Get My API Key
Get My API Key

Powered by Sourceful

Riverflow V2 Fast Preview

  • Text Generation

Riverflow V2 Fast Preview is Sourceful’s fastest preview variant in the Riverflow V2 lineup, offering high-throughput text-to-image and image-to-image generation with an 8K token context window.

Start Using API

Providers Comparison

Speed

Output tokens per second · Higher is better

246
97
92
91
90
80
60
27
LLM API
SiliconFlow (FP8)
GMI
CoreWeave
Novita
DeepSeek
Parasail (FP8)
DeepInfra (FP4)

End-to-End Response Time

Seconds · Lower is better

65.1
8.1
19.8
20.4
20.9
23.1
24.6
30.6
LLM API
SiliconFlow (FP8)
GMI
CoreWeave
Novita
DeepSeek
Parasail (FP8)
DeepInfra (FP4)

Price

USD per 1M tokens (blended) · Lower is better

65.1
8.1
19.8
20.4
20.9
23.1
24.6
30.6
LLM API
SiliconFlow (FP8)
GMI
CoreWeave
Novita
DeepSeek
Parasail (FP8)
DeepInfra (FP4)

About the model

What is Riverflow V2 Fast Preview?

Riverflow V2 Fast Preview is a preview-stage Sourceful model that unifies text-to-image and image-to-image capabilities for fast, production-oriented visual generation. It is mainly used for quickly generating design, branding, and illustration assets from text prompts, and for rapidly transforming or iterating on existing images in latency-sensitive workflows. It also supports 8K context for complex prompt specifications and multimodal inputs where both textual and visual instructions guide the output. As part of the Riverflow V2 preview family, it succeeds and outperforms the earlier Riverflow 1 models while sitting alongside the Riverflow V2 Standard Preview and Riverflow V2 Max Preview variants.

Model capabilities

5 Core Capabilities

  • Text-to-image generation

    Generates high-quality images directly from natural language prompts using Sourceful’s unified text-to-image generation pipeline.

  • Image-to-image editing

    Transforms or refines existing images based on text instructions, leveraging unified image-to-image generation capabilities.

  • Image input handling

    Accepts image inputs, including via URLs within size limits, enabling multimodal workflows combining visual and textual information.

  • Fast interactive workflows

    Optimized as the fastest Riverflow V2 preview variant, suitable for interactive, latency-sensitive image applications and rapid experimentation.

  • Multilingual prompt support

    Supports prompts in multiple languages for controlling image generation, allowing localized visual content creation from diverse text inputs.

Use cases

6 Most Valuable Use Cases

  • High-speed image generation
  • Image editing workflows
  • Custom font graphics
  • Super-resolution enhancement
  • Latency-critical production apps
  • Multistep visual reasoning

Transparent pricing

Cost Comparison

LLM API offers the lowest cost and latency for Riverflow V2 Fast Preview–class models.

Provider Region Latency Throughput Uptime Input ($/1M) Output ($/1M) Context
LLM API BEST Global 80ms 120 tps 99.99% $0.20 $0.60 128K
Sourceful Global ~220ms ~45 tps ~99.9% ~$0.30 ~$0.90 ~64K
OpenRouter Global ~240ms ~40 tps ~99.9% ~$0.32 ~$0.95 ~64K
Together AI US East ~250ms ~38 tps ~99.9% ~$0.34 ~$1.00 ~64K

Performance benchmarks

Technical Specifications

Metric Riverflow V2 Fast Preview OpenAI GPT-4.1 Mini Anthropic Claude 3 Haiku
Avg Latency ~180ms ~220ms ~250ms
Context Window 128K 128K 200K
Input Price ($/1M) $0.05 $0.15 $0.25
Output Price ($/1M) $0.10 $0.60 $1.25
Max Output Tokens 4K 4K 4K
Throughput 80 tps 60 tps 50 tps
Uptime 99.9% 99.9% 99.9%

30-day usage via LLM API

2.8B
Prompt tokens processed (last 30 days)
460M
Completion tokens generated (last 30 days)
3.1M
API requests served (last 30 days)
98.9%
Average uptime (last 30 days)
Start Using API

Architecture & Integration

Why Build on LLM.API?

One unified API. Every major model. Built-in reliability, cost control, and observability.

  • Unified AI Routing

    Dynamically route each request to the optimal model or provider based on cost, latency, or quality—no client changes, just smarter traffic from a single endpoint.

    One endpoint, every model

  • Cost-Aware Orchestration

    Automatically balance premium and budget models, enforce spend controls, and track per-team usage so you ship faster without surprise invoices or manual tuning.

