Free Plan Updates

• New Models Added
- Gemini 2.5 Pro 06-05
- Gemini 2.5 Pro 05-06

• Availability & Performance
- 7-day experimental period
- 95% uptime approximation
- Vision support included
- 256k context window
- 64k maximum tokens

• Provider 6 Integration
- Available across all plans including Free
- RPM remains at 5 for free users
- RPD increased to 300-400

• Bug Fix Status
- RPD update to 300 from 100
- Changes reflected at a4f.co/dashboard
• Upcoming Features
- Sonar DeepResearch support
- Sana 6B model integration

Claude models are stable in Provider 4 (80k context), I will adding new providers for claude soon.
Btw, I will be completely inactive today due to my exams. I will be back at 9:00 PM IST

API Update - New Models Added

• New Models Available:
- Claude 4 Opus thinking
- Claude 4 Sonnet thinking
- Claude 3.7 Sonnet thinking

• Provider Details:
- Added to Provider 6 of our API
- All models fully integrated and ready for use

• Pricing Information:
- Free access for all users until June 21st, 3:00 PM IST
- This includes free tier users
- No charges during this promotional period

• System Stability:
- Extensively tested for high load capacity
- Optimized to handle expected user traffic
- Stable performance expected across all models

• Support:
- Report any issues via Telegram (reply to this post)
- Our team will address problems promptly
- Feedback helps us improve service quality

• Important Reminder:
- Free access ends on June 21st at 3:00 PM IST
- Make sure to test the new models before the deadline

Thank you for your continued support. We're committed to providing reliable AI services to our community.

Important Notice - Claude Models Temporary Removal

• Key Changes Effective June 27th, 00:00 IST:
- Claude 4 Opus and Claude 4 Sonnet removed from Provider 6
- Removal applies to free and basic tier users only
- Pro users unaffected

• Reason for Changes:
- Severe API abuse over the past 5 days
- Excessive usage causing system instability
- Unsustainable costs: $4,000+ in just 10 hours

• Usage Statistics:
- Last 10 hours showed extreme spike in usage
- Pattern indicates significant abuse of free access
- System performance heavily impacted

• Future Availability:
- Collaboration with Provider 6 planned
- Claude 4 Opus and Sonnet will return
- Limited 3-day promotional period in coming weeks
- Dates to be announced soon

• What This Means:
- Free and basic users: No Claude 4 access from June 27th
- Premium users: Continued access maintained
- Other models in Provider 6 remain available

• Our Commitment:
- Working to restore stable service
- Implementing better abuse prevention measures
- Ensuring fair access for all legitimate users

We appreciate your understanding as we work to maintain service quality and sustainability.

🎬 Exciting Update: New Video Generation Models Coming Soon in A4F.co

• Wan 2.1 from Alibaba - Our newest video generation model will be rolling out to the API in the next 1-2 days
  - Free access for everyone for the first 2-3 days
  - After that, it'll be exclusive to Pro plan users
  - Features advanced text-to-video capabilities with support for both Chinese and English text generation
  - Runs efficiently on consumer-grade GPUs, making it highly accessible

• Veo 3 from Google - We've secured access through Replicate, but quota limitations are holding us back
  - Capable of producing 4K videos with synchronized audio
  - Features native audio generation including sound effects and dialogue
  - Until we get enough quota, Wan 2.1 will be our default model

Here's where you come in: If this post gets enough thumbs-up (👍) reactions, we'll prioritize getting more Veo 3 quota to make it available faster!

Update on Recent Inactivity & Upcoming API Features

Recent Absence:
I was helping with a hospitalized relative over the past few days, which limited my activity during this period. Thankfully, everything remained stable in my absence.

Delayed API Updates - Compensation Timeline:
Previous promised updates were delayed. All updates will be added today or by tomorrow as compensation.

