LLM Context Feeder
Stop wasting tokens and start feeding intelligence. Most AI applications fail because they overwhelm the LLM with noise. LLM Context Feeder was built to solve the 'garbage in, garbage out' problem. Our API provides a high-performance injection layer that filters, structures, and optimizes your data before it hits the model. Why top developers choose us: Token Efficiency: Drastically reduce costs…
1 subscribers
8 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
LLM Context Feeder endpoints
| Method | Endpoint | Description |
|---|---|---|
| metrics | ||
| GET |
metrics_metrics_get /metrics |
Endpoint that serves Prometheus metrics. |
| extract | ||
| POST |
extract_stream_extract_stream_post /extract/stream |
Extrai URL e retorna o Markdown em tempo real via Server-Sent Events (SSE). Eventos: data: {"chunk": "..."} por fragmento; ao final data: {"done": true, "tokens_processed": N}. |
| POST |
extract_batch_extract_batch_post /extract/batch |
Coloca URLs na fila Redis (RQ). Worker processa e envia resultado ao webhook. job_id para rastrear. |
| POST |
extract_extract_post /extract |
|
| GET |
get_batch_job_status_extract_batch__job_id__get /extract/batch/{job_id} |
Consulta status e resultado de um job batch (RQ). |
| GET |
extract_extract_get /extract |
|
| crawl | ||
| POST |
crawl_crawl_post /crawl |
Deep crawling: descobre URLs do mesmo domínio (BFS, max_depth, max_pages), enfileira na fila RQ para extração em lote e retorna job_id. |
| Other endpoints | ||
| GET |
root__get / |
|
LLM Context Feeder pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | 5 / hour |
|
| PRO | $29 / month | 20 / minute |
|
| ULTRA | $99 / month | 50 / hour |
|
| MEGA | $449 / month | 100 / minute |
|