    More performance per dollar

  • Resilient Fallbacks

    Define fallback chains across providers so outages, rate limits, or bad responses transparently fail over—keeping your AI features up without incident pages.

    Never go dark

  • Deep Observability

    Get per-request traces, metrics, and logs across all models and vendors in one place, making debugging, optimization, and compliance reviews actually manageable.

    One pane for all calls

  • Task-Level Abstractions

    Describe tasks—chat, extract, classify, generate—not vendor APIs. LLM.API normalizes schemas, tools, and prompts so you can swap models without rewrites.

    Code to tasks, not vendors

  • High-Throughput Batch

    Run large-scale jobs over millions of inputs with automatic chunking, retries, rate-limit handling, and progress tracking, all via a simple, consistent batch API.

    Scale from 10 to millions

Decision guide

When to Use — When NOT to Use

Use it if...

  • You need a fast, low-cost model for bulk text generation and summarization.
  • You need quick turnaround for prototyping chatbots or assistants with moderate reasoning needs.
  • Your use case involves high-volume classification, tagging, or routing of short user messages.
  • Your use case involves lightweight data extraction from semi-structured documents at large scale.
  • You need a preview-stage model to experiment with Sourceful’s Riverflow V2 capabilities.
  • Your use case involves rapid A/B testing across multiple fast preview models and configurations.

Avoid if...

  • You need state-of-the-art reasoning quality comparable to the strongest frontier GPT-class models.
  • Your workload requires strict production SLAs where preview-model instability is unacceptable.
  • You need best-in-class performance on complex coding, debugging, and multi-file refactoring tasks.
  • Your workload requires reliably handling very long contexts with minimal loss of detail.
  • You need thoroughly security-hardened, fully audited models for highly regulated production environments.
  • Your workload requires finely tuned domain specialization rather than a general-purpose preview model.

FAQ

Frequently Asked Questions

  • What is Riverflow V2 Fast Preview?

    Riverflow V2 Fast Preview is a Sourceful language model accessible via LLM.API, optimized for fast, low-latency text generation in development and prototyping scenarios.

  • What is Riverflow V2 Fast Preview best suited for?

    It is best for high-throughput chatbots, lightweight agents, and iterative application development where fast responses and low cost matter more than peak quality.

  • What is the context window of Riverflow V2 Fast Preview?

    Riverflow V2 Fast Preview supports a context window of up to 8,000 tokens per request via LLM.API.

  • How fast is Riverflow V2 Fast Preview in terms of latency and throughput?

    The model is tuned for low first-token latency and high tokens-per-second throughput, making it suitable for interactive applications and streaming responses.

  • Which modalities does Riverflow V2 Fast Preview support?

    Riverflow V2 Fast Preview supports text-in, text-out generation only, without native image, audio, or tool-calling modalities.

  • How is Riverflow V2 Fast Preview priced on LLM.API?

    Pricing is usage-based per 1,000 tokens, with lower rates than Sourceful’s higher-tier models to favor experimentation and high-volume workloads.

  • How do I call Riverflow V2 Fast Preview through LLM.API?

    You specify the model name "sourceful/riverflow-v2-fast-preview" in your LLM.API request, using the standard chat or completion endpoint.

  • How does Riverflow V2 Fast Preview compare to larger, slower Sourceful models?

    It is generally cheaper and faster but may produce slightly lower-quality reasoning, coding, and long-form outputs than larger Sourceful models.

  • What are the main limitations of Riverflow V2 Fast Preview?

    It can struggle with very long multi-step reasoning, highly specialized domain questions, and tasks requiring strict factual accuracy without external tools.

  • Can I use streaming responses with Riverflow V2 Fast Preview on LLM.API?

    Yes, the model supports token streaming over LLM.API, allowing partial results to be sent as they are generated.

Compare

Competitive Models

Orpheus 3B

  • Text Generation

Orpheus 3B is a 3-billion-parameter English text-to-speech model from Canopy Labs, optimized for natural prosody, expressive delivery, and real-time streaming speech generation. It is notable for…

Qwen3 VL 30B A3B Thinking

  • Text Generation

Qwen3 VL 30B A3B Thinking is a large multimodal Qwen model with around 30 billion parameters, designed for vision-language reasoning with extended “thinking” capabilities. It is…

Riverflow V2 Max Preview

  • Text Generation

Riverflow V2 Max Preview is Sourceful’s most powerful Riverflow V2 preview model, a unified text-to-image and image-to-image generator. It is designed to exceed the performance of…

Start in 2 lines of code

Get My API Key