Enter the AI Universe

Access a constellation of AI models through a single, unified API at 60% of the original price. Claim your $5 in free credits and start exploring.

Galactic Features

Unified API

Navigate between models with a single line of code. No more vendor lock-in.

Cost Control

Set budgets and monitor your spending in one central dashboard.

Playground

Experiment with models and prompts before writing any code.

Analytics

Gain insights into your API usage, costs, and performance.

Explore a Universe of Models

Find the perfect model for your needs from a growing library of top providers. We charge only 40% of the original price!

gpt-4o-mini

openai

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.

Input $0.06 / 1M tokens
Output $0.24 / 1M tokens
Context 128K

gemini-2.5-flash

google

Gemini 2.5 Flash is a fast, cost-efficient AI model with a 1 million-token context window and controllable reasoning, optimized for real-time and multimodal tasks.

Input $0.12 / 1M tokens
Output $1.00 / 1M tokens
Context 1M

deepseek-chat

deepseek

DeepSeek Chat is a large language model optimized for reasoning and long-context understanding, with a 128K token input limit and strong coding performance.

Input $0.11 / 1M tokens
Output $0.44 / 1M tokens
Context 64K

gpt-4.1-nano

openai

GPT-4.1 nano is OpenAI’s fastest and most affordable model in the GPT-4.1 family, released after GPT-4o. It supports text input and output only, with a large 128k token context window, and is optimized for ultra-low latency and high efficiency—ideal for lightweight tasks at scale.

Input $0.04 / 1M tokens
Output $0.16 / 1M tokens
Context 128K

deepseek-ai/DeepSeek-V3

deepseek

DeepSeek-V3 is a powerful Mixture-of-Experts language model with a huge 128K token context window. Trained on 14.8 trillion tokens, it excels at complex reasoning, coding, and multilingual tasks, making it ideal for handling long and challenging inputs efficiently.

Input $0.11 / 1M tokens
Output $0.44 / 1M tokens
Context 128K

gemini-2.0-flash

google

Gemini 2.0 Flash is Google’s flagship multimodal model in the 2.0 series, succeeding Gemini 1.5. It supports text, image, audio, and video input, with text output only, and is built for fast, efficient AI interactions—perfect for agents and long-context applications .

Input $0.04 / 1M tokens
Output $0.16 / 1M tokens
Context 1M

deepseek-reasoner

deepseek

DeepSeek‑R1 is purpose-built for complex reasoning: it uses chain-of-thought to boost transparency, works with very large contexts, and remains significantly cheaper—especially off-peak—than alternatives like OpenAI’s o1. If you need help estimating costs or maximizing performance, just say the word!

Input $0.04 / 1M tokens
Output $0.20 / 1M tokens
Context 64K

o4-mini

openai

o4-mini is a compact multimodal model from OpenAI, released after o3-mini. It supports both text and image inputs with text outputs, offering strong reasoning capabilities at a lower cost—ideal for fast, tool-augmented tasks and long-context use.

Input $0.44 / 1M tokens
Output $1.76 / 1M tokens
Context 200K

flux.1-schnell

bfl.ai

FLUX.1 [schnell] is a 12-billion parameter rectified flow transformer model designed for ultra-fast text-to-image generation. Released in 2024 by Black Forest Labs, it leverages latent adversarial diffusion distillation to create high-quality images in just 1 to 4 inference steps, making it one of the fastest image generation models available.

Input $0.00 / 1M tokens
Output $0.00 / 1M tokens
Context 256

flux.1-dev

bfl.ai

FLUX.1 [dev] is a high-quality, open-weight text-to-image generation model developed by Black Forest Labs. It serves as a distilled version of FLUX.1 [pro], offering a balance between performance and efficiency. Designed for non-commercial applications, it is ideal for research, education, and personal projects.

