Sourceful: Riverflow 2.5 Pro
riverflow-2-5-pro- Price
- From $0.235
- Modalities
- Image
About Riverflow 2.5 Pro
Riverflow 2.5 Pro is the higher-capability variant of Sourceful's Riverflow 2.5 reasoning image model, aimed at commercial visual work that needs stronger quality and tighter brand control. It takes text-to-image and image-edit requests, with the family's deeper reasoning, review controls, Font Control, and 4K export. Pick it over Fast for final packaging, product, and advertising assets.
Where it works well
- Reasoning steps with review controls let the model check and revise candidates before returning one.
- Thinking levels run from low to extra high, with Sourceful pointing to the high end for consistent batch results.
- Custom scoring rubrics let you define what counts as on-brand for your own use.
- Font Control and 4K exports address typography and print-oriented deliverables.
When to choose another model
- Deeper reasoning is slower than the Fast variant, so it fits finals better than rapid exploration.
- It is designed for commercial marketing imagery, not for broad artistic experimentation.
- Higher thinking levels add review passes, so batch jobs at the top setting take longer per image.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Image editingText to imageTokenLab endpointPOST/v1/images/generationscurl -X POST "https://api.tokenlab.sh/v1/images/generations" \ -H "Authorization: Bearer sk-xxx" \ -H "Content-Type: application/json" \ -d '{ "operation": "image-to-image", "model": "riverflow-2-5-pro", "prompt": "A minimalist product photo of matte black headphones on a soft blue background.", "image_url": "https://example.com/source.png" }'
Parameters
Image editing
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
height | 624, 720, 832, 864, 896, 1024, 1120, 1152, 1248, 1280 | 1024 | Use an integer. Use a listed width and height pair: 1024x1024 (1k, 1:1), 1456x624 (1k, 21:9), 1280x720 (1k, 16:9), 1248x832 (1k, 3:2), 1152x864 (1k, 4:3), 1120x896 (1k, 5:4), 896x1120 (1k, 4:5), 864x1152 (1k, 3:4), 832x1248 (1k, 2:3), 720x1280 (1k, 9:16). |
image | Not provided | Not provided | Alias of the combined images input. See input_limits.images for the total input image count. |
image_url | Not provided | Not provided | Alias of the combined images input. See input_limits.images for the total input image count. |
image_urls | Not provided | Not provided | Alias of the combined images input. See input_limits.images for the total input image count. |
images | Inputs: ≥ 1, ≤ 10 | Not provided | Limits apply when this input is supplied. Image aliases are combined into one input image list; the limit applies to the combined list. |
n | 1 | 1 | Use an integer. |
operationRequired | Not provided | Not provided | Not provided |
output_format | jpeg, png, webp | Not provided | Default encoding is shared by these equivalent values: jpg, jpeg. |
prompt | Not provided | Not provided | Minimum length: 2 characters. Maximum length: 24000 characters. |
width | 720, 832, 864, 896, 1024, 1120, 1152, 1248, 1280, 1456 | 1024 | Use an integer. Use a listed width and height pair: 1024x1024 (1k, 1:1), 1456x624 (1k, 21:9), 1280x720 (1k, 16:9), 1248x832 (1k, 3:2), 1152x864 (1k, 4:3), 1120x896 (1k, 5:4), 896x1120 (1k, 4:5), 864x1152 (1k, 3:4), 832x1248 (1k, 2:3), 720x1280 (1k, 9:16). |
Text to image
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
height | 624, 720, 832, 864, 896, 1024, 1120, 1152, 1248, 1280 | 1024 | Use an integer. Use a listed width and height pair: 1024x1024 (1k, 1:1), 1456x624 (1k, 21:9), 1280x720 (1k, 16:9), 1248x832 (1k, 3:2), 1152x864 (1k, 4:3), 1120x896 (1k, 5:4), 896x1120 (1k, 4:5), 864x1152 (1k, 3:4), 832x1248 (1k, 2:3), 720x1280 (1k, 9:16). |
images | Not provided | Not provided | Text-to-image does not accept source images. Do not send this field for that operation. Use one of this model's declared image operations for source-image requests. |
n | 1 | 1 | Use an integer. |
operationRequired | Not provided | Not provided | Not provided |
output_format | jpeg, png, webp | Not provided | Default encoding is shared by these equivalent values: jpg, jpeg. |
prompt | Not provided | Not provided | Minimum length: 2 characters. Maximum length: 24000 characters. |
width | 720, 832, 864, 896, 1024, 1120, 1152, 1248, 1280, 1456 | 1024 | Use an integer. Use a listed width and height pair: 1024x1024 (1k, 1:1), 1456x624 (1k, 21:9), 1280x720 (1k, 16:9), 1248x832 (1k, 3:2), 1152x864 (1k, 4:3), 1120x896 (1k, 5:4), 896x1120 (1k, 4:5), 864x1152 (1k, 3:4), 832x1248 (1k, 2:3), 720x1280 (1k, 9:16). |
Fields outside this contract are rejected.
