We are delighted to welcome users to experience the LFM 2.5-24b-a2b model, which is currently live and ready for deployment at https://Qtum.ai.
Our platform proudly operates this as a self hosted model. It boasts a robust architecture featuring a 131k context capacity, paired perfectly with a 6k max output limit to comfortably accommodate your extensive tasks.
In addition, we have structured our pricing to be exceptionally affordable. Usage costs are fixed at a highly competitive rate of $0.01 per 1 million tokens for input, while the associated charge for output is just $0.03 per 1 million tokens.
For those who wish to dive deeper into the technical specifications and broader capabilities of LFM 2.5-24b, we warmly encourage you to review the comprehensive details provided at https://www.liquid.ai/blog/lfm2-5-24b-a2b.
Our platform proudly operates this as a self hosted model. It boasts a robust architecture featuring a 131k context capacity, paired perfectly with a 6k max output limit to comfortably accommodate your extensive tasks.
In addition, we have structured our pricing to be exceptionally affordable. Usage costs are fixed at a highly competitive rate of $0.01 per 1 million tokens for input, while the associated charge for output is just $0.03 per 1 million tokens.
For those who wish to dive deeper into the technical specifications and broader capabilities of LFM 2.5-24b, we warmly encourage you to review the comprehensive details provided at https://www.liquid.ai/blog/lfm2-5-24b-a2b.