FLUX 2 PRO is the flagship commercial model in the FLUX 2 series, delivering state-of-the-art image generation with unprecedented quality and detail. Built for professional and enterprise applications, it offers superior prompt adherence, photorealistic outputs, and exceptional artistic capabilities. This model represents the cutting edge of AI image synthesis technology.
from openai import OpenAI
client = OpenAI(
base_url="https://api.throughputs.ai/v1",
api_key="tp_your_api_key",
)
response = client.chat.completions.create(
model="flux-2-pro",
messages=[
{"role": "user", "content": "Hello! What can you do?"}
],
)
print(response.choices[0].message.content)This model isn't available on Throughputs yet. Pricing will be announced at launch.
Coming soon
NOTIFY ME WHEN LIVE
Similar models by modality and capability
OpenAI
GPT Image 2 is openai state-of-the-art image generation model for fast, high-quality image generation and editing. It supports flexible image sizes and high-fidelity image inputs.
PRICING
Coming soon
Gemini 3.1 Flash Lite Image model is an efficiency expert in the image generation family, designed for ultra-low latency and cost-effective image generation and modification.
PRICING
Coming soon
Core Capabilities Overview: Resolution: Up to 4K (4096×4096), on par with Pro. Reference Image Consistency: Up to 14 reference images (10 objects + 4 characters), maintaining style/character consistency. Extreme Aspect Ratios: New 1:4, 4:1, 1:8, 8:1 ratios added, suitable for long images, posters, and banners. Text Rendering: Advanced text generation, suitable for infographics and marketing poster layouts. Search Enhancement: Integrated Google Search + Image Search. Grounding: Built-in thinking process; complex prompts are reasoned before generation.
PRICING
Coming soon
Flux
FLUX.2 [max] is a top-tier visual-intelligence model from Black Forest Labs (BFL) designed for production workflows: marketing, product photography, e-commerce, creative pipelines, and any application that requires consistent character/product identity, accurate text rendering, and photoreal detail at multi-megapixel resolutions. The architecture is engineered for strong prompt-following, multi-reference fusion (up to ten input images), and grounded generation (ability to incorporate up-to-date web context when producing images).
PRICING
Coming soon