Last refreshed 2026-10-07. Next refresh: weekly.
Why use Riverflow 2.5 Fast on Replicate API?
Replicate API offers Riverflow 2.5 Fast with pay-as-you-go pricing at $10.00/1M output tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.
Compare Riverflow 2.5 Fast across 3 providers to find the best fit for your use caseInput / 1M
-
Output / 1M
$10.00
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install replicateAuth
export REPLICATE_API_TOKEN=...Call
import replicate
output = replicate.run(
"sourceful/riverflow-v2.5-fast",
input={"prompt": "Hello"}Model ID
sourceful/riverflow-v2.5-fastRequest example
import replicate
# reads REPLICATE_API_TOKEN from env
# sourceful/riverflow-v2.5-fast format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"sourceful/riverflow-v2.5-fast",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Gotchas
- Use provider model ID "sourceful/riverflow-v2.5-fast", not the LLMReference slug "riverflow-2.5-fast".
- Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
- The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.
Compare Riverflow 2.5 Fast Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Runware | — | — |
| OpenRouter | — | — |
| Replicate API | — | $10.00 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Output tokens | $10.00 |
Capabilities
VisionMultimodal
About Riverflow 2.5 Fast
Riverflow 2.5 Fast by Sourceful. Speed-optimized text-to-image and image-to-image generation for latency-sensitive production workflows. Supports 1K and 2K resolution outputs with up to 4 input images for editing. Features controllable reasoning effort (low/medium/high). Best suited for rapid creative iteration, packaging exploration, branded product visuals, and latency-sensitive pipelines. Available on Runware.
Get Started
Model Specs
Released2026-06-05