Known vulnerabilities for a list of dependencies, npm and PyPI, in one call. Send {"npm":["[email protected]"],"pypi":["django==3.2.0"]} or a package.json or requirements.t…
Prediction market consensus probability for one yes/no question: an LLM judge keeps only markets that resolve on the same event, then a volume-weighted YES price with mi…
Corrected reticulocyte count (retic% × Hct/45), Hillman 1969 maturation-shift reticulocyte index, and optional absolute reticulocyte count. Deterministic published arith…
Brahmer 2018 ASCO Table 3.1 irAE pneumonitis. First-match: G4 life-threatening respiratory compromise; else G3 hospitalization, oxygen, limiting self-care, or all lobes/…
ASCO 2018 (Brahmer) irAE nephritis grade from creatinine vs baseline (mg/dL). First-match: 4 if dialysis or life-threatening; 3 if fold >3, creatinine >=4.0, or hospital…
Brahmer 2018 ASCO Table 4.1.1 irAE primary hypothyroidism grade from tsh_miu_l (0.01-150 mIU/L) and three caller-assigned flags. First-match: grade 3 if severe_or_life_t…
ASCO 2018 (Brahmer) immune-related hepatitis grade from caller AST, ALT, and total bilirubin as folds of laboratory ULN (mg/dL only). Lab grade is the max of transaminas…
Brahmer 2018 ASCO Table 4.4 irAE diabetes from glucose_mg_dl (50-1000, mg/dL only) plus caller ketosis, t1dm, severe_unable_adl, and life_threatening. First-match: G4 if…
Brahmer 2018 ASCO Table 2.1 irAE colitis grade from stools_over_baseline (0-40) and four caller-assigned flags. First-match: grade 4 if life_threatening; else 3 if stool…
Grogan 2016 ATTRwt staging: 1 point when NT-proBNP >3000 ng/L; 1 point when cardiac TnT >0.05 ng/mL. Stage I = 0, II = 1, III = 2. Equal to a cutoff does not score. Coho…
Gillmore 2018 NAC ATTR cardiac staging from NT-proBNP (ng/L) and caller-assigned eGFR. Stage I: NT-proBNP <=3000 and eGFR >=45. Stage III: NT-proBNP >3000 and eGFR <45.…
Callery 2013 Fistula Risk Score after pancreatoduodenectomy: gland texture firm 0 / soft 2; pathology PDAC or pancreatitis 0 / other (ampullary, duodenal, cystic, islet…
Hyams 2016 Rome IV H2c
magentHyams 2016 Rome IV H2c. rome_iv_child_abdominal_migraine is true iff paroxysmal intense periumbilical, midline, or diffuse pain lasting 1 hour or more, episodes weeks to…
Clinical trials run by a company, from ClinicalTrials.gov, newest first. Pass `?sponsor=Vertex Pharmaceuticals` (required) plus `?limit=` (max 100). Each trial carries N…
Quick pre-flight quality score: composite (0-100) + grade (A-F) + three framework sub-s…
promptqualityscore.comQuick pre-flight quality score: composite (0-100) + grade (A-F) + three framework sub-scores (PEEM, RAGAS, G-Eval) + verdict. Run upstream of any other paid call to filt…
Agent morning brief
tensorfeed.aiAgent morning brief. One paid call returns the last 24 hours of AI pricing changes, new and removed models, service-status incidents, and top news headlines. The endpoin…
Chat completions via Telnyx Inference (meta-llama/Meta-Llama-3.1-8B-Instruct). OpenAI-compatible. $0.002237 USDC per call.
A specific dated snapshot (YYYY-MM-DD, ids listed free at /) of the 129-series AI-progress and technology pull: frontier benchmark scores, compute trends, AGI prediction…
AI chat completions API - pay per request with USDC on Base
blockrun-web-vbsbhh7lea-uc.a.run.appAI chat completions API - pay per request with USDC on Base
Current weather at a location by latitude and longitude or city name: temperature, feels-like, humidity, precipitation, wind. Live conditions an LLM cannot know. weather…
AI chat completion
llm-toll-production.up.railway.appAI chat completion. Body: {"messages":[{"role":"user","content":"Hello"}]}. Returns AI reply.
AI-generated cryptocurrency market analysis report
bazaar-gateway.vercel.appAI-generated cryptocurrency market analysis report. Fetches real-time prices from CoinGecko then uses Claude AI to generate a professional market analysis with trends, r…
Live capacity of the Animica compute network in one call: which GPU render kinds have miners online right now and how many, whether a registered AICF worker is serving i…
Instruction-tuned mixture-of-experts model for high-volume work: classification, extraction, summarisation, routing and short chat. Chosen when throughput and cost matte…