--- url: "https://predictiontoolkit.com/tools/eversight-and-signals-apis/" publisher: "PredictionToolkit" dateModified: "2026-11-02" --- [โ† Forecasting]() Research tool # Eversight and Signals APIs: Probabilistic Forecasts and Sourced Signals Eversight and Signals APIs provide Numinous forecasting and evidence retrieval for prediction-market questions, including Polymarket and Kalshi. Forecast jobs, signal queries and Numinous-1 inference are distinct operations. [**3.5**/ 5Editorial rating]() [Editorial assessment]() [Open Eversight]() eversight.numinouslabs.io **Available on:** Web ยท API **Pricing:** [See plans and costs โ†“]() [Screenshots]() [Explore alternatives]() [Forecasting]() [Data APIs]() +1 more [Signals]() ## Screenshots and interface Product preview1 / 3 Start a question and attach a market. ## What is Eversight and Signals APIs? Eversight accepts a precise question as an asynchronous job. Poll until COMPLETED before reading result.prediction on a 0โ€“1 scale. Signals accepts supported market URLs, slugs, condition IDs or questions and returns weighted material for research. Use as\_of to restrict historical retrieval, and distinguish published\_at from capture time. Numinous-1 is a specialized forecasting model with an OpenAI-compatible endpoint and structured output, not a general assistant. Its documented context window is 16,384 tokens; inspect finish\_reason and parsing if an answer is cut short. ### Who it is for - Developers building research assistants. - Analysts comparing forecasts with market prices. - Teams needing attributable evidence. ## Research coverage and methods - **Forecast jobs** Submit questions, poll states and read completed probabilities. - **Market-aware signals** Use URLs, slugs, condition IDs or free text. - **Attribution** Inspect material behind weighted signals. - **Historical retrieval** Use as\_of to preserve an earlier information boundary. - **News impact** Read supported scored signals and their direction. - **Related markets** Explore causal relationships with associated evidence. - **Numinous-1** Use the specialized forecasting model through an OpenAI-compatible endpoint with structured-output support. ## Research tasks ### Compare a forecast Read exact resolution terms, submit a job and wait for completion. Compare probability and quote while retaining evidence. ### Build a research panel Retrieve Signals, display linked material and separate publication and snapshot times. ### Replay past research Set as\_of before retrieval so later articles stay outside the earlier decision window. ## Pricing and total cost Metered access uses supported API-key or x402 payment paths. Forecast jobs, signals and model inference are separate operations; check their rate schedule before batching. ## Research inputs and access 1. Choose Eversight for jobs or Signals for evidence. 2. Configure the documented API-key or x402 route. 3. Start with a precise question or supported identifier. 4. Poll forecasts until COMPLETED before reading result.prediction. 5. Store sources and the query time boundary. 6. Handle truncation and structured parsing for model inference. [Read Eversight and Signals documentation]() ## Useful links ### What to check - Numinous-1 specializes in forecasting rather than general assistance. - Use either event\_id or condition\_id when mutually exclusive. - Publication and capture timestamps can differ. - The documented context window is 16,384 tokens; inspect finish\_reason for truncated output. A closer look ## Ratings & reviews Editorial rating **3.5**/ 5 0 user reviews PredictionToolkit editorial ### Our take on Eversight and Signals APIs Separate job and signal paths make integration clear. Asynchronous processing and metered operations need explicit budgets and careful reading of model output. **Assessment criteria:** Task usefulness, documented scope, setup clarity, and access and cost transparency. **Assessment date:** 2026-10-01 **Documentation reviewed:** 2026-10-01 Documentation-based assessment. [How we rate]() ### User reviews 0 The main score switches to user ratings after 5 published reviews. **Be the first to share your experience** A specific example helps the next person choose the right tool. ## Related tools [Browse category]() ![Numinous Tools agent-skill overview and installation paths]() [Numinous Tools]() SDK**3.5**Editorial Request forecasts and market evidence from an agent while tracking separately metered API usage. - Language Python Connect Numinous forecasts and sources to a compatible agent through its skill package. ![Alphascope market-research entry point and forecasting tools]() ![Alphascope logo]()[Alphascope]() Research tool**3.0**Editorial Request an AI forecast from a link, question or image, then compare market odds and news context. - Access Web Compare another research-focused market product. ![Polyseer market-link input and research entry page]() ![Polyseer logo]()[Polyseer]() Research tool**3.0**Editorial Paste a Polymarket or Kalshi contract link to start a focused AI research task through Valyu. - Access Web Compare another market-research interface. ## Frequently asked questions about Eversight and Signals APIs ### Where do I retrieve supporting articles? Use Signals retrieval endpoints. ### How is probability returned? Completed jobs return result.prediction from 0 to 1. ### Can I exclude later information? Use documented as\_of retrieval. ### Do these APIs execute trades? No. They supply research and probabilities; execution requires another integration. In this profile