Get My API Key
Get My API Key

Powered by Sourceful

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 the earlier Riverflow 1 family while supporting rich, high-context visual generation workflows.

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 Max Preview?

Riverflow V2 Max Preview is a high-performance image generation model from Sourceful that unifies text-to-image and image-to-image capabilities. It is mainly used for creating high-quality images from text prompts and for transforming or editing images with additional textual guidance. It also targets professional creative workflows such as brand asset production and other controlled visual design tasks. Riverflow V2 Max Preview belongs to the Riverflow V2 family and is positioned as the flagship successor to the Riverflow 1 model family.

Model capabilities

5 Core Capabilities

  • Text-to-image generation

    Generates high-quality images from detailed natural language prompts using Sourceful’s unified Riverflow V2 Max Preview image model.

  • Image-to-image transformation

    Transforms or enhances existing input images based on guidance prompts, leveraging Riverflow V2’s unified image-to-image capabilities.

  • Conversational prompting

    Supports chat-style prompting via OpenRouter’s chat completions API for iterative refinement of image generation instructions.

  • Request content handling

    Handles image requests up to Sourceful’s 4.5MB limit, with best practices recommending image URLs instead of Base64 payloads.

  • Multilingual prompt support

    Accepts prompts in multiple languages through OpenRouter, enabling image generation workflows for international users and content.

Use cases

6 Most Valuable Use Cases

  • Marketing Image Generation
  • Billboard Ad Design
  • Product Photography Mockups
  • Image-to-Image Editing
  • Brand Visual Prototyping
  • Multimodal Workflow Testing

Transparent pricing

Cost Comparison

Save up to ~70% vs other Riverflow V2 Max-compatible APIs

Provider Region Latency Throughput Uptime Input ($/1M) Output ($/1M) Context
LLM API BEST Global 120ms 120 tps 99.99% $0.20 $0.40 256K
Sourceful Global ~260ms ~40 tps ~99.9% ~$0.60 ~$1.20 ~128K
OpenRouter Global ~280ms ~35 tps ~99.8% ~$0.70 ~$1.40 ~128K
Together AI US East ~240ms ~50 tps ~99.9% ~$0.55 ~$1.10 ~128K

Performance benchmarks

Technical Specifications

Metric Riverflow V2 Max Preview OpenAI GPT-4.1 Mini Anthropic Claude 3.5 Haiku
Avg Latency ~180ms ~220ms ~250ms
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

3.8B
Prompt tokens processed (last 30 days)
720M
Completion tokens generated (last 30 days)
9.5M
API requests served (last 30 days)
99.8%
Avg 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

    Automatically route each request to the best-fit model across providers using rules, metadata, and performance signals — no client changes, just smarter traffic.

    One endpoint, any model

  • Cost-Aware Orchestration

    Control spend with per-route pricing rules, hard caps, and automated downshifts to cheaper models while keeping SLA and quality constraints intact.

    Predictable, tunable spend

  • Resilient Fallback Flows

    Design multi-step failover chains across providers with timeouts and retries so user-facing features stay online even when a model or region fails.

    Never ship single points of failure

  • End-to-End Observability

    Trace every request across providers with logs, metrics, and structured events to debug latency spikes, errors, and quality regressions in one place.

    One pane for every call

  • Task-Level Orchestration

    Define high-level tasks—chat, extract, classify, generate—and let LLM.API pick tools, models, and prompts so you ship features, not glue code.

    Describe tasks, not wiring

  • High-Throughput Batch Runs

    Run millions of inferences in parallel with automatic chunking, retries, and cost tracking—no custom workers, no rate-limit headaches.

    Batch at platform scale

Decision guide

When to Use — When NOT to Use

Use it if...

  • You need a capable general-purpose LLM from Sourceful for prototypes or internal tools.
  • You need to integrate with Sourceful’s ecosystem and leverage Riverflow V2 Max–specific tooling.
  • Your use case involves drafting or refining business documents, emails, and structured reports reliably.
  • Your use case involves building chat-style assistants that handle multi-turn conversations with users.
  • You need an English-first model for summarization, rewriting, and light analytical reasoning tasks.
  • Your use case involves experimenting with Sourceful previews to evaluate future production model capabilities.

Avoid if...

  • You need a battle-tested, non-preview model with strong uptime and long-term stability guarantees.
  • Your workload requires state-of-the-art reasoning benchmarks comparable to top-tier frontier models today.
  • You need rigorous compliance attestations or certifications that preview models typically do not provide.
  • Your workload requires predictable performance and latency under strict production service-level agreements.
  • You need mature ecosystem support, extensive documentation, and large community examples around the model.
  • Your workload requires highly optimized cost-performance tuning data that previews rarely finalize.

FAQ

Frequently Asked Questions

  • What is Riverflow V2 Max Preview?

    Riverflow V2 Max Preview is a large language model from Sourceful focused on high-quality text generation and reasoning, accessible through the LLM.API platform.

  • What is Riverflow V2 Max Preview best suited for?

    Riverflow V2 Max Preview is best for building chatbots, agents, data analysis assistants, and complex reasoning workflows where accuracy and controllability matter.

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

    Riverflow V2 Max Preview supports a large-context window suitable for multi-turn conversations and long documents, but exact token limits depend on the LLM.API configuration.

  • Which modalities does Riverflow V2 Max Preview support?

    Riverflow V2 Max Preview currently supports text input and text output; image, audio, and video inputs are not available via LLM.API for this model.

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

    Typical responses arrive within a few seconds, with latency varying based on prompt size, output length, and current LLM.API load.

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

    Pricing for Riverflow V2 Max Preview is usage-based per input and output token, with exact rates shown in the LLM.API pricing dashboard.

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

    Select the Sourceful provider and the Riverflow V2 Max Preview model name in your LLM.API request, then send standard chat or completion-style payloads.

  • How does Riverflow V2 Max Preview compare to similar large models?

    Riverflow V2 Max Preview targets a balance of quality, cost, and speed, often suited as a mid-to-high tier alternative to flagship frontier models.

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

    Riverflow V2 Max Preview can produce hallucinations, lacks real-time knowledge, and should not be relied on for critical decisions without external verification.

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

    Riverflow V2 Max Preview can hallucinate facts, lacks real-time internet access, and may struggle with highly specialized domain knowledge without grounding tools.

Compare

Competitive Models

MiniMax M2.1

  • Text Generation

MiniMax M2.1 is a second-generation, open-weight Mixture-of-Experts large language model from MiniMax, optimized for real-world coding, tool use, and long-horizon agentic workflows. It is notable for…

Qwen3.5-9B

  • Text Generation

Qwen3.5-9B is a 9‑billion‑parameter multimodal language model from Qwen that supports long-context reasoning over text and images. It is designed to offer strong reasoning, coding, and…

Cogito v2.1 671B

  • Text Generation

Cogito v2.1 671B is Deep Cogito’s flagship 671B-parameter open-weight Mixture-of-Experts language model optimized for efficient hybrid reasoning. It delivers frontier-level performance while using significantly shorter reasoning…

Start in 2 lines of code

Get My API Key