Back to list
decisionavailableverified

Parallel Decisions Fast

Parallel

Typed, web-grounded answers (boolean, choice, score) with cited evidence.

Data basis
Input → Output
text → text
Pricing unit
— means unknown; unknown prices are never shown as free.
Access
api
Last verified
2026-11-14

Pricing and verification

Official Decisions API: $1/1,000 requests, up to 100 questions per request. Vercel AI Gateway: free through 2026-11-23.

Decisions API request
$1 / per 1k requests
Per 1M input tokens
—
Per 1M output tokens
—
Per 1M tasks
—
Context
—
Price status
Priced
Verified
2026-11-14

Official Parallel Decisions API list price is $1 per 1,000 requests, with up to 100 questions included in each call. Official docs name the product “Decisions”; “Decisions Fast” and the model id parallel/parallel-decisions-fast are from the Vercel AI Gateway changelog (published 2026-11-13). Vercel AI Gateway offers it free through 2026-11-23; no separate Parallel account is required on that channel. Question types on Vercel: Boolean (probability of yes), Choice, and Score. Related questions share context and retrieved evidence in one request. Official latency band: 200 ms–1 s, synchronous. No token rate or context window is published on the official pricing page. Sources verified 2026-11-14.

Model performance benchmarks
No audited, comparable public benchmark score is available yet. Music and world models do not currently have a unified public leaderboard; video models are seeded from public sources such as VBench / VBench++ where available.
Capabilities
web-grounded decisions

Official Parallel Decisions API list price is $1 per 1,000 requests, with up to 100 questions included in each call. Official docs name the product “Decisions”; “Decisions Fast” and the model id parallel/parallel-decisions-fast are from the Vercel AI Gateway changelog (published 2026-11-13). Vercel AI Gateway offers it free through 2026-11-23; no separate Parallel account is required on that channel. Question types on Vercel: Boolean (probability of yes), Choice, and Score. Related questions share context and retrieved evidence in one request. Official latency band: 200 ms–1 s, synchronous. No token rate or context window is published on the official pricing page. Sources verified 2026-11-14.

Pricing and plans status

Official Decisions API: $1/1,000 requests, up to 100 questions per request. Vercel AI Gateway: free through 2026-11-23.

Note: multimodal pricing can be seconds, generations, credits, minutes, plan allowances or enterprise contracts. It is not forced into token pricing; only verified source-backed rows appear below.

Pricing sources and usage units

No structured pricing reference row yet; showing official pricing unit and source links above.

Related plans

No mapped plan yet. Next step is to materialize plans for Runway, Kling, Pika, Luma, Suno, Udio and similar providers.