Gemini 1.5 Flash-8b Is Now Production Ready

Metadata

• Author: Simon Willison’s Weblog
• Full Title: Gemini 1.5 Flash-8b Is Now Production Ready
• URL: https://simonwillison.net/2024/Oct/3/gemini-15-flash-8b/#atom-everything

Highlights

• Gemini 1.5 Flash-8B is “a smaller and faster variant of 1.5 Flash” - and is now released to production, at half the price of the 1.5 Flash model. It’s really, really cheap: • $0.0375per1milliontokensonprompts<128K•$0.15 per 1 million tokens on prompts >128K • $0.01per1milliontokensoncachedprompts<128KIbelieveimagesarestillchargedataflatrateof258tokens,whichIthinkmeansasinglenon-cachedimagewithFlashshouldcost0.00097cents-anumbersotiny{I}^{\prime }mdoubtingifIgotthecalculationright.OpenA{I}^{\prime }scheapestmodelremainsGPT-4omini,at$0.150/1M input - though that drops to half of that for reused prompt prefixes thanks to their new prompt caching feature (and by half again if you use batches - Gemini also offer half-off for batched requests). Anthropic’s cheapest model is still Claude 3 Haiku at $0.25/M,thoughthatdropsto$0.03/M for cached tokens (if you configure them correctly). (View Highlight)