Data as of November 13, 2026 · How the score is built
HeyGen Decision 1
Decision readingHeyGen Decision 1 is tracked, but not publicly ranked yet. The profile exposes 0 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Email me when its price, rank or availability changes.
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Decision-system
HeyGen Decision 1 TurboSpec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- heygen-decision-1HeyGen Decision API documentation
- Context window
- 131072 tokens per model readHeyGen Decision API documentation
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- text, image, videoHeyGen Decision API documentation
- Output modalities
- typed JSONHeyGen Decision API documentation
- Parameters
- Not disclosed by the provider
- Availability
- HeyGen APIHeyGen Decision API documentation
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- POST /v3/models/decisions with 1 to 400 named noul, choice and score questions over a text or JSON state, up to 4 images and 1 video. Synchronous JSON response with probabilities; no streaming, polling or webhook.HeyGen Decision API documentation
- Prompt caching
- Not documented in the pricing recordHeyGen Decision API documentation
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track HeyGen Decision 1, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
HeyGen Decision 1 is a proprietary model with a 131072 tokens per model read context window. No explicit reasoning mode is documented in this profile.
Available on the HeyGen API (POST /v3/models/decisions) with a production API key that has the assets:write scope; trial API keys and OAuth are not supported. No downloadable weights.
HeyGen Decision 1 is HeyGen's typed-decision model on POST /v3/models/decisions. It reads a text or JSON state with up to four images and one video (read as sampled frames) and answers 1 to 400 named questions in one synchronous request: noul (probability that a statement is true), choice (one of up to 255 options, with a probability for each) and score (an ordered scale of up to 10 levels). Output tokens are always zero. HeyGen documents a 131,072-token context budget per model read and calls confidence a property of the returned distribution, not a calibrated probability of being correct. HeyGen publishes no benchmark results for it, so none are recorded.
HeyGen Decision 1 sits in the HeyGen Decision 1 family with HeyGen Decision 1 Turbo. The profile has no source-displayable benchmark row yet.
Last updated November 13, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does HeyGen Decision 1 perform overall in AI benchmarks?
HeyGen Decision 1 does not have any source-displayable benchmark rows yet, so this profile does not assign a public score or rank. Documented specifications remain visible, while score-led charts and claims stay unavailable until a published evaluation can be attached to the exact model.
Which sibling models are related to HeyGen Decision 1?
HeyGen Decision 1 belongs to the HeyGen Decision 1 family. Related tracked variants include HeyGen Decision 1 Turbo. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does HeyGen Decision 1 have full benchmark coverage on BenchLM?
No. HeyGen Decision 1 currently has 0 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of HeyGen Decision 1?
HeyGen Decision 1 has a documented context window of 131072 tokens per model read. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.