Gemini 3 Flash API Pricing & Cost Calculator

Gemini 3 Flash costs $0.50 per 1M input tokens and $3.00 per 1M output tokens. A typical chat call (1000 input + 500 output tokens) costs approximately $0.0020. Use the calculator above to estimate your specific use case.

Gemini 3 Flash supports a 1049K token context window with a max output of 65,535 tokens. Knowledge cutoff: 2025-10.

Yes. Cached input is priced at $0.05 per 1M tokens — 90% cheaper than uncached input. This is especially valuable for repeated system prompts, long-context retrieval, and chat threads with shared history.

Yes. Gemini 3 Flash supports the Batch API at $0.25 input / $1.50 output per 1M tokens — typically 50% off standard pricing. Batch jobs complete within ~24 hours, ideal for non-realtime workloads like overnight data processing or content generation pipelines.

Yes, Gemini 3 Flash accepts image input. Vision token pricing is generally calculated based on image dimensions and folded into the input token count. Specific image-specific pricing varies — refer to Google's official documentation.

Token counts for Gemini 3 Flash are estimated from character ratios (~10-20% margin). Cost calculations use prices verified on 2026-08-01. For final billing accuracy, always verify with Google's usage dashboard.

Yes, Google offers fine-tuning for Gemini 3 Flash. Fine-tuned model pricing is separate from base model pricing — check Google's pricing page for current fine-tuning rates.