Changelog

Added support for Google's Gemini Pro model, expanding our AI capabilities with this advanced multimodal model. Users can now leverage Gemini Pro for tasks involving text, images, and other data types.

The FLUX series — FLUX.1 [pro], FLUX.1 [schnell], Realism LoRA, and [dev] offers top-tier image generation for professional use, ideal for designers and creatives.

Incorporated Luma AI's video generation capabilities, allowing users to create video from text and image directly within our API.

Introduced support for the GPT-4o-mini model, offering a more lightweight and cost-effective option for certain AI tasks.

Fixed an issue where invalid inputs to the image prompt endpoint were causing 500 errors.

One of the top open-source models like Llama 3.1 (405B), Llama 3.1 (70B), and Code LlaMa are ready to boost your natural language tasks.

Resolved an issue where requests for custom subscription plans were incorrectly returning a 404 error instead of the expected response.

Integrated Optical Character Recognition (OCR) and Computer Vision (CV) models, enabling advanced image processing and text extraction capabilities. This addition allows users to analyze images and convert visual information into machine-readable text.

Added support for OpenAI's DALL-E 3, providing users with state-of-the-art image generation capabilities directly within our platform.

Integrated open-source and Anthropic models with JSON mode support, enabling structured data output and improved parsing capabilities for developers working with these AI models.

Implemented a dedicated endpoint for language completion tasks, optimizing performance and providing a streamlined API for text generation and auto-completion features.

Implemented cryptocurrency payment options, allowing users to pay for services using various digital currencies, enhancing payment flexibility and global accessibility.

Added support for function calling with OpenAI and open-source models, enabling more complex and structured interactions between applications and AI models.

Enhanced the AI Playground interface with improved usability, a feature to save and recall previous prompts, adjustable parameters for image generation tasks.

Integrated Stripe payment processing natively into our platform, offering a seamless and secure payment experience for users with support for various payment methods and currencies.

Added support for OpenAI's GPT-4-turbo and Vision models, expanding text and image processing capabilities with these cutting-edge AI models. https://aimlapi.com/models/chat-gpt-4-turbo

Integrated the full suite of Anthropic's Claude 3 models (Haiku, 3.5 Sonnet, and Opus), providing users with a range of AI capabilities suited for different tasks and performance requirements.

Integrated Whisper, Aura and Nova 2 Text-to-Speech (TTS) and Automatic Speech Recognition (ASR) models, enabling advanced audio processing and generation features within our platform.

Our API References just got a major upgrade!

Expect a detailed guide to AI models and API usage, covering setup, supported SDKs, text, image, audio, video models, and a comprehensive FAQ section.

Implemented an automated backup system to ensure data safety and recovery options. This feature allows for scheduled backups of critical system data, providing enhanced reliability and disaster recovery capabilities.

We’re pumped to announce that our app is live!

After months of hard work, it’s live and ready for you. This is just the beginning of a journey where we aim to give you the best AI/ML services around.