development 🚀
- 20% more accurate than ragas on hallucination detection
- Beats Perspective and Llama Guard on safety tasks by 28% and 11%
- Excels in practical domains like finance and customer support
Hundreds of elite AI teams across companies like @hospitable, @ExaAILabs, and Algomo use Patronus to do alpha evals ⚡
Try it out today: app.patronus.ai
1
1
7
415
Next up, was @RajaswaPatil from @getpostman on building Postbot
From disjointed features to a smooth-talking AI assistant - this team's journey with Postbot is a masterclass in evolving AI architectures.
Multi-agent systems, here we come!
1
2
7
298
80+ open-source models from @FireworksAI_HQ are now available on Portkey!
✅ Test your existing prompts on faster, cheaper open source models
✅ Switch to open source models without changing any underlying code
✅ Version, track, and deploy your prompts to production with one click
Just add your Fireworks API key to Portkey vault to get started!
2
7
1,003
Better availability, fewer 429s!
Vertex AI has rolled out global endpoints, and they’re now fully supported on Portkey!
If you’ve hit'resource exhausted' errors before, switching to the global endpoint can significantly improve availability and reduce throttling under load.
1
7
218
🚀 OpenAI just announced Predicted Outputs for GPT-4o & GPT-4o-mini models!
Dramatically decrease latency for gpt-4o and gpt-4o-mini:
• 2-4x faster response times than existing models while maintaining high accuracy.
•Large file edits that took ~70s now complete in ~20s.
Here's all you need to know:-
1
7
1,398
OpenAI: Still Leading, But Watch Out
• 24% monthly growth in requests
• 6% monthly growth in organizations
OpenAI remains the leader, but here’s the twist: their adoption has dropped from 89% to 76%.
Steady dominance? Yes. But competitors are catching up faster than expected.
1
7
323
Last weekend, we hosted an inspiring AI practitioners meetup with @ojasvi_yadav and @anudeepy_!
The focus? Building Multi-Agent Systems using Event-Driven Architecture and MCP
Here’s a glimpse of the session and more details 👇
📸 from the event
1
7
2,246
Prompt Engineering is broken and we are fixing it today! 🚀
We started with a simple question: 𝘸𝘩𝘺 𝘢𝘳𝘦 𝘱𝘳𝘰𝘮𝘱𝘵 𝘦𝘯𝘨𝘪𝘯𝘦𝘦𝘳𝘴 𝘴𝘵𝘪𝘭𝘭 𝘶𝘴𝘪𝘯𝘨 𝘣𝘢𝘴𝘪𝘤 𝘵𝘦𝘹𝘵 𝘦𝘥𝘪𝘵𝘰𝘳𝘴 𝘢𝘯𝘥 𝘮𝘢𝘯𝘶𝘢𝘭 𝘵𝘦𝘴𝘵𝘪𝘯𝘨 𝘸𝘩𝘦𝘯 𝘥𝘦𝘷𝘦𝘭𝘰𝘱𝘦𝘳𝘴 𝘩𝘢𝘷𝘦 𝘴𝘰𝘱𝘩𝘪𝘴𝘵𝘪𝘤𝘢𝘵𝘦𝘥 𝘐𝘋𝘌𝘴 𝘧𝘰𝘳 𝘤𝘰𝘥𝘦?
Introducing Portkey's Prompt Engineering Studio - the complete solution for modern AI teams 🧵
1
3
7
2,899
The Sorting Hat has spoken!
Open source → Gryffindor
OpenAI → Slytherin
Anthropic → Ravenclaw
Google → Hufflepuff
1
7
755
🔔Calling all Bengaluru AI builders🔔
Learn how to build production-grade & reliable AI apps this Sat at the @huggingface @Inferless_ party
Our CTO @ayushgarg_xyz will demo how you can add critical production functionalities on top of your existing LLM workflows with Portkey✨
2
2
7
930
OpenAI's new o1-preview and o1-mini models are supported on Portkey.
Compared to gpt-4o, these models reflect for a long time, and are able to answer questions like "how many r's in the word strawberry?", "how many words in your output?" exceptionally well.
o1 models work significatly better on maths, science, puzzle solving, and coding tasks.
Try them on Portkey:
1
1
7
576
🚨 @AnthropicAI just announced new weekly rate limits for Claude Code, and developers aren't happy.
Starting August 28, Claude Code users will face both 5-hour AND weekly usage caps.
This is hitting the developer community hard. Let's break down what's happening 🧵
1
6
1,325
Bringing AI agents to production just got a whole lot easier! 🚀
Over the past year, we've seen AI agents evolve from experimental tech to production-ready tools. But deploying them at scale? That's been a challenge.
With Portkey, we are addressing that challenge head-on.
Portkey now offers full support for AI agents, with just a 2-line code upgrade.
2
1
7
333
⚡ Day 0 support for Grok 4!
You can now start using @xai's Grok 4 via Portkey’s AI gateway.
Grok 4 currently tops the Artificial Analysis Intelligence Index and outperforms others in coding and math tasks.
With Portkey, bring Grok 4 into production with:
✅ Smart routing, failover, and retries built in
✅ Guardrails for safe, compliant interactions
✅ Full observability with logging, latency, and cost insights
✅ Budget and rate-limit controls across use cases
2
7
353
