An LLM API gateway with budget-limited tokens for your LLM API keys
Overview This gateway is created to (1) keep real API keys completely away from the client, and (2) provide fine-grained budget control functionality. Real upstream API keys (DeepSeek, OpenAI, Anthropic) live only in the Cloudflare worker's secrets — they do not need to be set at the client. On each request, the gateway looks up the token from D1 database, verifies it's unexpired, from an allowed IP, and under budget, then substitutes in the real upstream secret and forwards the request.
- ▪Overview This gateway is created to (1) keep real API keys completely away from the client, and (2) provide fine-grained budget control functionality.
- ▪Real upstream API keys (DeepSeek, OpenAI, Anthropic) live only in the Cloudflare worker's secrets — they do not need to be set at the client.
- ▪On each request, the gateway looks up the token from D1 database, verifies it's unexpired, from an allowed IP, and under budget, then substitutes in the real upstream secret and forwards the request.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,266 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/er91/budget_aware_llm_api_gateway |
| Publication time | Mon, 20 Jul 2026 06:18:38 +0000 |
| Retrieval time | 2026-07-20T10:35:38.732Z |
| Last seen | 2026-07-20T10:35:38.732Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | RdGAeInDx4LY |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Overview This gateway is created to (1) keep real API keys completely away from the client, and (2) provide fine-grained budget control functionality. Real upstream API keys (DeepSeek, OpenAI, Anthropic) live only in the Cloudflare worker's secrets — they do not need to be set at the client. Instead, you create an opaque token scoped to: a single provider — the token only works against the provider it was created for an expiration time an IP allowlist — checked against CF-Connecting-IP, which Cloudflare's edge sets from the real TCP connection and a client cannot spoof a spending budget (in USD) Point your client's base URL at the gateway and use the opaque token in place of a real API key.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.