Upcoming API Features:

Text-to-Speech Models
- TTS 1 HD
- GPT-4o Mini TTS
- Additional TTS variants

GPT-4o Audio Preview
- All available versions included

Online Web Search Integration
- GPT-4o with web search
- GPT-4o Mini with web search

Transcription Models
- GPT-4o Transcribe
- GPT-4o Mini Transcribe
- Whisper integration

Embedding Models
- Text Embedding 3
- Text Embedding 3 Large
- Ada 002

Content Moderation
- Omni Moderation
- Text Moderation models

Video Generation
- Alibaba Wan 2.1

Enhanced Functionality
- Function calling (Provider 3)

Important Notes:
• All new models will be available completely free as compensation for 1-3 days (depending on usage)
• Website will be updated one day after the new models are released
• Timeline: All features rolling out within 24-48 hours

All models will be stable with (95%+ uptime)

🔄 API & Model Updates - Important Changes

What's New:
• Provider 4 API has been updated with enhanced stability
• Model availability has been restructured across all providers

📋 Updated Plan Features:

• Pro Plan - Full access to all available models
• Basic Plan - Reduced model selection (streamlined offerings)
• Free Plan - Limited model access

🔍 Check Available Models:

• Free Plan: api.a4f.co/v1/models?plan=free
• Basic Plan: api.a4f.co/v1/models?plan=basic
• Pro Plan: api.a4f.co/v1/models?plan=pro

📝 Why These Changes?

• Recent operational costs have significantly impacted our sustainability

• API stability improvements required infrastructure adjustments

• These modifications ensure continued reliable service for all users

I will provide the detailed description of models URL soon. This message will be edited and updated.

🚨 Provider Updates & Service Changes

Provider 3 Status Alert:
Following Provider 5's recent issues, Provider 3 is now facing financial instability. Anthropic models on Provider 3 are experiencing significant instability due to these challenges. We will be migrating to Provider 6, which will feature new Claude models (non-thinking versions).

Current Service Status:
Provider 6 is operating with excellent stability across all models, including Sonnet and Opus thinking variants. We sincerely apologize for the ongoing disruptions, but the unprecedented load on our Anthropic models has created these challenges. Recent usage has reached extremely high levels, putting strain on our Anthropic quota.

Load Distribution Strategy:
We anticipate that the upcoming launch of XAI Grok 4 will help distribute the current load more effectively. Provider 6 has demonstrated strong capacity to handle current demand, and we're working to have the migration completed by 6:00 PM IST today.

Provider Recommendations:

Provider 5 - Dumb/Unstable for most of the models
Provider 6 - Generally stable across all AI companies
Provider 2 - Stable for open source models (available for free users)
Provider 4 - Stable for image generation models (Google and OpenAI)

We appreciate your patience as we work to maintain service quality during these transitions.

New Non-Thinking Claude Models Added to Provider 6! 🚀
Due to overwhelming demand from our community, we're excited to announce that we've added the highly requested non-thinking versions of Anthropic's latest models to our API!

Newly Available Models:
• gemini-2.5-flash
• gemini-2.5-flash-thinking
• claude-3-7-sonnet-20250219
• claude-sonnet-4-20250514
• claude-opus-4-20250514

Check Your Plan Access:
• Free Plan: api.a4f.co/v1/models?plan=free
• Basic Plan: api.a4f.co/v1/models?plan=basic
• Pro Plan: api.a4f.co/v1/models?plan=pro

Important Notes:
• All models are stable and ready for use
• Claude Opus 4 (non-thinking) is currently in experimental stage
• Opus 4 will become fully stable within 1-2 hours

🤖 New AI Models - Provider 6 (Free tier):
• OpenAI GPT-4.1
• O3-medium - With vision capabilities
• O4-mini-medium - Vision supported

✨ Key Features:
• All new models available to free users
• Original context and max tokens as per official API
• 1 Million Context for GPT-4.1
• Available to free plan users

👁️ Vision Support Enhancements:
• Gemini 2.5 Pro & Flash - Vision now enabled
• All Claude Models - Vision added to both thinking and non-thinking variants (Sonnet & Opus)

🎯 Coming Today by 9 PM IST:
• Speech Models integration
• Image Generation Models addition

All updates are live in Provider 6 and ready for use! 🎉

Hey everyone!
Our logo and motto has always been about providing access to as many AI models as possible to as many users as possible - that's what A4F (AI for Free and for Everyone) truly represents.

But here's the honest truth: we've been noticing that our free plan users aren't getting enough value. Right now, we're somewhat similar to OpenRouter for free users, and that's NOT what A4F stands for. We refuse to be called just another OpenRouter alternative!

While our paid consumers already enjoy unmatched cost-to-value ratios that no competitor can touch, our free users deserve the A4F experience too.

Here's what's changing:
• Free plan RPD jumping to 500 (that's 5x more generous!)
• Special rate limits for SOTA models included
• Basic plan restructuring coming
• Pro plan stays exactly the same

We need YOUR support to make this happen!

