DEV Community

NovaStack profile picture

NovaStack

404 bio not found

Joined Joined on 
Building a Multi-Model LLM Router Without Losing Your Mind

Building a Multi-Model LLM Router Without Losing Your Mind

Comments
2 min read
Building a Multi-Model LLM Router Without Losing Your Mind

Building a Multi-Model LLM Router Without Losing Your Mind

Comments
2 min read
I A/B tested 4 LLMs on the same 500 queries. The results surprised me.

I A/B tested 4 LLMs on the same 500 queries. The results surprised me.

Comments
3 min read
I just got $50 free credits for LLM APIs. Here's what I'm testing with it.

I just got $50 free credits for LLM APIs. Here's what I'm testing with it.

Comments
2 min read
I'm tired of managing 4 different API keys for different AI models. Here's my fix.

I'm tired of managing 4 different API keys for different AI models. Here's my fix.

2
Comments
2 min read
Claude Code with non-Anthropic models — a working setup & what broke

Claude Code with non-Anthropic models — a working setup & what broke

Comments
3 min read
Got Claude Code working with open-source models via a unified API endpoint

Got Claude Code working with open-source models via a unified API endpoint

Comments
4 min read
I wired Claude Code to some newer models – here's the config that survived

I wired Claude Code to some newer models – here's the config that survived

Comments
3 min read
Claude Code Just Got a Massive Upgrade: Here's How to Connect It to Any API

Claude Code Just Got a Massive Upgrade: Here's How to Connect It to Any API

Comments
2 min read
We tried routing between 4 different LLMs automatically – here's what we learned

We tried routing between 4 different LLMs automatically – here's what we learned

Comments
2 min read
We Built a Single API for 4 Frontier LLMs (So You Don't Have To)

We Built a Single API for 4 Frontier LLMs (So You Don't Have To)

1
Comments
3 min read
{"title": "How I Cut My LLM Inference Costs by 40% While Handling 5x More Reques

{"title": "How I Cut My LLM Inference Costs by 40% While Handling 5x More Reques

Comments
3 min read
{"title": "How to stream reasoning tokens from an LLM in production: a practical

{"title": "How to stream reasoning tokens from an LLM in production: a practical

Comments
3 min read
From Cold Starts to Hot Paths: How I Cut LLM Inference Latency by 40% with a Simple Routing Trick

From Cold Starts to Hot Paths: How I Cut LLM Inference Latency by 40% with a Simple Routing Trick

Comments
2 min read
{"title": "Bending the Cost Curve: How I Slashed My LLM Inference Bill by 70% Wh

{"title": "Bending the Cost Curve: How I Slashed My LLM Inference Bill by 70% Wh

Comments
2 min read
{"title": "Bending the Cost Curve: How I Slashed My LLM Inference Bill by 70% Wh

{"title": "Bending the Cost Curve: How I Slashed My LLM Inference Bill by 70% Wh

Comments
2 min read
How I Cut My LLM Inference Costs by 40% While Keeping the Same Performance

How I Cut My LLM Inference Costs by 40% While Keeping the Same Performance

Comments
2 min read
Sharing a simple Python script to benchmark LLM inference latency across different providers

Sharing a simple Python script to benchmark LLM inference latency across different providers

Comments
2 min read
I benchmarked three LLM inference providers this week and one route surprised me

I benchmarked three LLM inference providers this week and one route surprised me

Comments
2 min read
**Title:** I benchmarked three LLM inference providers this week and one route s

**Title:** I benchmarked three LLM inference providers this week and one route s

Comments
2 min read
Prompt caching is great until you lock yourself into one provider.

Prompt caching is great until you lock yourself into one provider.

Comments
1 min read
Been testing different inference backends lately.

Been testing different inference backends lately.

Comments
1 min read
Meet NovaStack: the simplest way to buy and sell inference tokens. 🚀

Meet NovaStack: the simplest way to buy and sell inference tokens. 🚀

Comments
1 min read
NovaStack — token inference, reimagined. ⚡

NovaStack — token inference, reimagined. ⚡

Comments
1 min read
Meet NovaStack: the simplest way to buy and sell inference tokens. 🚀

Meet NovaStack: the simplest way to buy and sell inference tokens. 🚀

Comments
1 min read
Join this new token platform

Join this new token platform

Comments
1 min read
Building a Multi-Model AI Router in Python with Novastack 🚀

Building a Multi-Model AI Router in Python with Novastack 🚀

Comments
3 min read
Why You Need a Single API Gateway: The Novastack Solution for AI Model Token Forwarding

Why You Need a Single API Gateway: The Novastack Solution for AI Model Token Forwarding

Comments
3 min read
## Migrate from OpenAI to DeepSeek in 60 Seconds

## Migrate from OpenAI to DeepSeek in 60 Seconds

Comments
1 min read
he Single Key, Unified Gateway: Why Novastack is the Future of AI Model Access

he Single Key, Unified Gateway: Why Novastack is the Future of AI Model Access

Comments
3 min read
Why Novastack is the Future of AI Model Token Forwarding

Why Novastack is the Future of AI Model Token Forwarding

Comments
3 min read
The "One Key" API Gateway: Decoupling Your Models for Scalability

The "One Key" API Gateway: Decoupling Your Models for Scalability

Comments
3 min read
new token pai platform

new token pai platform

Comments
3 min read
loading...