T
Token saver
Self-hosted caching proxy that cuts LLM API costs
3.8editorial
ํ๋ฆฌ๋ฏธ์
2026 ์ถ์
์๊ฐ
TokenSaver is a self-hosted caching proxy that sits between your app and the LLM API. It deduplicates prompts using SHA256 for exact matches and sentence-transformers embeddings for near-identical queries. Catch retries, refreshes, and the same question from different users before they reach the API. Includes per-user budgets, Slack/email alerts, rate limiting, per-model cost analytics, and anomaly detection. Free for up to 5 users (MIT).
์ฅ์
- +Deduplica prompts exatos e semelhantes, economizando custos de API
- +Oferece alertas via Slack e email para anomalias
- +Inclui anรกlise de custos por modelo e limites de taxa
๋จ์
- โVersรฃo gratuita limitada a 5 usuรกrios
- โRequer auto-hospedagem e configuraรงรฃo tรฉcnica
์์ฃผ ๋ฌป๋ ์ง๋ฌธ
O que รฉ o Token saver?
O Token saver รฉ uma ferramenta de inteligรชncia artificial especializada em open-source e developer-tools. TokenSaver is a self-hosted caching proxy that sits between your app and the LLM API. It deduplicates prompts using SHA256 for exact matches and sentence-transformers embeddings for near-identical queries. Catch retries, refreshes, and the same question from different users before they reach the API. Includes per-user budgets, Slack/email alerts, rate limiting, per-model cost analytics, and anomaly detection. Free for up to 5 users (MIT).
O Token saver tem versรฃo gratuita?
Sim, o Token saver oferece um plano gratuito com funcionalidades bรกsicas.
Quais sรฃo as melhores alternativas ao Token saver?
As principais alternativas ao Token saver sรฃo: -ludr-ai-understand-any-screen, session-bridge-ai, speakcli. Compare todas as opรงรตes no FindMyAI para escolher a ideal para o seu caso de uso.
