models

Sourceful: Riverflow V2.5 Pro

Markdown · JSON

Sourceful: Riverflow V2.5 Pro

Riverflow 2.5 Pro is Sourceful’s quality-focused image generation and editing profile for product and campaign creative. Its family combines multi-step editing, custom judging and font control, helping a detailed brief preserve brand identity and the intended layout.

About the model

This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.

Riverflow 2.5 Pro is the Pro profile of Sourceful’s Riverflow 2.5 image generation and editing family, aimed at creative work where control and final image quality matter. A text brief can create a visual, while reference images supply the product, artwork or scene to edit. The family’s distinguishing approach plans several editing steps, reviews candidates and corrects them toward the requested result rather than treating the first image as the complete workflow.

For a campaign image, prepare the product references and brand direction before describing the scene. Specify the product features that distinguish one SKU from another, the arrangement, lighting and space needed for copy. A useful brief can place three labelled products into one coherent composition while keeping their colours, sizes and visible identity distinct. For a single-product lifestyle scene, identify which reference provides the object and which supplies the mood or setting, then state what should be preserved during the transformation.

Riverflow 2.5 adds a custom scoring rubric to its reasoning and review process. Describe the criteria that matter to the artifact: product identity, label readability, composition, scene plausibility or the amount of space for a headline. After editing steps, the reasoning model can assess candidates against that rubric and decide how to continue. A packaging-oriented result and an expressive campaign visual need different review priorities, so keep the generation instruction separate from the criteria used to judge it.

Thinking effort controls how much iterative work and how strict a review the family applies before accepting an image. The 2.5 producer workflow ranges from low to xhigh: lower effort supports early exploration, while more effort is useful when the brief needs additional refinement. More internal review does not remove the need to inspect the finished asset. For a demanding product layout, make the important details and acceptance criteria explicit so extra editing work has a clear goal.

Font Control accepts up to two custom font files and uses the supplied lettering, spacing and weight as guidance. Provide the exact words to render, the role of each text block and the corresponding font reference. A headline and a short supporting caption can use different fonts without leaving the typographic hierarchy implicit. Inspect the actual letters and numbers in the output, particularly where a package label or product name identifies the item, rather than treating a font reference as proof that every glyph is correct.

The 2.5 family provides normal, solid-colour and transparent background output modes, including transparent PNG for compositing, with export options at 1K, 2K and up to 4K. Select the artifact for its placement: a cutout for assembly into another design, a controlled solid background for consistent product sets or a completed scene for a campaign. Prepare the output shape and text placement together so increasing delivery detail does not solve a composition that puts the main subject in the wrong place.

Pro remains distinct from the Fast profile and from the earlier Riverflow 2.0 generation. The 2.5 family builds on 2.0’s multi-step foundation with deeper review control, custom judging and expanded background and export choices. A useful final review compares the image with the product references, rubric and typography, then changes the specific instruction or criterion responsible for a mismatch. Keep the selected image with its brief and references so the next edit can refine the same creative direction rather than losing its established identity.

Ailoot Ultra · Images POST /v1/images/generations sourceful/riverflow-v2.5-pro

sourceful/riverflow-v2.5-pro

Sourceful /sourceful/riverflow-v2.5-pro

Overview

Riverflow 2.5 Pro is Sourceful’s quality-focused image generation and editing profile for product and campaign creative. Its family combines multi-step editing, custom judging and font control, helping a detailed brief preserve brand identity and the intended layout.

Accepted inputs
Text · Images
Results
Images

Available in Ailoot · inputs & methods

Ailoot Ultra · Images POST /v1/images/generations
Input types
text, image
Output types
image
FieldTypeRequirementValues & limitsDefault
FieldmodelTypestringRequirementRequiredValues & limits
sourceful/riverflow-v2.5-pro
Default—
FieldpromptTypestringRequirementRequiredValues & limits
Minimum length: 1
Default—
FieldresolutionTypestringRequirementOptionalValues & limits
1K, 2K, 4K
Default—
Fieldaspect_ratioTypestringRequirementOptionalValues & limits
1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16, 21:9, auto
Default—
Fieldoutput_formatTypestringRequirementOptionalValues & limits
png, jpeg, webp
Default—
FieldbackgroundTypestringRequirementOptionalValues & limits
auto, transparent, opaque
Default—
FieldnTypeintegerRequirementOptionalValues & limits
Minimum: 1
Maximum: 1
Default—
Fieldinput_referencesTypearrayRequirementOptionalValues & limits
Minimum items: 0
Maximum items: 10
Default—
FieldproviderTypeobjectRequirementOptionalValues & limitsDefault—
Method parameters and lifecycle
ParameterContract
Parametercontent_typeContractapplication/json
ParameterrequiredContractmodel, prompt
Parametermaterial_typesContracttext, image

Lifecycle: synchronous_result_then_owned_library

GET /v1/media/tasks/{task_id} · actual returned task_id or media library record

GET /v1/media/assets/{asset_id}/content

GET /v1/media/assets

GET /v1/media/assets/{asset_id}

Pricing

How the final charge is calculated

The displayed rates estimate the cost before generation. The final charge is calculated from the cost recorded for the original generation. Measured output duration and forecast quantities are not the final billable quantity.

