Smaller and faster variant of 1.5 Flash features half the price, twice the rate limits, and lower latency on small prompts compared to its forerunner.
Google’s Gemini 1.5 Flash-8B AI model is now production-ready. The company said the stable release of Gemini 1.5 Flash-8B has the lowest cost per intelligence of any Gemini model.
Availability was announced October 3. Developers can access gemini-1.5-flash-8B for free via Google AI Studio and the Gemini API. Gemini 1.5 Flash-8B offers a 50% lower price compared to 1.5 Flash and twice the rate limits. Lower latency on small prompts also is featured.
An experimental version of Gemini 1.5 Flash-8B had been released in September as a smaller, faster variant of 1.5 Flash. Flash-8B nearly matches the performance of the 1.5 Flash model launched in May across multiple benchmarks and performs well on tasks such as chat, transcription, and long context language translation, Google said.
The stable release of Gemini 1.5 Flash-8B is priced at the following rates:
- $0.0375 per 1 million input tokens on prompts < 128K
- $0.15 per 1 million output tokens on prompts < 128K
- $0.01 per 1 million tokens on cached prompts < 128K
Developers on the paid tier will be billed beginning October 14. The new price, along with work Google has done to drive down developer costs with the 1.5 Flash and 1.5 Pro models, show the company’s commitment to ensuring that developers have the freedom to build products and services that push the world forward, Google said.