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Image editing
per image- Official price
- $0.235
- Verified price
- —
- Discount
- —
Text to image
per image- Official price
- $0.235
- Verified price
- —
- Discount
- —
| Official priceper image | Verified priceper image | Discount | |
|---|---|---|---|
| Image editing | $0.235 | — | — |
| Text to image | $0.235 | — | — |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open Riverflow 2.5 Pro in Console with a prompt ready to edit or send.
Help me create an image with riverflow-2-5-pro using image-edit at /v1/images/edits. Show the result, cost, and any limits I should know.
Use cases
Best for- Text to Image
Final packaging artwork
Produce on-brand label and pack images where exact product identity and lettering matter.
Advertising creatives
Generate ad visuals and score them against a paid-social rubric before choosing one.
Infographic and text-led images
Make graphics and ad layouts with controlled typography by supplying brand font files, so headlines match the lettering your design system already uses.
Batch consistency
Create sets of product images with matching lighting and color for a shop range.
Prompt examples
Create a premium cold-brew can render with the supplied label artwork, brushed aluminum, transparent background, 4K.
Edit this model photo: swap the jacket for a navy wool coat, keep face and pose unchanged, studio lighting match.
Design a landscape banner for a spring sale with the headline in the supplied brand font, floral border, plenty of copy space.
FAQ
What is Riverflow 2.5 Pro?
It is the most capable variant of Sourceful's Riverflow 2.5 family. It supports text-to-image and image editing, and targets production creative workflows where quality and brand control matter most.
How is Pro different from Fast?
Pro is positioned for stronger output quality and tighter brand control, while Fast is the speed-focused variant. Use Fast to explore and Pro to finalize.
What does thinking level do?
Sourceful lists levels from low, for faster exploration, up to extra high, which it recommends for consistent results in batch work. Higher levels mean more review passes.
Can it produce transparent images?
Yes. Sourceful lists background modes of transparent, solid color, and normal, which suits product compositing. Pick transparent when the image will sit on other artwork, and solid color for flat shop backdrops.
What can I edit with it?
It is built for editing as well as generation: send a source image with an instruction, such as swapping a garment or changing the scene, and the model keeps the subject recognizable. Sourceful targets product, packaging, and advertising imagery with this family.
How much does Riverflow 2.5 Pro cost?
On TokenLab, Riverflow 2.5 Pro costs $0.235 per image. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
Which endpoint should Riverflow 2.5 Pro use?
Use https://api.tokenlab.sh/v1/images/edits for Riverflow 2.5 Pro. The request example below shows the matching code shape.
Which operations does Riverflow 2.5 Pro support?
Riverflow 2.5 Pro supports Image editing, Text to image. Select an operation above to see its endpoint and request example.
Compare Riverflow 2.5 Pro
Sources
Reviewed Oct 2, 2026