Prompt API Sampling Mode

Category: Miscellaneous
Type: New or changed feature
Status: Proposed (Chrome Proposed)
Intent stage: None

Breaking change: No
Enterprise impact: None
Chromium flag: prompt-api-sampling-mode
Spec maturity: Incubation
Web Platform Tests: Yes

WPT details: Yes; the API surface is tested in https://wpt.fyi/results/ai/language-model (language-model-availability-sampling-mode.tentative.https.window.html and language-model-create-sampling-mode.tentative.https.window.html). Automated testing of sampling parameter effects on probabilistic model response is not readily feasible; instead we conduct rounds of evaluations on configuration updates.

Summary

Allows developers to configure language model output variety and creativity in the Prompt API using high-level samplingMode presets. Instead of exposing raw numerical parameters like topK and temperature that vary unpredictably across models, developers can choose semantic presets ranging from "most-predictable" for deterministic extraction to "most-creative" for open-ended brainstorming. The browser maps these presets to optimal sampling hyperparameters for the underlying model, providing developers with reliable response tuning while preserving cross-browser interoperability. enum LanguageModelSamplingMode { "most-predictable", // For strict consistency/factual extraction "predictable", // For highly focused outputs "slightly-predictable", // For moderately focused, consistent outputs "balanced", // The default state for standard prompting "slightly-creative", // For moderately varied, expressive outputs "creative", // For tasks favoring variety over strict facts "most-creative" // For maximum token diversity and brainstorming }; This feature is an enhancement of the Prompt API (https://chromestatus.com/feature/5134603979063296).

Motivation

Web developers using the Prompt API often need to steer response variance to match their task, such as deterministic decoding for structured data extraction, classification, and tool calling, or higher output diversity for open-ended drafting and brainstorming. Raw numerical hyperparameters (`temperature` and `topK`) were excluded from the initial Prompt API launch due to cross-browser and cross-model interoperability concerns raised during TAG review (https://github.com/w3ctag/design-reviews/issues/1093), leaving web applications with no way to tune output variability beyond default session behavior. `samplingMode` bridges this gap with seven semantic presets (`"most-predictable"` through `"most-creative"`) that express developer intent without coupling web code to a single model's hyperparameter scale. User agents map each preset to model-specific sampling configurations and can apply mode-specific inference optimizations (such as greedy speculative decoding in `"most-predictable"` sessions). Live interactive demo: https://isaacahouma.github.io/prompt-api-sampling-presets/

Standards & signals

Specification: https://webmachinelearning.github.io/prompt-api
Firefox: Negative — View reflects parent specification
Safari: Oppose — View reflects parent specification
Web developers: Positive — Relative to the current shipped baseline (no sampling control on the web, since raw temperature and topK were excluded per TAG guidance), a significant fraction of developers support adding samplingMode to steer output variance, though a subset would still prefer the raw knobs: Developer Demand & Surveys: When asked to compare presets directly against raw parameters, 75% of parameter-tuning Early Preview Program (EPP) respondents accepted presets (55% preferred presets outright, 20% were open to them), while 25% would still prefer raw temperature / topK floats. Interoperable presets also address concerns from EPP sign-ups, where 33% flagged “Cross-Engine Prompt Fragility” (needing per-model tuning) and 22% cited “API Configuration Gaps” (e.g. inability to tune). The number of presets expanded from 5 to 7 options, partly in response to OT developer feedback around gaps in the predictable end of the spectrum. Telemetry: Across the modest samplingMode OT and the larger legacy (temperature & topK) Chrome extension usage, over 95% of tuned sessions opt for predictable outputs, with 75% choosing most-predictable and >60% setting equivalent parameters (temperature = 0 / topK = 1). Adoption Examples: Origin Trial partners (production e-commerce platforms, merchant website builders, and shopping extensions) and open-source projects rely on most-predictable and predictable (often paired with responseConstraint) for deterministic tasks such as catalog attribute extraction, merchant copywriting tools, intent classification, analysis of administrative procedures survey data by a governmental agency, and extraction of audio impairments from clinical report images. Other signals: The API implementation can deliver mode-specific inference speedups like Multi-Token Prediction (MTP) speculative decoding in most-predictable sessions (75% of parameter overrides, per our telemetry). This benefits users and developers by providing quicker responses while consuming less compute and power resources.
Tracking bug: https://issues.chromium.org/573612811

Ecosystem

Web Platform Tests: https://wpt.fyi/results/?q=ai%2Flanguage-model
Chrome Platform Showcase: https://chrome-platform-showcase.paulkinlan-ea.deno.net/features
GenDN reference: https://gendn.paulkinlan-ea.deno.net/features
chrome.dev demos search: https://www.google.com/search?q=site%3Achrome.dev+Prompt%20API%20Sampling%20Mode
MDN Web Docs: https://developer.mozilla.org/en-US/search?q=Prompt%20API%20Sampling%20Mode
Baseline status: https://webstatus.dev/?q=Prompt%20API%20Sampling%20Mode

Samples: https://isaacahouma.github.io/prompt-api-sampling-presets

Explainers: https://github.com/webmachinelearning/prompt-api#sampling-parameters

View on chromestatus.com