Changelog - AI Content Labs

Stay up to date with all the latest additions and improvements we’ve made to AI Content Labs.

September 2025

09/01/2025: Integration of new AI models:
- OpenAI models:
  - ‘gpt-5’
  - ‘gpt-5-mini’
  - ‘gpt-5-nano’
  - ‘gpt-5-chat’
- Azure models:
  - ‘gpt-5’
  - ‘gpt-5-mini’
  - ‘gpt-5-nano’
  - ‘gpt-5-chat’
- AI Content Labs models:
  - ‘gpt-5’
  - ‘gpt-5-mini’
  - ‘gpt-5-nano’
  - ‘gpt-5-chat’
  - ‘gemini-2.5-flash-image-preview’
- Vertex AI models:
  - ‘gemini-2.5-flash-image-preview’
- Google models:
  - ‘gemini-2.5-flash-image-preview’

August 2025

08/01/2025: Model updates and changes:
- Vertex AI models added for text/image to video:
  - ‘veo-3.0-generate-preview’
  - ‘veo-3.0-fast-generate-preview’
  - ‘veo-3.0-generate-001’
  - ‘veo-3.0-fast-generate-001’
- New model ‘gpt-image-1’ from Azure is now available.
- Added ‘imagen-4.0-fast-generate-preview-06-06’ from Vertex AI.
- Added ‘o3’ and ‘o3-pro’ from Azure.
- Deprecated models removed, including ‘gemini-2.5-pro-preview’, ‘r1-1776’, ‘claude-3-sonnet’, among others.

June 2025

06/05/2025: New AI model additions and updates:
- Openrouter:
  - ‘deepseek/deepseek-r1-0528’
  - ‘google/gemini-2.5-pro-preview’
  - ‘google/gemini-2.5-flash-preview-05-20:thinking’
  - ‘google/gemini-2.5-flash-preview-05-20’
  - ‘google/gemini-2.5-flash-preview’
  - ‘google/gemini-2.5-flash-preview:thinking’
  - ‘google/gemini-2.5-pro-preview-03-25’
  - ‘anthropic/claude-opus-4’
  - ‘anthropic/claude-sonnet-4’
- Anthropic:
  - ‘claude-opus-4-0’
  - ‘claude-sonnet-4-0’
- Fal.ai:
  - ‘fal-ai/flux-pro/kontext/max/text-to-image’
  - ‘fal-ai/flux-pro/kontext/text-to-image’
  - ‘fal-ai/imagen4/preview’
  - ‘fal-ai/flux-pro/kontext’
  - ‘fal-ai/flux-pro/kontext/max’
  - ‘fal-ai/flux-pro/kontext/max/multi’
  - ‘fal-ai/kling-video/v2.1/master/image-to-video’
  - ‘fal-ai/kling-video/v2.1/master/text-to-video’
  - ‘fal-ai/kling-video/v2.1/pro/image-to-video’
  - ‘fal-ai/kling-video/v2.1/standard/image-to-video’
  - ‘fal-ai/pixverse/v4.5/image-to-video’
  - ‘fal-ai/pixverse/v4.5/image-to-video/fast’
  - ‘fal-ai/pixverse/v4.5/text-to-video’
  - ‘fal-ai/pixverse/v4.5/text-to-video/fast’
  - ‘fal-ai/pixverse/v4.5/effects’
  - ‘fal-ai/pixverse/v4.5/transition’
- Vertex AI:
  - ‘gemini-2.5-flash-preview-05-20’
  - ‘gemini-2.5-pro-preview-05-06’
  - ‘imagen-4.0-generate-preview-05-20’
  - ‘imagen-4.0-ultra-generate-exp-05-20’
- AI Content Labs:
  - ‘gemini-2.5-flash-preview-05-20’
  - ‘gemini-2.5-pro-preview-05-06’

May 2025

02/05/2025: New AI models added:
- OpenAI:
  - ‘gpt-image-1’ (text to image and image to image)
- Vertex AI:
  - ‘imagen-3.0-capability-001|Default’
  - ‘imagen-3.0-capability-001|Controlled customization’
  - ‘imagen-3.0-capability-001|Inpaint Insertion’
  - ‘imagen-3.0-capability-001|Inpaint Removal’
  - ‘imagen-3.0-capability-001|Background Swap’
- Azure:
  - Model ‘dall-e-2’ removed, no longer available.
02/05/2025: New tools available in the ‘Multimedia Tools’ node:
- Get Audio Metadata
- Get Video Metadata
- Merge Videos
- Add Subtitles to Video
- Add Watermark to Video
- Audio Speed Adjustment
- Video Speed Adjustment
- Audio Trimming
- Video Trimming
- Extract Audio from Video
- Merge Audio Files
- Add Audio to Video
- Extract paragraph duration from SRT file
These tools use a credit system. For now, credit consumption values are in testing and final values will be defined later.

