Packets x402 REST usage
NextArk saved store-copy packet; no model generation
Model inference and embedding endpoints, including routers that front several providers. Context limits and prices change often, so treat the price with its check date.
NextArk saved store-copy packet; no model generation
GPT-5.6 Luna: OpenAI's small GPT-5.6. Fast and cheap for everyday calls.
Calculate recognized contribution and a separate contract completion forecast using integer USD cents and labor minutes. Returns formula inputs and assumptions; no client identifiers or accounting integrations.
Content purpose - Train local text baseline and classify: Train local text baseline and classify for Content purpose. Up to 200 supplied labelled text records. Local dataset tools, evaluation and small naive-Bayes baseli...
Audience level - Taxonomy prompt template: Taxonomy prompt template for Audience level. Up to 200 supplied labelled text records. Local dataset tools, evaluation and small naive-Bayes baselines; no hosted model or founda...
Full agent-readiness report for a website or API: everything in the readiness audit plus a quality review of the agent card, OpenAPI document, llms.txt, MCP server (connects, tools, descriptions) and pay-per-call manifes...
Full agent-readiness report for a website or API: everything in the readiness audit plus a quality review of the agent card, OpenAPI document, llms.txt, MCP server (connects, tools, descriptions) and pay-per-call manifes...
Course completion — Record quality audit + String normalisation + Two-measure correlation: Record quality audit + String normalisation + Two-measure correlation for supplied course completion records (completions, enrolm...
Tutorial completion — Equal-width histogram + Keyed dataset comparison: Equal-width histogram + Keyed dataset comparison for supplied tutorial completion records (starts, completions). Up to 200 rows; 2 independent repor...
Course completion — Equal-width histogram + Keyed dataset comparison: Equal-width histogram + Keyed dataset comparison for supplied course completion records (completions, enrolments). Up to 200 rows; 2 independent repor...
Delivery intent - Taxonomy prompt template: Taxonomy prompt template for Delivery intent. Up to 200 supplied labelled text records. Local dataset tools, evaluation and small naive-Bayes baselines; no hosted model or foun...
Cheapest H200 GPU rental — best hourly rate across cloud providers for large model inference — Ed25519 signed attestation
Cheapest L40S GPU rental — best hourly rate for inference-optimized NVIDIA GPU across providers — Ed25519 signed attestation
Cheapest RTX 4090 GPU rental — best hourly rate for cost-efficient AI inference and fine-tuning — Ed25519 signed attestation
Course completion — Duplicate key report + Numeric interval filter: Duplicate key report + Numeric interval filter for supplied course completion records (completions, enrolments). Up to 200 rows; 2 independent reports u...
Look up official fuel economy, annual fuel cost, electric range and emissions for a vehicle model year.
Momus football model: 1X2 probabilities, fair odds, correct-score grid and derived markets for one fixture. Deterministic Dixon-Coles, no LLM. Team names are matched loosely.
Momus MLB model: win probabilities for one game from a pitcher-aware Elo (starter FIP/ERA, bullpen, home field) fitted on 7,000+ games, the de-vigged market, the 60/40 blend Momus bets on, fair odds, probable starters. D...
LLM chat completion with no API key or signup (Claude Sonnet class, anthropic/claude-sonnet-5.5). OpenAI-compatible: set your SDK base URL to https://keyless-theta.vercel.app/best/v1. Flat $0.05 per call, up to 1500 outp...
News Gurus Intel API — Kelly-criterion outcome ledger: per-trade signal_type, pnl, r_multiple, kelly_fraction, narrative_score and llm_provider — the strategy's live performance history. Optional ?signal_type= filter for...
Notarize AI output in bulk: one signed Ed25519 attestation of the model response per record for up to 20 AI inferences in a single call — same content hash, receipt token, and anchor status as single notarization, giving...
Rewrite text in a style. Rewrite text to be more formal, casual, simpler, shorter, friendlier, more professional or more persuasive, keeping the meaning and language. Use to polish emails, replies, product copy and messa...
Prompt injection detection. Scan text an agent is about to read (web page, email, tool result; up to 8,000 characters) for prompt-injection attempts: instruction overrides, fake system messages, asks to hide things from...