Sourceful: Riverflow V2 Fast
- by sourceful
- sourceful/riverflow-v2-fast
Riverflow V2 Fast is the fastest variant of Sourceful's Riverflow 2.0 lineup, best for production deployments and latency-critical workflows. The Riverflow 2.0 series represents SOTA performance on image generation and...
What the numbers mean
- Context window8,192 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 6,100 words, or 12 pages.
- Max output7,372 tokens
- The longest single reply it can write: about 5,500 words.
- Input priceFree
- What you pay for everything the model reads. A 1,000-word prompt costs nothing.
- Output priceFree
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs nothing.
- Modalitiestext, image in, image out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.