April 2025

04/17/2025: Fixes and new AI models:
- Fixed an issue where, in some cases, AI-generated results were not displayed in the flow editor view.
04/17/2025: Addition of new artificial intelligence models:
- Fal.ai models:
  - ‘cassetteai/music-generator’
  - ‘fal-ai/kling-video/v2/master/image-to-video’
  - ‘fal-ai/kling-video/v2/master/text-to-video’
  - ‘fal-ai/vidu/image-to-video’
  - ‘fal-ai/vidu/reference-to-video’
  - ‘fal-ai/vidu/start-end-to-video’
  - ‘fal-ai/vidu/template-to-video’
  - ‘fal-ai/pika/v2/turbo/text-to-video’
  - ‘fal-ai/pika/v2/turbo/image-to-video’
  - ‘fal-ai/pika/v2.2/text-to-video’
  - ‘fal-ai/pika/v2.2/image-to-video’
  - ‘fal-ai/pika/v2.1/text-to-video’
  - ‘fal-ai/pika/v2.1/image-to-video’
  - ‘fal-ai/pika/v1.5/pikaffects’
  - ‘fal-ai/ltx-video-v095/image-to-video’
  - ‘fal-ai/ltx-video-v095’
- OpenRouter models:
  - ‘openai/o4-mini’
  - ‘openai/o4-mini-high’
  - ‘openai/o3’
- OpenAI models:
  - ‘o4-mini’
  - ‘o3’
- Azure models:
  - ‘o4-mini’
  - ‘gpt-4.1-nano’
  - ‘gpt-4.1-mini’
- Models in AI Content Labs (credit-based use):
  - ‘o4-mini’
  - ‘gpt-4.1-nano’
  - ‘gpt-4.1-mini’

04/15/2025: Improvements to execution functionalities and infrastructure:
- Streaming-based AI execution is now enabled in templates (for supported models).
- Improved error message when an image is not valid in the ‘gemini-2.0-flash-exp’ model.
- Block execution credits are now simply called credits. These can now be used not only for bulk executions, but also for some AI models (no API key required), as well as tools we run on our servers like image or PDF processing. These credits do not affect usage of your own API keys.
- Each bulk execution of a flow now consumes only 1 credit, instead of the previous 10.
04/15/2025: Addition of new artificial intelligence models:
- OpenRouter models:
  - ‘deepseek/deepseek-v3-base:free’
  - ‘deepseek/deepseek-chat-v3-0324:free’
  - ‘deepseek/deepseek-chat-v3-0324’
  - ‘x-ai/grok-3-beta’
  - ‘x-ai/grok-3-mini-beta’
  - ‘google/gemini-2.5-pro-preview-03-25’
  - ‘google/gemini-2.5-pro-exp-03-25:free’
  - ‘mistralai/mistral-small-3.1-24b-instruct:free’
  - ‘mistralai/mistral-small-3.1-24b-instruct’
  - ‘meta-llama/llama-4-scout’
  - ‘meta-llama/llama-4-scout:free’
  - ‘meta-llama/llama-4-maverick:free’
  - ‘meta-llama/llama-4-maverick’
  - ‘openai/gpt-4.1-nano’
  - ‘openai/gpt-4.1-mini’
  - ‘openai/gpt-4.1’
- OpenAI models:
  - ‘gpt-4.1-nano’
  - ‘gpt-4.1-mini’
  - ‘gpt-4.1’
  - ‘gpt-4o-mini-tts’
  - ‘gpt-4o-mini-transcribe’
  - ‘gpt-4o-transcribe’
- Vertex AI models:
  - ‘gemini-2.5-pro-preview-03-25’
  - ‘gemini-2.5-pro-exp-03-25’
  - ‘veo-2.0-generate-001|text-to-video’
  - ‘veo-2.0-generate-001|image-to-video’
- Google models:
  - ‘gemini-2.5-pro-preview-03-25’
  - ‘gemini-2.5-pro-exp-03-25’
  - ‘imagen-3.0-generate-002’
  - ‘veo-2.0-generate-001|text-to-video’
  - ‘veo-2.0-generate-001|image-to-video’
- xAI models:
  - ‘grok-3-mini-fast-latest’
  - ‘grok-3-mini-latest’
  - ‘grok-3-fast-latest’
  - ‘grok-3-latest’
- Fal.ai models:
  - Audio: ‘fal-ai/minimax-tts/text-to-speech’, ‘fal-ai/minimax-tts/text-to-speech/turbo’, ‘cassetteai/sound-effects-generator’, ‘fal-ai/mmaudio-v2/text-to-audio’
  - Text to image: ‘fal-ai/hidream-i1-full’, ‘fal-ai/hidream-i1-dev’, ‘fal-ai/hidream-i1-fast’
  - Image to image: ‘fal-ai/ghiblify’
  - Video AI: ‘fal-ai/wan-effects’, ‘fal-ai/wan-i2v’, ‘fal-ai/wan-pro/image-to-video’, ‘fal-ai/wan-t2v’, ‘fal-ai/wan/v2.1/1.3b/text-to-video’, ‘fal-ai/pixverse/v4/image-to-video’, ‘fal-ai/pixverse/v4/image-to-video/fast’, ‘fal-ai/pixverse/v4/text-to-video’, ‘fal-ai/pixverse/v4/text-to-video/fast’, ‘fal-ai/pixverse/v3.5/effects’, ‘fal-ai/pixverse/v3.5/image-to-video’, ‘fal-ai/pixverse/v3.5/image-to-video/fast’, ‘fal-ai/pixverse/v3.5/text-to-video’, ‘fal-ai/pixverse/v3.5/text-to-video/fast’, ‘fal-ai/veo2/image-to-video’, ‘fal-ai/kling-video/v1.6/standard/effects’, ‘fal-ai/kling-video/v1/standard/effects’, ‘fal-ai/kling-video/v1.5/pro/effect’
- Leonardo AI models:
  - ‘Leonardo Phoenix | Style and Content Reference’
  - ‘Leonardo Phoenix 0.9 | Style and Content Reference’
  - ‘Flux Dev | Style and Content Reference’
  - ‘Flux Schnell | Style and Content Reference’
  - ‘Motion 2.0|Image to video’
  - ‘Motion 2.0|Text to video’
- Minimax models:
  - ‘image-01’
- Azure models:
  - ‘gpt-4.1’
- Models in AI Content Labs (credit-based use):
  - Text generation: ‘gpt-4.1’, ‘gpt-4o-mini’, ‘o3-mini’, ‘o1-mini’, ‘gpt-4o’, ‘o1’, ‘gpt-4.5-preview’, ‘gemini-2.0-flash-lite-001’, ‘gemini-2.0-flash-001’, ‘gemini-1.5-flash-002’, ‘gemini-2.5-pro-preview-03-25’, ‘gemini-1.5-pro-002’
  - Tools: ‘Google Search’, ‘Google Image Search’, ‘Python Code Interpreter’
04/15/2025: Additional improvements:
- New voices added for OpenAI TTS models.
- Updated parameters for text-to-image generation in Leonardo AI models.
- Upscale configuration added for ‘imagen-03’ model from VertexAI.
- PDF merge now supports up to 50 files.

