Show HN: An unmetered LLM API–$6/month, no token tracking, no limits
14 hours ago
- #AI API
- #OpenAI-Compatible
- #Cost-Effective
- Yolo-auto provides unlimited Qwen3.6-35B access at a flat $6/month API rate, eliminating per-token costs and surprise bills.
- It features an OpenAI-compatible /v1 endpoint, integrates with tools like Cursor and LangChain, and does not store prompts or data for training.
- The free tier offers 15 requests/day for testing, while unlimited plans allow unrestricted tokens for agents and automations without caps.
- Using a Sparse MoE architecture with 35B parameters (3B active per token), it reduces compute costs and runs on dedicated bare-metal capacity.
- Suitable for tasks like batch processing, CI summaries, and high-volume jobs, it prioritizes affordability and predictable billing.