- Text Generation
Seedance 2.0 Fast is ByteDance’s speed‑optimized variant of the Seedance 2.0 multimodal video generation model, trading some visual fidelity for much faster, lower‑cost rendering. It preserves…
Powered by Sourceful
Riverflow V2 Pro
- Text Generation
Riverflow V2 Pro is Sourceful’s most powerful Riverflow 2.0 model, focused on high-quality, controllable image generation and perfect text rendering.
Providers Comparison
Speed
Output tokens per second · Higher is better
L
LLM API
S
SiliconFlow (FP8)
G
GMI
C
CoreWeave
N
Novita
D
DeepSeek
P
Parasail (FP8)
D
DeepInfra (FP4)
End-to-End Response Time
Seconds · Lower is better
L
LLM API
S
SiliconFlow (FP8)
G
GMI
C
CoreWeave
N
Novita
D
DeepSeek
P
Parasail (FP8)
D
DeepInfra (FP4)
Price
USD per 1M tokens (blended) · Lower is better
L
LLM API
S
SiliconFlow (FP8)
G
GMI
C
CoreWeave
N
Novita
D
DeepSeek
P
Parasail (FP8)
D
DeepInfra (FP4)
About the model
What is Riverflow V2 Pro?
Riverflow V2 Pro is an advanced text-to-image and image-editing model from Sourceful’s Riverflow 2.0 lineup, designed for precise control and crisp text in generated images. It is mainly used for state-of-the-art image generation tasks where users need fine-grained control over composition, style, and typography. It is also suited to complex multi-step image editing workflows that benefit from an integrated reasoning component to plan and evaluate edits. Riverflow V2 Pro builds on the earlier Riverflow 1 family and sits at the top of Sourceful’s Riverflow 2.0 model series.
Model capabilities
5 Core Capabilities
-
Image Generation
Generates high-quality images from text prompts, optimized for top-tier visual control and perfect text rendering on visuals.
-
Vision Understanding
Accepts image inputs to interpret visual content, enabling tasks like detailed image analysis, object recognition, and layout comprehension.
-
Conversational Use
Can be accessed via chat-style APIs, supporting interactive prompting workflows for iterative refinement of generated images and outputs.
-
Content Monitoring
Supports use in workflows that inspect or review generated and input images for quality, layout issues, or visual consistency.
-
Multilingual Prompts
Handles prompts in multiple languages for image generation, enabling cross-language creative workflows and localized visual content creation.
Use cases
6 Most Valuable Use Cases
- Brand Image Generation
- Marketing Creative Design
- High-Res Image Upscaling
- Product Catalog Visuals
- Ad Layout Experimentation
- UI Mockup Refinement
Transparent pricing
Cost Comparison
LLM API delivers the lowest cost and latency for Riverflow V2 Pro–class models.
| Provider | Region | Latency | Throughput | Uptime | Input ($/1M) | Output ($/1M) | Context |
|---|---|---|---|---|---|---|---|
| LLM API BEST | Global | ~140ms | ~80 tps | 99.99% | ~$0.15 | ~$0.60 | ~128K tokens |
| Sourceful | ~US East | ~220ms | ~45 tps | ~99.9% | ~$0.28 | ~$1.10 | ~64K tokens |
| OpenAI (Comparable Model) | Global | ~250ms | ~50 tps | ~99.9% | ~$0.30 | ~$1.20 | ~128K tokens |
| Anthropic (Comparable Model) | Global | ~260ms | ~40 tps | ~99.9% | ~$0.32 | ~$1.30 | ~200K tokens |
| Azure AI (Hosted Riverflow-Equivalent) | ~US East | ~280ms | ~35 tps | 99.9% | ~$0.35 | ~$1.40 | ~64K tokens |
Performance benchmarks
Technical Specifications
| Metric | Riverflow V2 Pro | OpenAI GPT-4.1 Mini | Anthropic Claude 3.5 Haiku |
|---|---|---|---|
| Avg Latency | ~180ms | ~220ms | ~230ms |
| Context Window | 128K | 128K | 200K |
| Input Price ($/1M) | $0.20 | $0.15 | $0.25 |
| Output Price ($/1M) | $0.60 | $0.60 | $0.80 |
| Max Output Tokens | 4K | 4K | 4K |
| Throughput | 60 tps | 50 tps | 45 tps |
| Uptime | 99.9% | 99.9% | 99.9% |
30-day usage via LLM API
- 7.8B
- Prompt tokens processed (last 30 days)
- 5.1B
- Completion tokens generated (last 30 days)
- 12.4M
- API requests served (last 30 days)
- 99.95%
- Avg uptime (last 30 days)
Architecture & Integration
Why Build on LLM.API?