Input $0.00 / 1M tokens
Output $0.01 / 1M tokens
Context 256

flux.1-pro

bfl.ai

FLUX.1 Pro is a high-performance text-to-image generation model developed by Black Forest Labs. It offers advanced capabilities for creating detailed and realistic images from textual descriptions. Designed for professional and commercial applications, FLUX.1 Pro provides enhanced image quality and faster generation speeds compared to its predecessors.

Input $0.00 / 1M tokens
Output $0.02 / 1M tokens
Context 256

flux.1.1-pro

bfl.ai

FLUX1.1 [pro] provides six times faster generation than its predecessor FLUX.1 [pro] while also improving image quality, prompt adherence, and diversity.

Input $0.00 / 1M tokens
Output $0.02 / 1M tokens
Context 256

dall-e-2

openai

DALL·E 2 is a powerful text-to-image model developed by OpenAI, released in April 2022. Based on a diffusion architecture conditioned on CLIP embeddings, DALL·E 2 can generate highly detailed, high-resolution (1024×1024) images from text prompts. It also supports advanced image editing features such as inpainting and outpainting.

Input $0.00 / 1M tokens
Output $0.01 / 1M tokens
Context 75

dall-e-3

openai

DALL·E 3 is OpenAI’s third-generation text-to-image model, released in October 2023. It builds on the architecture of DALL·E 2 with dramatic improvements in prompt fidelity, realism, and ease of use—especially when used inside ChatGPT. With tight integration into ChatGPT (Plus and Enterprise), DALL·E 3 can generate high-resolution images from simple or complex prompts, and even perform conversational image editing.

Input $0.00 / 1M tokens
Output $0.02 / 1M tokens
Context 128K

imagen-3

google

Imagen 3 is the latest text-to-image generation model from Google DeepMind, released in July 2024. It delivers photorealistic images with enhanced detail, richer lighting, and fewer artifacts than previous versions. Imagen 3 is accessible through Google's Gemini platform and Vertex AI, making it available for both consumers and developers.

Input $0.00 / 1M tokens
Output $0.01 / 1M tokens
Context 1024

imagen-4

google

Imagen 4 is Google's latest state-of-the-art text-to-image generation model, officially released in May 2025. It delivers photorealistic images with remarkable detail and clarity, supporting high-resolution outputs up to 2K. Imagen 4 is accessible via the Gemini API, Google AI Studio, and integrated into Google Workspace apps like Slides and Docs.

Input $0.00 / 1M tokens
Output $0.02 / 1M tokens
Context 4096

meta-llama/Llama-4-Scout-17B-16E-Instruct

meta

LLaMA 4 Scout is a compact, highly efficient model in Meta’s LLaMA 4 family, released in April 2025. It offers massive context length, strong multimodal capabilities, and optimized performance on low-latency hardware.

Input $0.07 / 1M tokens
Output $0.24 / 1M tokens
Context 10M

meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

meta

LLaMA 4 Maverick ist ein leistungsstarkes multimodales Modell aus Metas LLaMA 4 Familie, veröffentlicht im April 2025. Es bietet starke Text- und Bildverarbeitung, eine enorme Kontextlänge und eine hochskalierbare Mixture-of-Experts-Architektur.

Input $0.11 / 1M tokens
Output $0.34 / 1M tokens
Context 1M

veo3

google

Veo 3 is a next-generation text-to-video model developed by Google DeepMind and released in May 2025. It produces cinematic-quality 8-second video clips from text or image prompts with native audio, including dialogue, sound effects, and music.

Input $0.00 / 1M tokens
Output $2.40 / 1M tokens
Context 32K

flux.1-kontext-dev

bfl.ai

FLUX.1 Kontext [dev] is the **open-source development variant** of the FLUX.1 Kontext multimodal image editing suite from Black Forest Labs, released recently with **12 billion parameters**. It supports both **text + image input**, providing powerful, iterative, context-aware image editing entirely on local machines ([huggingface.co](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev)).

