Riverflow 2.5. Pro for control, Fast for volume.
Sourceful's unified text-to-image and image-to-image family: Riverflow 2.5 Pro up to 4K with up to 10 references, and Riverflow 2.5 Fast for production volume.
- Text and image input
- Pro 1K to 4K, Fast 1K or 2K
- 8 aspect ratios plus auto
- Up to 10 reference images
- Transparent PNG backgrounds on Pro
Riverflow 2.5 is Sourceful's unified text-to-image and image-to-image family, in two tiers. Riverflow 2.5 Pro is the most capable, for top-tier control and quality-sensitive work, at 1K, 2K or 4K with up to 10 reference images. Riverflow 2.5 Fast is the speed tier for production and latency-critical work, at 1K or 2K with up to 4 references. Both offer eight aspect ratios plus auto, from 9:16 to 21:9.
In our tests a 1K square took 23 seconds on Fast and billed about 3 cents, and an edit with one reference took 46 seconds and about 6 cents. Pro took 123 seconds and billed about 25 cents. Both bill more than OpenRouter's listed per-image price, so Treza quotes what we measured. On Treza both sit in the Image Generation node's picker, and Fast is also in chat.
Two tiers
Fast for volume at about 3 cents an image, Pro for quality-sensitive finals at up to 4K. The prompt carries across unchanged.
Eight aspect ratios
1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16 and 21:9, plus auto, from vertical stories to ultrawide headers.
Up to 10 references
Pro takes up to 10 reference images and Fast up to 4, for edits and compositions built from your own assets.
Up to 4K on Pro
Pro renders at 1K, 2K or 4K; Fast at 1K or 2K. Draft small on Fast and render the final large on Pro.
What to make with Riverflow 2.5
Real prompts, and what comes back. Every one runs as a node on the Treza canvas.
“A ceramic cup of coffee on a sunlit wooden cafe table, steam rising, shallow depth of field”
A clean commercial still on Fast.
“The same folded shirt (attached) on a white marble counter in a bright studio”
Your product in a new set.
“A glass perfume bottle as a cutout on a transparent background, on Pro”
A transparent PNG to place on any layout.
“A 4K hero image of a skincare range on wet stone, on Pro”
A large final for print or crop.
“This label (attached) on these three bottle shapes (attached)”
Packaging mockups from your own assets.
“A 21:9 banner of a coastal road at sunrise for a website header”
An ultrawide still at the ratio you asked for.
Riverflow 2.5 is one node on a canvas
Chain it with language, image, and video models, then publish the whole pipeline as an API. See how a full AI video pipeline fits together.
- Step 01
Draft the brief
A language model node expands a one-line idea into a detailed, on-brand prompt before it ever reaches the model.
- Step 02
Generate with Riverflow 2.5
Run variants in parallel, compare against other models on the same prompt, and keep every result in run history.
- Step 03
Publish it as an API
The pipeline becomes a versioned endpoint. Your product calls it with the typed /invoke API or any OpenAI SDK.
Riverflow 2.5 as an API, priced per image
The Riverflow 2.5 API
Build a pipeline with Riverflow 2.5 on a node and publish it. It becomes a versioned HTTP endpoint: the typed /invoke route enqueues a run and returns a run id to poll, and an OpenAI-compatible route works with SDKs you already use. Agents connect over MCP the same way. Your prompt engineering ships inside the pipeline, so every caller gets your quality, and swapping the model later does not change the API your product calls.
Riverflow 2.5 pricing
Prepaid credits, no subscription. Each image is charged at Riverflow 2.5's own rate from your balance, shown before you run, and a failed generation costs nothing. Credit packs start at $5 and never expire, which suits spiky production schedules. Run history records the cost of every generation, per node, so spend is auditable rather than a surprise.
Riverflow 2.5, answered
What does Riverflow 2.5 cost?
OpenRouter lists Pro at 13, 15 and 17 cents per image at 1K, 2K and 4K, and Fast at 1.9 and 2.1 cents. Our tests billed more: about 25 cents for a 1K image on Pro, about 3 cents on Fast, and about 6 cents for a Fast edit with one reference. Treza quotes the measured amounts before a run.
What is the difference between Pro and Fast?
Pro goes up to 4K and takes up to 10 references; Fast goes up to 2K and takes up to 4. In our tests Fast came back in 23 seconds and Pro in about two minutes. Draft on Fast and finish on Pro when quality matters most.
Can I use Riverflow 2.5 in chat?
Riverflow 2.5 Fast, yes: ask for it by name and the image comes back in the conversation. Pro runs on the canvas, in the Image Generation node, where its longer renders do not hold up a chat turn.
How much does Riverflow 2.5 cost on Treza?
Treza uses prepaid credits with no subscription. Each image is charged at Riverflow 2.5's rate from your balance, and only successful generations are charged. Credit packs start at $5 and never expire.
Can I call Riverflow 2.5 through an API?
Yes. Build a pipeline that uses Riverflow 2.5 and publish it as a versioned HTTP endpoint. Call the typed /invoke API from your product, or point any OpenAI SDK at the OpenAI-compatible endpoint. If a better model ships later, swap it on the node without changing the API your product calls.
Your first video is one prompt away.
Generate your first video, image, or draft today. Prepaid credits, no subscription.