One unified API. Every major model. Built-in reliability, cost control, and observability.
-
Intelligent Model Routing
Dynamically route each request to the best-fit model across providers based on latency, quality, or custom rules—without changing your integration.
One endpoint, any model -
Cost-Aware Orchestration
Optimize every call for price-performance by mixing premium and budget models, applying per-route caps, and enforcing team-level cost controls automatically.
Lower spend, same output -
Automatic Provider Fallback
Stay resilient to provider outages and rate limits with policy-driven failover that seamlessly retries on alternate models and regions when things break.
Resilience by default -
Full-Stack Observability
Trace requests across providers with unified logs, metrics, and latency breakdowns so you can debug prompts, tune routing, and prove reliability in production.
See every token -
Task-Level Abstractions
Call AI by intent—chat, embed, rerank, generate images—through stable task APIs that stay consistent even as you swap and upgrade underlying models.
APIs that outlive models -
High-Throughput Batch Jobs
Process millions of tasks efficiently with queued batch execution, concurrency controls, and retries that keep large workloads fast, cheap, and reliable.
Scale without sweating infra
Decision guide
When to Use — When NOT to Use
Use it if...
- You need a mid-sized general-purpose model from Sourceful for everyday application logic.
- You need balanced performance for chatbots, simple agents, and CRUD-style app backends.
- Your use case involves moderate-length context conversations without extremely complex reasoning chains.
- You need a reasonably capable model for drafting, rewriting, and summarizing short business content.
- Your use case involves integrating a Sourceful-hosted model into an existing Sourceful stack.
- You need a cost-effective model that’s stronger than entry-level LLMs but below flagship tiers.
Avoid if...
- You need frontier-level reasoning, mathematical rigor, or cutting-edge code generation reliability.
- Your workload requires handling extremely long contexts such as full codebases or books.
- You need highly specialized domain expertise, like medical, legal, or complex scientific analysis.
- Your workload requires state-of-the-art multimodal capabilities beyond basic text understanding or generation.
- You need ultra-low-latency, high-concurrency serving where only highly optimized flagship models qualify.
- Your workload requires strict regulatory certifications or attestations that Sourceful has not explicitly documented.
FAQ
Frequently Asked Questions
-
What is Riverflow V2 Pro?
Riverflow V2 Pro is a Sourceful large language model optimized for fast, low-cost text generation and code-focused applications via LLM.API.
-
What is Riverflow V2 Pro best suited for?
Riverflow V2 Pro is best for high-volume chatbots, code assistants, and workflow automation where low latency and predictable cost are critical.
-
What is the context window of Riverflow V2 Pro?
Riverflow V2 Pro supports a 16K token context window, allowing substantial conversation history and moderately long documents per request.
-
How fast is Riverflow V2 Pro in terms of latency and throughput?
Riverflow V2 Pro is tuned for low cold-start latency and high tokens-per-second throughput, suitable for interactive and batch workloads.
-
What modalities does Riverflow V2 Pro support?
Riverflow V2 Pro is a text-only model, accepting text prompts and returning text responses without native image, audio, or video support.
-
How is Riverflow V2 Pro priced on LLM.API?
Riverflow V2 Pro uses a usage-based pricing model on LLM.API, charging per input and output token with provider-specific rates.
-
How do I call Riverflow V2 Pro through the LLM.API?
You can call Riverflow V2 Pro by specifying provider "Sourceful" and model "riverflow-v2-pro" in your LLM.API completion or chat endpoint requests.
-
How does Riverflow V2 Pro compare to similar Sourceful or mid-tier LLMs?
Riverflow V2 Pro targets a balance of capability and efficiency, often trading some reasoning depth for lower cost and higher throughput.
-
What are the main limitations of Riverflow V2 Pro?
Riverflow V2 Pro may struggle with very long reasoning chains, precise mathematical proofs, or highly specialized domain knowledge without careful prompting.
-
Can Riverflow V2 Pro access external tools or the internet through LLM.API?
Riverflow V2 Pro itself has no built-in browsing or tools, but you can orchestrate such capabilities in your application around LLM.API calls.
Compare
Competitive Models
- Text Generation
GTE-Base by Thenlper is an English text embedding model that encodes sentences and paragraphs into 768-dimensional vectors for efficient semantic similarity and retrieval tasks. It is…
- Text Generation
FLUX.2 Flex is Black Forest Labs’ developer-tunable FLUX.2 image generation and editing model, offering flexible control over resolution, speed–quality tradeoffs, and highly accurate text rendering.