• The API is 100% functional for both free and paid users.

• Minor glitches will be fixed within the next 6 hours.

• Some parts of the documentation are AI-generated, so things might f*ck up here and there.

• Official pricing is now live — previous discounts have ended.

• a4f.co reserves the right to add or remove free models dynamically.

• Apologies for the delay — I’m the sole developer and handling this, hence took longer than expected.

• Added Claude 3.7 Sonnet to the free API (may be unstable but gets the job done)
• Added Gemini 2.5 Pro (05-06) to the free API (may be unstable but gets the job done)

• Added Imagen-3 & Imagen 3.5 to the free API (unstable)

• Updated free-tier rate limit to 300 requests per day (rpd)

• Will adjust rate limits up or down based on actual usage

• We have updated the models available in the free tier to improve performance and stability.
• The main GPT model providers have been changed – now using Provider 2 and Provider 4 as the primary sources.

• GPT-based models have been upgraded for better accuracy, response quality, and reliability.

• Most models have been stabilized to reduce downtime and ensure smoother performance.

• Imagen 3 and Imagen 3.5 from Google have been removed from the API due to instability or provider limitations.

• Two new models, Flux Dev and Flux Pro, have been added to the free tier – accessible to all users without needing a paid plan.

• These updates are intended to enhance your experience with more consistent and powerful AI models.

• All changes have been applied automatically – no action is needed from your side.

• If you face any issues with the new models, feel free to report via our support group.

· System prompt support added
· Thinking functionality enabled for thinking models
· Fully optimized for mobile screens
· Auto-scroll bug fixed
· Easier model switching
· Title, description, and icons updated
· Logo alignment for AI models and user fixed
· V1 is still under refinement and will officially replace V2 in 1–2 days
· V2 will be deprecated soon
· Both versions will be made public as part of our open-source contributions

I’ve tried my best to give you what you want, so please take a moment to support us back. 😊 Just a quick upvote or review means a lot! Share a screenshot with me after—it’ll make my day! 🚀
Thanks!

Model Additions
• Added deepseek-r1-0528
• Added Gemini 2.5 Pro 0506
• In Free and Basic tiers across Provider 2 & 4

Image Generation Models
• New image generation models in Provider 4 free tier 👇
• shuttle-3-diffusion
• shuttle-jaguar
• shuttle-3.1-aesthetic
• flux-1.1-pro-ultra
• flux-dev
• flux-schnell
• dall-e-3

System Improvements
• Enhanced platform stability

Plan Updates
• Basic plan modifications under consideration
• Existing customers will remain unaffected by any upcoming changes

We've added uptime, latency, and throughput metrics to help you choose the best performing model for each provider.
• Clear performance data
• Detailed provider comparisons
• Clutter-free interface
• Resigned Models Layout

🏆 Provider 5 continues to lead in stability.

🚀 UPDATES take place from 9 June 9:00 IST

Dear a4f.co users,

We are implementing significant improvements to enhance your experience. Please be aware that the platform may experience temporary downtime during this update process.

PROVIDER OPTIMIZATION 👇

- Reduced from 5 to 4 providers for improved stability
- Removed provider 3 due to unstable function calling capabilities
- Former provider 4 is now provider 3
- Former provider 5 is now provider 4
- All remaining providers offer enhanced reliability

NEW MODEL ADDITIONS 👇

Chat Completion Models:
- Gemini 2.5 Pro 0605
- Claude 4 Sonnet
- Claude 4 Opus

Image Generation Models:
- Flux.1 Kontext Pro
- Flux.1 Kontext Max
- GPT Image 1
- Additional models across various categories

Model list - Here

PLATFORM ENHANCEMENTS 👇

- Comprehensive design refresh for improved user interface
- Enhanced information display with detailed metrics
- Remaining RPD and RPM limits now visible
- Model success rates with expanded accuracy
- More extensive and detailed model information
- Global schema implementation ensuring perfect compatibility with Cline & Roo Code

COMPATIBILITY NOTICE 👇

All models will operate on a unified global schema, guaranteeing seamless integration with development tools. Please note that n8n compatibility has not been tested and may require additional configuration.

We appreciate your patience during this maintenance period and look forward to providing you with an enhanced experience.

Thank you for your continued support.

• Model names have been updated in all providers.
• Refer to a4f.co/models
• More consistent and more branded from now on ✌️

