LLM Reference

Riverflow Models by Sourceful

SourcefulProprietary
3 models2026

Last refreshed 2026-06-29. Next refresh: weekly.

Details

ResearcherSourceful
LicenseProprietary
Commercial useCommercial use: conditional
Models3
Released2026

Capabilities

Vision2 of 3 models
MultimodalAll models

Links

Website

About

Sourceful's agentic image generation and editing model family, optimized for production brand creative. Riverflow uses a reasoning model combined with open-weight diffusion models for high-precision text-to-image generation. Ranked #1 on the Artificial Analysis Image Editing Leaderboard.

Decision facts

Best fit
image generationvision and multimodal workagent workflows
Capability starting point
Riverflow 2.5 Pro with multimodal inputs
Lowest tracked input
Not tracked
Closest related family
Claude 3

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

3 in view

Use when the workload needs image generation and multimodal inputs.

2026-06image generationmultimodal inputs

Use when the workload needs image generation and multimodal inputs.

2026-06image generationmultimodal inputs

Use when the workload needs image generation and multimodal inputs.

2026-02image generationmultimodal inputs

Release Timeline

2 release groups
2026-06
2 current
Riverflow 2.5 Fast
image generationmultimodal inputs
Current
Riverflow 2.5 Pro
image generationmultimodal inputs
Current
2026-02
1 current
Riverflow 2.0
image generationmultimodal inputs
Current

Specifications(3 models)

Riverflow model specifications comparison
ModelReleasedVisionMultimodal
Riverflow 2.5 Pro2026-06YesYes
Riverflow 2.5 Fast2026-06YesYes
Riverflow 2.02026-02NoYes

Available From(1 provider)