LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
he

HeyGen Decision 1 Turbo

heygen·heygen/heygen-decision-1-turbo·GA·Closed·Decision·NEW
HeyGen Decision 1 Turbo is a lower-cost, longer-context variant of HeyGen Decision 1 for high-volume classification, routing, and scoring. It evaluates text, structured JSON, up to four images, and one video against yes/no questions, custom choices, and ordered rubrics, returning typed answers with probabilities. It supports a 256K context window and is in preview.

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·Vercel AI GatewayCloud
$0.09 / $0
Blended $0.068 · 1× spread
Context
262,144
Output limit
—
Knowledge cutoff
—
Released / updated
2026-11-16 / 2026-11-16
Capabilities
ReasoningTool useStructured outputTemperature✓ Attachments
Modalities
TextImageVideo

HeyGen Decision 1 Turbo is offered by 2 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Vercel AI Gateway at $0.09 / $0 per 1M.

The context window is 262,144 tokens. Accepted input modalities are Text, Image, and Video.

Available at 2 providers2 with public prices

  • ProviderInput / Output
  • Vercel AI GatewayCloud
    $0.09 / $0
    Context 262,144
  • OpenRouterGateway
    $0.09 / $0
    Context 262,144
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Vercel AI GatewayCloud$0.09$0——262,144—
OpenRouterGateway$0.09$0——262,144—

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1Vercel AI Gateway$18.00
2OpenRouter$18.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $0.068

Price history accumulates from each data sync; currently only 1 sample(s) (2026-11-14). Each future sync adds a point, and once accumulated a line is drawn here.

Data partly from models.dev (MIT)