Adding New Provider (5) soon in the API. Stay tuned ✌️

veo-3
imagen-4.0-ultra-generate-exp-05-20
o4-mini
o4-mini-high
o4-mini-medium
o4-mini-low
o3-high
o3-medium
o3-mini
o3-low
o3
gemini-2.5-pro-preview-06-05
gemini-2.5-pro-preview-05-06
gemini-2.5-flash-preview-05-20
gemini-2.5-flash-preview-04-17
claude-opus-4-20250514-thinking
claude-sonnet-4-20250514-thinking
claude-opus-4-20250514
claude-sonnet-4-20250514
brainrot-sonnet-4-20250514
claude-3-7-sonnet-20250219
claude-3-7-sonnet-20250219-thinking
gpt-4.5-preview
gpt-4.1
gpt-4.1-mini
gpt-4.1-nano
o3-mini-high
o3-mini-low
gemini-2.0-flash-thinking-exp-01-21
grok-3-latest
grok-3-beta
grok-3-fast-beta
grok-3-mini-fast-beta
grok-3-mini-beta
grok-2-vision-1212
grok-2-1212
grok-vision-beta
grok-beta
deepseek-v3
deepseek-r1
deepseek-v3-0324
deepseek-prover-v2-671b
o1
o1-preview
o1-mini
gpt-4o-audio-preview-2024-12-17
gpt-4o-audio-preview
chatgpt-4o-latest
gpt-4o-search-preview-2025-03-11
gpt-4o-mini-search-preview-2025-03-11
gpt-4o
gpt-4-turbo
gpt-4-32k
gpt-4-32k-0314
gpt-4-32k-0613
gpt-4-1106-preview
gpt-4o-mini-2024-07-18
gpt-4o-2024-08-06
gpt-4-1106-vision-preview
gpt-4o-2024-11-20
gpt-4-turbo-preview
gpt-4-0125-preview
gpt-4o-mini
gpt-4
gpt-3.5-turbo
text-moderation-latest
text-moderation-stable
omni-moderation-latest
mistral-large-latest
mistral-large-2411
pixtral-large-latest
pixtral-large-2411
mistral-moderation-latest
mistral-moderation-2411
ministral-3b-latest
ministral-3b-2410
ministral-8b-latest
ministral-8b-2410
open-mistral-nemo
open-mistral-nemo-2407
mistral-small-latest
mistral-small-2503
mistral-medium-2505
mistral-saba-2502
mistral-large-2407
mistral-large-2402
mistral-medium-2312
mistral-small-2501
mistral-small-2402
mistral-small-2409
open-mixtral-8x22b
open-mixtral-8x22b-2404
open-mixtral-8x7b
open-mistral-7b
mistral-tiny
mistral-tiny-2312
mistral-tiny-2407
mistral-tiny-latest
codestral-2501
codestral-2405
codestral-latest
codestral-mamba-2407
open-codestral-mamba
pixtral-12b-2409
pixtral-12b
imagen-3.0-generate-002
imagen-3.0-generate-001
imagen-3.0-fast-generate-001
gpt-image-1
dall-e-3
dall-e-2
claude-3-5-haiku-20241022
claude-3-5-sonnet-20241022
claude-3-5-sonnet-20240620
claude-3-opus-20240229
claude-3-sonnet-20240229
claude-3-haiku-20240307
claude-2
whisper-1
tts-1
tts-1-hd
gpt-4o-transcribe
gpt-4o-mini-transcribe
gpt-4o-mini-tts
gemini-2.0-flash
gemini-2.0-flash-lite-preview-02-05
gemini-2.0-pro-exp-02-05
learnlm-2.0-flash-experimental
gemini-2.5-flash-exp-native-audio-thinking-dialog
gemini-2.5-flash-preview-native-audio-dialog
learnlm-1.5-pro-experimental
gemini-exp-1206
sonar
sonar-pro
sonar-reasoning
sonar-deep-research
gemini-1.5-pro
gemini-1.5-pro-latest
gemini-1.5-flash
gemini-1.5-flash-latest
gemini-1.5-flash-8b
gemini-1.5-flash-8b-latest
gemini-2.0-flash-exp
FLUX.1 [dev]
FLUX.1 [schnell]
FLUX.1 [pro]
FLUX 1.1 [pro] ultra raw
stable-diffusion-3
elevenlabs
gemini-2.5-flash-preview-tts
gemini-2.5-pro-preview-tts
llama-3.3-70b
command-a-03-2025
llama-4-scout-17b-16e-instruct
llama-4-maverick
llama-3.1-8b
Qwen/Qwen3-235B-A22B
Qwen/QwQ-32B
Qwen/Qwen2.5-VL-72B-Instruct
Qwen/Qwen3-30B-A3B
text-embedding-3-large
text-embedding-3-small
text-embedding-ada-002

🌐 a4f.co
🎉 EXCITING UPDATES & CHANGES

• Provider 5 Added - Generous free tier with initial testing complete

• GPT Image 1 (Stable) - Now available for everyone (limited time)

• Claude 3.5 Haiku - claude-3-5-haiku-20241022 now available for all users

• All Image Generation Models - Free access for everyone (limited time)

• Enhanced Context Limits
- Claude 4 Sonnet (Provider 5): 150k context
- Gemini 2.5 Pro (all versions): 1M context for Pro users

• Provider 4 Termination - Will be terminated/rate-limited from June 12, 00:00 GMT for Pro users

• Free Tier Changes - SOTA Text Generation models removed to ensure stable experience for paid users

• Basic Plan Rate Limits - 500 RPD limit starting June 18, 2025
- Existing basic plan customers: No changes
- Pro users: Unlimited access continues (no changes to Pro plan)

• Veo 3 Access - Currently extremely unstable (12/100 requests successful)
- Will be added to Pro Plan once 50%+ stability achieved

• Adding o3 Pro to Free Users (since OpenAI reduced the pricing by 80%

• OpenAI Audio Models - Coming soon with 90%+ uptime:
- TTS-1-HD & TTS-1
- GPT-4o-audio-preview (all versions)
- OpenAI Whisper models
- Text-moderation models (OpenAI & Mistral)
- GPT-4o-transcribe
- ElevenLabs (experimental)

• Provider 6 - Planned for June 2025
- SOTA Models: Gemini 2.5 Pro & Claude 3.5, 3.7, 4 Sonnet

• Improved Stability - Continuous model stability improvements and additional providers

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)