v10.0.0•
Free Tier Restructuring & Horizon Beta Integration
SreeAuthor
This update introduces Horizon Beta while restructuring the free tier to ensure sustainable service for paid customers, addressing quota limitations and high demand challenges.
New Features
3
- Horizon Beta Integration: Added Horizon Beta - OpenAI's upcoming open-source model via OpenRouter, available for free to all users.
- Qwen Image SoTA: Added Qwen Image SoTA with GPT Image 1 level performance in the Free Tier.
- Free Tier Expansion: Added
Qwen3-Coder-480B-A35B-InstructandQwen-3-235B-A22B-Instruct-2507to Provider 6 Free Tier.
Free Tier Changes
4
- Premium Model Removal: Removed several premium models from free tier due to high demand affecting paid users' experience:
- Text-to-speech models
- Image editing models
- Video generation models
- Exclusive Pro Tier: Some models now exclusive to Pro tier only to ensure uninterrupted service for paid customers.
- Quota Limitations: Current quota insufficient to support free tier demand, prioritizing paid customer service quality.
- Future Restoration: Will restore free tier models once adequate quota is secured.
Provider 6 Updates
3
- New Model Additions: Added comprehensive model collection to Provider 6 Free Tier:
- Chat Completion:
Kimi-K2-Instruct,Llama-4-Maverick,Llama-4-Scout - Image Generation:
Flux.1-dev,Flux.1-pro,Flux.1.1-pro,Flux.1-kontext-dev,Flux.1-kontext-pro,Flux.1-kontext-max - Image Editing:
Flux.1-kontext-dev,Flux.1-kontext-pro,Flux.1-kontext-max - Audio Speech:
cartesia/sonic,cartesia/sonic-2
- Chat Completion:
- Limited Time Access: All new models available on free tier for limited time.
- Enhanced Capabilities: Original context preserved with maximum tokens for free users.
Bug Fixes
6
- Google-Embedding-001: Resolved issues with Google-Embedding-001 model in Provider 3.
- Image Editing: Improved functionality of image editing models across providers.
- Gemini 2.5 Pro: Fixed issues with Gemini 2.5 Pro in Provider 1.
- Sonar Models: Addressed problems with Sonar models in Provider 1.
- Token Counting: Corrected token counting issue in Provider 3 during streaming.
- Streaming Issues: Resolved streaming issue in Provider 6 for improved performance.
Platform Enhancements
3
- Vision Capabilities: Enhanced vision capabilities for select models.
- Mini Max Models: Fixed Mini Max models (40K and 80K) for improved performance.
- Opus Removal: Removed Opus and Opus Thinking features for platform optimization.