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode
Not specified When fast mode is selected
Flex mode
Not specified When flex mode is selected
Maximum reasoning effort
Not specified When maximum reasoning effort uses the default adjustment

Estimated rates for comparison

Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

ConfigurationRate scheduleForecast quantityBilling unitCharge
ConfigurationBase token ratesRate scheduleBase rateForecast quantity—Billing unit—Charge
Input · Input tokens · Estimate for comparison only — / 1K tokens
Output · Output tokens · Estimate for comparison only — / 1K tokens
Input · Cache read · Estimate for comparison only — / 1K tokens
Input · Cache write · Estimate for comparison only — / 1K tokens
Input · Cache write, 1 hour · Estimate for comparison only — / 1K tokens
Configurationoutput imageRate schedule—Forecast quantity—Billing unitper output imageCharge
Output · output image · Estimate for comparison only $0.26 per output image
ConfigurationEstimated generation costRate schedule—Forecast quantityone generation estimateBilling unit—Charge
Output · Estimated generation cost · Estimate for comparison only $0.26 estimate before generation

This estimate is not an additional charge or a fixed rate for the completed generation.

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →

Example requests

Ailoot Ultra · Images

curl
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
export AILOOT_API_KEY
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p={'model': 'sourceful/riverflow-v2.5-pro', 'prompt': 'a red panda astronaut floating in space, studio lighting'}

Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json, os, subprocess
from pathlib import Path
from urllib.parse import urlsplit, urljoin

def save_images(items):
    if not items: raise SystemExit("No completed images; retain the full response")
    for index, item in enumerate(items):
        encoded=item.get("b64_json")
        uri=item.get("url", "")
        if not encoded and uri.startswith("data:image/"):
            header, separator, encoded=uri.partition(",")
            if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")
        if encoded:
            raw=base64.b64decode(encoded,validate=True)
        elif uri:
            uri=urljoin("https://api.ailoot.ai",uri)
            parsed=urlsplit(uri)
            if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:
                raise SystemExit("Invalid returned image URL")
            owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")
            args=["curl","--fail-with-body","--silent","--show-error",uri]
            if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]
            temporary=Path(f"image-{index}.bin")
            subprocess.run(args+["-o",str(temporary)],check=True)
            raw=temporary.read_bytes()
            temporary.unlink()
        else: raise SystemExit("Image has neither bytes nor URL")
        if not raw: raise SystemExit("Empty image result")
        ext="png" if raw.startswith(b"\x89PNG") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"
        Path(f"image-{index}.{ext}").write_bytes(raw)
    print("Every returned image saved; complete response metadata retained")
save_images(json.loads(Path("result.json").read_text())["data"])
PY_RESULT

Receive and save results

Ailoot Ultra · Images

Download each returned image or save its Base64 contents

  • GET /v1/media/tasks/{task_id}
  • GET /v1/media/assets/{asset_id}/content
  • GET /v1/media/assets
  • GET /v1/media/assets/{asset_id}
Other content reads
Read existing owned assets
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \
  -H "Authorization: Bearer $AILOOT_API_KEY" -o owned-assets.json
# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.
Keep all completed results

Save every completed image; retrieve each returned URL or decode its Base64 contents.

Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.

If the original response needs checking

Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task_id/asset_id values or the owned media library; never build a task URL from the operation ID and never resubmit creation.

Response fields
FieldType
FieldcreatedType
Fielddata[].urlType
Fielddata[].b64_jsonType
FieldusageType

Aliases

Model aliases

Ailoot Ultra sourceful/riverflow-v2.5-pro

Method path aliases

/v1/images

Related caller IDs

sourceful/riverflow-v2.5-pro

FAQ · Sourceful: Riverflow V2.5 Pro
What inputs and results are available?

POST /v1/images/generations · sourceful/riverflow-v2.5-pro: text, image → image

Which fields does the request use?

POST /v1/images/generations · sourceful/riverflow-v2.5-pro: model, prompt, resolution, aspect_ratio, output_format, background, n, input_references, provider

What limits apply?

POST /v1/images/generations · sourceful/riverflow-v2.5-pro: n.minimum: 1; n.maximum: 1

More details

Connect Ailoot to Claude Code, OpenCode, Hermes or your own app.

The company and its project portfolio

The company and its project portfolio: millions of customers; monthly sales in the billions.

Buy tokens at a discount.

Subscription discounts for regular use. Promo codes offer up to 50% off token purchases.

Subscription
Choose a discounted plan for your regular requests.
Promo code: up to 50% off
Enter your code at checkout. The price updates to reflect the current promotion.
Spending in your history
The model, tokens and amount are recorded for each request.

Choose a subscription · View model prices

Connect the API to a product you sell.

Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale.

Commercial application
Add text, image, video and audio generation to paid features in your service.
Reseller licence
Send a description of your project and how you provide access. Request written terms for use and resale.
Documents on the website
The service offer, licence agreement and data processing policy are available before you connect.

Request a reseller licence · Service offer and licence agreement