We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
sourceful/riverflow-v2.6-proRuns on your balance at the prices above. New accounts start with free usage.
Settings
Sourceful: Riverflow V2.6 Pro is the flagship model in Sourceful's Riverflow 2.6 lineup. Sourceful builds the Riverflow family, and this Pro tier sits at the top of it. The model's main category is image generation, and it belongs to a family that treats generation as a production workflow, with an integrated reasoning model that plans the work rather than producing a single unconsidered pass.
The model accepts text and image inputs and produces image outputs. Its context window is 32,768 tokens, and it can emit up to 29,491 output tokens, which covers the reasoning the model performs alongside generation. Output images can be produced at 1K, 2K or 4K resolution, in aspect ratios covering 1:1, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 16:9, 9:16, 21:9 and auto. Files can be written as png, jpeg or webp, and the background can be auto, transparent or opaque. A single request returns one image, and up to ten input references can be supplied. A size parameter is also exposed. Because the model handles both text and image inputs, it supports text-to-image and image-to-image work in the same family.
Those capabilities point to a few practical patterns. With up to ten input references, image-to-image work such as restyling, composition guidance from reference material or iterative refinement of an existing image fits naturally. Transparent and opaque background options suit assets that need to drop into a layout, and the 21:9 and 9:16 ratios cover wide banners and vertical formats. Resolution up to 4K is useful when the result is the final asset rather than a draft. The reasoning parameters let a caller control how much planning effort the model spends before generating, which matters for prompts with several constraints.
You call the model through api14's OpenAI-compatible API using the model id "sourceful/riverflow-v2.6-pro". The supported parameters are include_reasoning, reasoning and reasoning_effort, so you can decide whether reasoning is returned and how much effort is applied. Image options are passed alongside the request, covering resolution, aspect ratio, output format, background, the number of images and any input references.
Because the model returns a single image per request, jobs that need several variations require separate calls. Text output is not among its output modalities, so tasks that need written answers belong with a text model. Anyone working with tight prompt constraints should consider how the reasoning parameters interact with latency before settling on settings.
%3B%0A%0Aconst%20result%20%3D%20await%20client.images.generate(%7B%0A%20%20%22model%22%3A%20%22sourceful%2Friverflow-v2.6-pro%22%2C%0A%20%20%22prompt%22%3A%20%22A%20minimalist%20product%20photo%20of%20a%20ceramic%20mug%20on%20a%20wooden%20table%22%2C%0A%20%20%22n%22%3A%201%2C%0A%20%20%22aspect_ratio%22%3A%20%221%3A1%22%0A%7D)%3B%0Aimport%20%7B%20writeFile%20%7D%20from%20%22node%3Afs%2Fpromises%22%3B%0Aawait%20writeFile(%22image.png%22%2C%20Buffer.from(result.data%5B0%5D.b64_json%2C%20%22base64%22))%3B%0A){kind=link}
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.images.generate({
"model": "sourceful/riverflow-v2.6-pro",
"prompt": "A minimalist product photo of a ceramic mug on a wooden table",
"n": 1,
"aspect_ratio": "1:1"
});
import { writeFile } from "node:fs/promises";
await writeFile("image.png", Buffer.from(result.data[0].b64_json, "base64"));
include_reasoningreasoningreasoning_effortThis community has no topics yet. Open the first one about Sourceful: Riverflow V2.6 Pro.