If you believe in the A4F vision and want to see us become truly different from OpenRouter:

👍 React with thumbs up on this post to show your support for this decision

🔥 URGENT: Help us reach 100 ProductHunt reviews!
We're craving genuine reviews on ProductHunt. Please upvote, follow, and leave an honest review about your real experience with our platform.

The deal: Once we hit 100 reviews, we'll immediately implement these generous free plan changes and prove that A4F isn't just another OpenRouter competitor!

This isn't about fake reviews - we want authentic feedback that shows the world what A4F really represents.

Ready to help us become the most generous AI platform that truly lives up to our motto? Let's make this happen together! 🎯

🆕 NEW MODELS ADDED TO PROVIDER 6
Available Models:
• o3-pro
• o3 high
• o4 mini high
• o3 low
• sana 1.5
• sana 1.5 flash

Features:
• Original context preserved
• Maximum tokens for free users
• Full free tier access

Important Notes:
• Limited time availability
• o3-pro may be downgraded to o4 mini high
• All other models are stable

o3-Pro offically doesn't support streaming from OpenAI. So our API will also not support it

Added Function Calling in Provider 6
Models Supporting 👇
• claude-3-7-sonnet-20250219
• claude-sonnet-4-20250514
• claude-opus-4-20250514
• claude-sonnet-4-20250514-thinking
• claude-3-7-sonnet-20250219-thinking
• claude-opus-4-20250514-thinking
• gemini-2.5-flash
• gemini-2.5-flash-thinking
• gemini-2.5-pro-preview-06-05
• gemini-2.5-pro-preview-05-06
• o3-medium
• o4-mini-medium
• o3-pro
• o3-high
• o3-low
• o4-mini-high
• o4-mini-low

🚀 Grok-4-0709 Now Available on Provider 3 API

We're excited to announce the addition of Grok-4-0709 to our platform with full function calling support.
Context Limits by Plan:
• Free Users: 128k context
• Basic Plan: 200k context
• Pro Plan: 256k context

Expansion Plans:
• Currently exclusive to Provider 3
• Providers 1 and 6 integration confirmed and coming soon
• We're working closely with all providers to ensure seamless deployment

Important Note:
This is our initial launch phase. We appreciate your patience as we monitor stability and performance.

🚀 MAJOR FREE TIER UPDATE - Limited Time
We've significantly expanded our free tier offerings with premium models and new capabilities:

🆕 NEWLY ADDED MODELS:
• gemini-2.5-pro
• text-embedding-004
• codestral-22b
• whisper-1
• distil-whisper-large-v3-en
• gpt-4o
• gpt-4o-mini-search-preview
• deepseek-r1-uncensored
• r1-1776
• minimax-m1-40k
• kimi-k2
• imagen-3.0-generate-002
• imagen-4.0-generate-preview-06-06
• flux-kontext-dev
• gpt-4o-mini-transcribe
• magistral-medium-latest
• mistral-small-latest
• sonar
• sonar-deep-research
• sonar-pro
• sonar-reasoning
• sonar-reasoning-pro
• tts-1
• gemini-embedding-001
• claude-3.5-haiku
• claude-3.5-haiku-20241022

All models now accessible in FREE TIER - no premium subscription required.🔥

🌐 WEBSITE UPDATE - Enhanced Features & Documentation
📊 Models Page
• Added support for all new models
💰 Pricing Updates
• Yearly subscriptions now available with up to 30% discount
ℹ️ Information & FAQ
• Updated details for different plans
📚 Documentation Updates
• Chat completion models
• Image generation models
• Image editing models
• Embedding models
• Video generation models
• Audio speech models
• Audio transcription models

More website updates coming soon! 🚀

API Update Announcement

We are pleased to share the latest updates to our API, designed to enhance performance and reliability. Below is a summary of the changes:

• Resolved issue with Google-Embedding-001 model in Provider 3
• Improved functionality of image editing models
• Removed Opus and Opus Thinking features
• Fixed issues with Gemini 2.5 Pro in Provider 1
• Addressed problems with Sonar models in Provider 1
• Corrected token counting issue in Provider 3 during streaming
• Enhanced vision capabilities for select models
• Fixed Mini Max models (40K and 80K)
• Resolved streaming issue in Provider 6

Exciting Provider 6 API Update
We’re thrilled to announce the addition of new models to Provider 6, now available on the free tier for a limited time 👇

• 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