HN Showcase
Back to browse
Get GPT-5.2, Grok-4.1-fast, KimiK2.5 and more LLMs at half the cost

Get GPT-5.2, Grok-4.1-fast, KimiK2.5 and more LLMs at half the cost

by vnhc·Feb 28, 2026·2 points·0 comments
Visit ProjectView on HN

AI Analysis

●MidSlick

LLM API gateway with 2x credit matching, but model names appear fabricated.

Strengths
  • •OpenAI-compatible interface means zero SDK migration overhead
  • •Single key and unified billing across 9 different model families
  • •Per-token pricing with deposit matching incentive is clever cost structure
Weaknesses
  • •Model names (GPT-5.2, Grok-4.1-fast, Llama-4-Maverick) don't match actual releases; credibility damage
  • •No clear technical moat—API gateways are commoditized; Anthropic, Together AI, and Lambda Labs do this
Target Audience

AI application developers managing multi-model inference and cost optimization

Similar To

Lambda Labs · Together AI · Anthropic API

Post Description

Hey I'm Vansh. I built frogAPI because I was tired of managing separate accounts and billing for every AI provider.

It's an OpenAI-compatible API gateway. Swap your base URL to frogapi.app/v1, keep your SDK code, and pick from 9 models: GPT-5.2, GPT-5-Mini, GPT-5-Nano, DeepSeek-V3.2, Mistral-Large-3, Llama-4-Maverick, Kimi-K2.5, Grok-4.1-Fast, GPT-OSS-120B.

Per-token pricing matches the source models exactly. The way it works out cheaper: every deposit is matched with free credits. Put in $10, get $20 in credits. So your effective cost per token is half.

No subscriptions, no tiers. Pay per token.

Would love feedback.

https://frogapi.app

Similar Projects

Developer Tools●●Solid

LLM Gateway for OpenAI/Anthropic Written in Golang

Runs as a single binary with embedded SQLite and zero-config start, acting as a transparent, provider-agnostic proxy that logs model, tokens, latency, cost and API key hashes while leaving full body capture opt-in. It also proxies streaming responses in real time and exposes stable JSON analytics endpoints — a practical, instrumentable way to get reproducible, audit-ready traces for real LLM traffic, though long-term value depends on how it handles provider edge-cases and SDK compatibility.

Solve My ProblemNiche GemSlick
oatmale
423mo ago