Sourceful: Riverflow 2.5 Fast
riverflow-2-5-fast- Price
- From $0.021
- Modalities
- Image
About Riverflow 2.5 Fast
Riverflow 2.5 Fast is the speed-focused variant of Sourceful's Riverflow 2.5, a reasoning image model for creative production. It handles text-to-image and image editing, and shares the 2.5 family's custom scoring, Font Control, transparent or solid backgrounds, and 1K to 4K exports. Use Fast for rapid iteration on packaging, product visuals, and ad concepts; Pro is the higher-capability sibling.
Where it works well
- It is the quicker Riverflow 2.5 variant, suited to pipelines where response time matters.
- Font Control accepts up to two custom font files, so lettering follows brand typography.
- A custom scoring rubric lets you tell the model what a good result means for your use.
- Background modes include transparent and solid color, which helps when compositing product images.
When to choose another model
- Pro is positioned for stronger quality and tighter brand control, so use it for final commercial assets.
- Riverflow is tuned for marketing and product imagery rather than open-ended art styles.
- Several of the controls matter only if you actually supply fonts or rubrics.
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-fast", "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 | 576, 768, 960, 1024, 1152 | 1024 | Use an integer. Use a listed width and height pair: 1024x1024 (1k, 1:1), 1344x576 (1k, 21:9), 1024x576 (1k, 16:9), 1152x768 (1k, 3:2), 1024x768 (1k, 4:3), 960x768 (1k, 5:4), 768x960 (1k, 4:5), 768x1024 (1k, 3:4), 768x1152 (1k, 2:3), 576x1024 (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, ≤ 4 | 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 | 576, 768, 960, 1024, 1152, 1344 | 1024 | Use an integer. Use a listed width and height pair: 1024x1024 (1k, 1:1), 1344x576 (1k, 21:9), 1024x576 (1k, 16:9), 1152x768 (1k, 3:2), 1024x768 (1k, 4:3), 960x768 (1k, 5:4), 768x960 (1k, 4:5), 768x1024 (1k, 3:4), 768x1152 (1k, 2:3), 576x1024 (1k, 9:16). |
Text to image
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
height | 576, 768, 960, 1024, 1152 | 1024 | Use an integer. Use a listed width and height pair: 1024x1024 (1k, 1:1), 1344x576 (1k, 21:9), 1024x576 (1k, 16:9), 1152x768 (1k, 3:2), 1024x768 (1k, 4:3), 960x768 (1k, 5:4), 768x960 (1k, 4:5), 768x1024 (1k, 3:4), 768x1152 (1k, 2:3), 576x1024 (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 | 576, 768, 960, 1024, 1152, 1344 | 1024 | Use an integer. Use a listed width and height pair: 1024x1024 (1k, 1:1), 1344x576 (1k, 21:9), 1024x576 (1k, 16:9), 1152x768 (1k, 3:2), 1024x768 (1k, 4:3), 960x768 (1k, 5:4), 768x960 (1k, 4:5), 768x1024 (1k, 3:4), 768x1152 (1k, 2:3), 576x1024 (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
- $0.021
- Verified price
- —
- Discount
- —
Text to image
per image- Official price
- $0.021
- Verified price
- —
- Discount
- —
| Official priceper image | Verified priceper image | Discount | |
|---|---|---|---|
| Image editing | $0.021 | — | — |
| Text to image | $0.021 | — | — |
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 Fast in Console with a prompt ready to edit or send.
Help me create an image with riverflow-2-5-fast using image-edit at /v1/images/edits. Show the result, cost, and any limits I should know.
Use cases
Best for- Text to Image
Packaging exploration
Try many label and pack layouts quickly, with your brand fonts applied to the lettering.
Product shots on clean backgrounds
Edit a product photo into several scenes, or output on a transparent background for later composition.
Ad concept rounds
Produce variants of a campaign visual and score them against a conversion-oriented rubric.
Latency-sensitive pipelines
Generate or edit images inside an app where users wait for the result.
Prompt examples
Place this bottle on a sunlit kitchen shelf with fresh herbs, keep the label exactly as is, transparent background version as well.
Redesign this snack pouch front in a bold green palette, using the supplied brand font for the product name.
Generate a square social ad: a pair of running shoes on a concrete step, headline text left aligned, clean studio light.
FAQ
What is Riverflow 2.5 Fast?
It is the speed-optimized model of Sourceful's Riverflow 2.5 family. It supports text-to-image generation and image editing, and is meant for production creative work where response time matters as much as control.
How does Fast differ from Riverflow 2.5 Pro?
Fast prioritizes speed for iteration and latency-sensitive use, while Pro is the higher-capability variant for work needing stronger quality and tighter brand control. Use Fast to explore directions and Pro to finalize them.
What is Font Control?
You can provide up to two custom font files, and the model uses them to match lettering, spacing, and weight. Sourceful introduced it in the 2.5 release.
What is custom scoring?
You include a scoring rubric with the prompt, and the reasoning model uses it after each step to judge candidates. This steers results toward goals like pack approval or social conversion.
What output sizes and backgrounds exist?
Sourceful lists 1K, 2K, and 4K exports and three background modes: transparent, solid color, or normal. Transparent output is the one to use when a product image will be composited onto other artwork.
How much does Riverflow 2.5 Fast cost?
On TokenLab, Riverflow 2.5 Fast costs $0.021 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 Fast use?
Use https://api.tokenlab.sh/v1/images/edits for Riverflow 2.5 Fast. The request example below shows the matching code shape.
Which operations does Riverflow 2.5 Fast support?
Riverflow 2.5 Fast supports Image editing, Text to image. Select an operation above to see its endpoint and request example.
Compare Riverflow 2.5 Fast
Sources
Reviewed Oct 2, 2026