Input $0.00 / 1M tokens
Output $0.01 / 1M tokens
Context 4096

flux.1-kontext-max

bfl.ai

FLUX.1 Kontext [Max] is a 30-billion parameter advanced multimodal image editing model from Black Forest Labs, extending the FLUX.1 Kontext series with enhanced capacity and performance. This proprietary model supports complex in-context editing tasks with text and image inputs, delivering the highest fidelity and flexibility for professional and enterprise-grade workflows. It is optimized for large-scale deployment with NVIDIA RTX GPUs and TensorRT acceleration.

Input $0.00 / 1M tokens
Output $0.03 / 1M tokens
Context 4096

flux.1-kontext-pro

bfl.aim

FLUX.1 Kontext [Pro] is a proprietary, high-performance multimodal image editing model developed by Black Forest Labs. It supports in-context editing by understanding both text and image inputs, enabling precise, professional-grade image generation and modification. Designed for enterprise and production environments, FLUX.1 Kontext [Pro] delivers high-fidelity outputs with optimized performance on NVIDIA RTX GPUs via TensorRT.

Input $0.00 / 1M tokens
Output $0.02 / 1M tokens
Context 4096

ideogram

ideogram

Ideogram is a freemium text-to-image generator, widely praised for its unmatched handling of text in images.

Input $0.00 / 1M tokens
Output $0.07 / 1M tokens
Context 256

perplexity-ai/r1-1776

perplexity

R1‑1776 is a post-trained variant of the DeepSeek-R1 model, open-sourced by Perplexity on **February 18, 2025**, with the goal of providing **uncensored, high-reasoning language generation**. It removes politically sensitive filters—particularly around CCP-related topics—while retaining strong general performance.

Input $1.20 / 1M tokens
Output $2.80 / 1M tokens
Context 128K

xai/grok-4

x.ai

Grok 4 is the latest flagship model from xAI, officially released on July 9, 2025.

Input $1.20 / 1M tokens
Output $6.00 / 1M tokens
Context 256K

gemini-2.5-flash-lite

google

Gemini 2.5 Flash is a fast, cost-efficient AI model with a 1 million-token context window and controllable reasoning, optimized for real-time and multimodal tasks.

Input $0.04 / 1M tokens
Output $0.16 / 1M tokens
Context 1M

veo3_fast

google

Veo 3 is a next-generation text-to-video model developed by Google DeepMind and released in May 2025. It produces cinematic-quality 8-second video clips from text or image prompts with native audio, including dialogue, sound effects, and music.

Input $0.00 / 1M tokens
Output $1.12 / 1M tokens
Context 32K

moonshotai/Kimi-K2-Instruct

moonshot

Kimi-K2 ranks among the top open-source models, rivaling proprietary systems like GPT-4 and Claude Opus in many key benchmarks — while remaining fully accessible to the community.

Input $0.24 / 1M tokens
Output $1.00 / 1M tokens
Context 128K

qwen-vlo

qwen

Qwen VLo is Alibaba Cloud’s open-source text-to-image and image-editing model, designed for interactive visual generation with intelligent refinement.

Input $0.00 / 1M tokens
Output $0.02 / 1M tokens
Context 32K

gpt-4.1-mini

openai

GPT‑4.1 Mini launched on April 14, 2025, alongside GPT‑4.1 and GPT‑4.1 Nano. It offers a 1 million-token context window, optimized for a balance of performance, speed, and affordability.

Input $0.04 / 1M tokens
Output $0.16 / 1M tokens
Context 1M

gpt-4.1

openai

GPT‑4.1 is OpenAI’s flagship large language model, launched on April 14, 2025. It offers powerful improvements in reasoning, coding, and multimodal understanding, with a massive 1 million-token context window and full support for text + image inputs.

Input $1.20 / 1M tokens
Output $4.80 / 1M tokens
Context 1M

Don't See Your Favorite Model?

We're constantly expanding our model universe. Request a new model on our Discord!

Flexible Payment Options

PayPal

Stripe

Cryptocurrency