Gemini Decision 1
Typed decision questions (yes/no, choice, rubric) over shared multimodal input; no text generation.
价格与核验
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
- 每百万输入 token
- $0.1
- 每百万输出 token
- $0
- 每百万次任务
- —
- 上下文
- 262144 tokens
- 价格状态
- 已标价
- 核验日期
- 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.
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.
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
说明：多模态模型的计费可能是秒、次、积分、分钟、套餐额度或企业合同，不会强行换算成 token 价格。只有来源可验证时才写入下方表格。
暂无结构化价格来源行；当前只展示官方计价单位和顶部来源链接。
暂无已映射套餐。下一步会把 Runway、Kling、Pika、Luma、Suno、Udio 等套餐写入 plans。