Back to list
decisionavailableverified

Gemini Decision 1

Google

Typed decision questions (yes/no, choice, rubric) over shared multimodal input; no text generation.

Data basis
Input → Output
text, image, video, audio → text
Pricing unit
1M tokens
Access
api
Last verified
2026-11-12

Pricing and verification

Official: $0.10/M input (text, image, video, audio, PDF); output free (0 tokens); no cache; no Batch. Vercel AI Gateway: $0.10/M input, $0 output

Per 1M input tokens
$0.1
Per 1M output tokens
$0
Per 1M tasks
—
Context
262144 tokens
Price status
Priced
Verified
2026-11-12

Google Decisions API model gemini-decision-1, released 2026-11-11. Multimodal evaluations (binary, categorical, rubric) over shared input; up to 1,000 questions per request; shared input tokens billed once. Official paid tier: $0.10 / 1M input tokens, same price for text, image, video, audio, and PDF. Output is not applicable (0 output tokens; calibrated probabilities). Context caching is not available. Batch API is not supported. Free tier is available; free-tier content may be used to improve Google products, paid tier is not. Input token limit 262,144; output token limit 0. Deprecations table: no shutdown date announced. The catalog modality enum has no pdf member; PDF support is recorded here, not as a structured modality. Vercel AI Gateway google/gemini-decision-1: GET /v1/models on 2026-11-12 lists context_window 262144, max_tokens 0, type evaluation, pricing.input 0.0000001 ($0.10 / 1M), pricing.output "0". Gateway modalities list text, image, and pdf; official docs also include video and audio.

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

Google Decisions API model gemini-decision-1, released 2026-11-11. Multimodal evaluations (binary, categorical, rubric) over shared input; up to 1,000 questions per request; shared input tokens billed once. Official paid tier: $0.10 / 1M input tokens, same price for text, image, video, audio, and PDF. Output is not applicable (0 output tokens; calibrated probabilities). Context caching is not available. Batch API is not supported. Free tier is available; free-tier content may be used to improve Google products, paid tier is not. Input token limit 262,144; output token limit 0. Deprecations table: no shutdown date announced. The catalog modality enum has no pdf member; PDF support is recorded here, not as a structured modality. Vercel AI Gateway google/gemini-decision-1: GET /v1/models on 2026-11-12 lists context_window 262144, max_tokens 0, type evaluation, pricing.input 0.0000001 ($0.10 / 1M), pricing.output "0". Gateway modalities list text, image, and pdf; official docs also include video and audio.

Pricing and plans status

Official: $0.10/M input (text, image, video, audio, PDF); output free (0 tokens); no cache; no Batch. Vercel AI Gateway: $0.10/M input, $0 output

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.