Alternatives
Products that do what European Swallow AI – Sonnet-quality coding at $2.60/M tokens does
Are you spending hundreds of dollars a month on AI coding costs? I built European Swallow AI, an API that uses reasoning models (Claude, Deepseek) for thinking and cheaper specialized coding models (Qwen, Grok) to write code, so you can save token costs while still getting high quality code. With an OpenAI formatted endpoint you can try European Swallow in Cursor, Typing Mind, Xibe AI and your own custom apps. During testing, European Swallow scored 80.5% on Big Code Bench and over 90% on the HumanEval+. It averaged $2.60 per million tokens compared with the $15 per million output tokens of…
- 1
- 2IP
The stack: two agents on separate boxes. The public one (nullclaw) is a 678 KB Zig binary using ~1 MB RAM, connected to an Ergo IRC server. Visitors talk to it via a gamja web client embedded in my site. The private one (ironclaw) handles email and scheduling, reachable only over Tailscale via Google's A2A protocol. Tiered inference: Haiku 4.5 for conversation (sub-second, cheap), Sonnet 4.6 for tool use (only when needed). Hard cap at $2/day. A2A passthrough: the private-side agent borrows the gateway's own inference pipeline, so there's one API key and one billing relationship…
Mar 2026 · georgelarson.me
- 3MO
I wanted to share our new speech to text model, and the library to use them effectively. We're a small startup (six people, sub-$100k monthly GPU budget) so I'm proud of the work the team has done to create streaming STT models with lower word-error rates than OpenAI's largest Whisper model. Admittedly Large v3 is a couple of years old, but we're near the top the HF OpenASR leaderboard, even up against Nvidia's Parakeet family. Anyway, I'd love to get feedback on the models and software, and hear about what people might build with it.
Feb 2026 · github.com
- 4IM
2022 · freesubtitles.ai
- 5
- 6
- 7LW
Some technical context on what we ran into building this. MCP tools don't really work for financial data at scale. One tool call for five years of daily prices dumps tens of thousands of tokens into the context window. And data vendors pack dozens of tools into a single MCP server, schemas alone can eat 50k+ tokens before the agent does anything useful. So we auto-generate typed Python modules from the MCP schemas at workspace init and upload them into the sandbox. The agent just imports them like a normal library. Only a one-line summary per server stays in the prompt. We have around 80…
Apr 2026 · github.com
- 8FF
I started leaning in on AI heavily this year, as I wanted to get more done autonomously, but then my token usage climbed dramatically to the point where my weekly quota would run out before the end of the week, sometimes a couple of days into the week. I realised I had to do something about it else I'd have to double my spend. So I decided to start tracking my cost per task type. This revealed that a lot of my spend went to searches/scans or simple things like scouting tasks. I then decided to turn this into a simple CLI tool that can be used to read your OpenAI-style logs locally, and…
Jul 2026 · github.com
- 9
- 10
- 11
- 12
- 13IB
Hello Hacker News, When learning foreign languages, I made the most progress by speaking them throughout the day, every day. So I made a site where you can *speak* to an AI language teacher to practice both listening and speaking. # The product *What I have now:* * Multilingual speech recognition: You can ask a question in English and get an answer in your target language. * Feedback on your grammar. * Suggestions: See examples of what to say next to keep the conversation flowing. * Speed: Choose a lower speed for beginners or a faster one for advanced levels. * Translations: Click to see a…
2023 · gliglish.com
- 14IB
In 2023, I tried my luck with four different educational apps, but none of them really made any money. Then, while working on an English learning website, I added a simple feature where users could chat with AI. Surprisingly, this became super popular! This got me thinking: why not create an app that lets people practice speaking English with AI characters? I put together a basic version of the app in a month and shared it on voz.vn, a well-known forum in Vietnam. The app got 500 downloads on the first day alone, though I didn't earn any money from it initially. In the next 3 months, I only…
2024 · fluentpal.app
- 15WV
I'm working on making it easier to use open-source AI models by providing simple APIs. Last week, OpenAI released Whisper v3, which showed improved performance across all its 100+ supported languages. We tried to optimize it as much as possible to be able to offer it for $0.0028 per minute (vs $0.006 on OpenAI). I hope it's helpful for someone: https://www.lemonfox.ai/apis/speech-to-text
2023
- 1601
Hey HN! I've been working on a side project to create an audio transcription API based on the OpenAI whisper model. Sign up link: https://whisperapi.com I tried to make the API really easy to use and get setup with. Also, because the Whisper model is so good, turns out I can offer the service for about 75% cheaper than what seems like the industry average. I'm always looking to make improvements, so would appreciate any feedback anyone has!
2022 · whisperapi.com
- 17OA
Hi HN, we're Kiran and Vijay! Over the past two years, we have built a columnar storage engine for observability: logs, metrics, and traces. Today, it's exciting for us to show what we've built on top of that foundation: LLM Agent Observability. Given how non-deterministic agents are, storing all traces without sampling was critical for us. But these traces tend to be in the MBs, sometimes GBs - we needed to store them inexpensively. We also needed the queries and analyses to be fast. To meet both these goals, we store them in S3 in our own parquet-like file format, and query them using AWS…
Jul 2026 · oodle.ai
- 18IB
Hey HN, I built an alternative to Google translate that's fast, accurate, and 1/30th the price. 20+ supported languages, not billed until 100k tokens, and already used thousands of times with real language learning users. The landing page has a demo for you to test performance yourself for free with no card required. (Also landing page says 1/13 the price because had to account for all 3 big names, with varying prices each). I built this as a workaround for my language learning startup, and it was perfect at a fraction of the cost. Hopefully it can help other devs in accessibility…
2023 · translateapi.web.app
- 19LI
A realtime, live transcription and translation app that works locally using a browser. Built with Huggingface Transformer.js and Supabase Realtime. Realtime in-browser speech-to-text with OpenAI Whisper! Broadcast to subscribed clients with Supabase Realtime. Translate to 200 languages with Meta's NLLB-200! Demo & source code https://supabase.link/realtime-ai-yt Shoutout to @xenovacom for building Transformers.js and providing plenty of examples at https://huggingface.co/docs/transformers.js/en/index#example...
2024 · github.com
- 20
Live pricing for 309+ AI models (GPT, Claude, Gemini, Llama, DeepSeek) plus real-world cost calculators: chatbots, API budgets, and token math. Updated 2026-09-06.
Aug 2026 · costperprompt.com
- 21OS
I built Whispering because I believe transcription is too fundamental a tool to be locked behind paywalls. It's a cross-platform desktop and web transcription app that turns speech into text with a keyboard shortcut, among other things. The app lets you bring your own API key (OpenAI, Groq, etc.) and make direct calls. If you want complete privacy, it also supports local transcription. Either way, your audio never goes through any middleman servers. It's super lightweight (~22MB), built with Svelte 5 and Tauri, and works on Mac, Windows, and Linux. I've been using it daily for the past few…
2025 · github.com
- 22IB
Hi HN! Since the launch of JigsawStack.com, we've been trying to dive deeper into fully managed AI APIs built and fine tuned for specific use cases. Audio/video transcription was one of the more basic things and we wanted the best open source model at this point it is OpenAI's whisper large v3 model based on the number of languages it supports and its accuracy. The thing is, the model is huge and requires tons of GPU power for it to run efficiently at scale. Even OpenAI doesn't provide an API for their best transcription model while only providing whisper v2 at a pretty high price. I…
2024 · github.com
- 23
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →