Epoch AI estimates that LLM costs are falling by over 10x per year at fixed intelligence https://epoch.ai/data-insights/llm-inference-price-trends, so I expect prices to fall at this level of quality.
I also think there's a good division of labor here where you can use the smartest model to write the script and prompts, and then use a cheaper model for all the glue work and minor revisions that trigger the tool calls.
appreciate the pipeline. it's interesting to read the steps, see the outcome, and know about the costs/time.
In addition to the repo I have a long blog post reflecting on my experience here, including war stories, more detailed costs, and bloopers https://dawndrain.notion.site/Making-AI-Movies-39cbb81dad798...
Its going to cost a lot more than $200 once LLM subsidies run out.
Epoch AI estimates that LLM costs are falling by over 10x per year at fixed intelligence https://epoch.ai/data-insights/llm-inference-price-trends, so I expect prices to fall at this level of quality. I also think there's a good division of labor here where you can use the smartest model to write the script and prompts, and then use a cheaper model for all the glue work and minor revisions that trigger the tool calls.