نُشر في 2026-08-16 · 赵予安
الجواب المباشر
Google Gemini 3 Flash Preview is listed at 0.072 / 0.434 per million tokens, with a 1,048,576 token context window. First-party cache scores are unpublished. هذا الدليل موجه لفرق المنتج والمنصة التي تقارن جودة النماذج، والتكلفة، وسياسة التوجيه، ومخاطر الإطلاق.
What shipped
Google's Gemini 3 Flash Preview is now listed in the NextModel gateway catalog as google/gemini-3-flash-preview. The public slug is google--gemini-3-flash-preview. The provider is Google. The display name is "Google: Gemini 3 Flash Preview".
Price and context
The listed input price is $0.072 per 1M tokens. The listed output price is $0.434 per 1M tokens. The model has a context window of 1,048,576 tokens. The catalog places latency in the 1000 to 3000ms band. For comparison, Gemini 2.5 Flash is listed at $0.043 per 1M input tokens and $0.362 per 1M output tokens. Gemini 3.5 Flash Lite has the same listed rates. Gemini 3.1 Flash Lite is listed at $0.036 per 1M input tokens and $0.217 per 1M output tokens.
Who this is for
The catalog lists vision, long-context, and agent work as the use cases. The model has capabilities for streaming, tool calling, JSON, vision, and long-context tasks. Developers building agent, vision, or long-context applications are the intended audience.
What is still unverified
The release date is unpublished in this catalog snapshot. Independent third-party quality scores are not in these notes. No first-party CacheSafety row exists for this exact model. Safe Hit, Bad Hit, and trap rates are not available.