March 2025

14/03/2025: Minor bug fixes in flow execution.
14/03/2025: It is now possible to generate images using ‘gemini-2.0-flash-exp’.
14/03/2025: New AI models added:
- OpenRouter models:
  - ‘google/gemma-3-27b-it:free’
  - ‘openai/gpt-4o-search-preview’
  - ‘openai/gpt-4o-mini-search-preview’
- OpenAI models:
  - ‘gpt-4o-mini-search-preview’
  - ‘gpt-4o-search-preview’
14/03/2025: Added the option to set custom separators in ‘Max-Character Smart Split’.

03/09/2025: The options available in the ‘Render Engine’ node are now added as plugins.
03/09/2025: Audio-generating nodes now allow configuring a custom name for the output file.
03/09/2025: New AI models added:
- OpenRouter models:
  - ‘perplexity/sonar-deep-research’
  - ‘perplexity/sonar-pro’
  - ‘perplexity/sonar-reasoning-pro’
- Straico models:
  - ‘anthropic/claude-3-5-haiku-20241022’
  - ‘anthropic/claude-3.7-sonnet’
  - ‘anthropic/claude-3.7-sonnet:thinking’
  - ‘deepseek/deepseek-r1’
  - ‘google/gemini-2.0-flash-001’
  - ‘gpt-4.5-preview’
  - ‘openai/o1’
  - ‘openai/o3-mini-high’
  - ‘openai/o3-mini’

03/05/2025: Addition of new AI models:
- ElevenLabs models:
  - ‘tts|eleven_flash_v2_5’
  - ‘tts|eleven_flash_v2’
  - ‘transcription|scribe_v1’
  - ‘voice_changer|eleven_english_sts_v2’
  - ‘voice_changer|eleven_multilingual_sts_v2’
  - ‘effects|sound_generation’
  - ‘audio_isolation|remove_background_noise’
- Leonardo AI models:
  - Image-to-image versions of the models:
    - ‘Leonardo Phoenix’
    - ‘Leonardo Phoenix 0.9’
    - ‘Flux Dev’
    - ‘Flux Schnell’
    - ‘Leonardo Anime XL’
    - ‘Leonardo Kino XL’
    - ‘AlbedoBase XL’
    - ‘Leonardo Lightning XL’
    - ‘Leonardo Vision XL’
- Ideogram models:
  - ‘V_2A’
  - ‘V_2A_TURBO’
  - ‘upscale’
  - Image-to-image versions of the models:
    - ‘V_1’
    - ‘V_1_TURBO’
    - ‘V_2’
    - ‘V_2_TURBO’
    - ‘V_2A’
    - ‘V_2A_TURBO’
03/05/2025: Improvements to the Text Splitter node:
- New text splitting methods added:
  - ‘Pattern-based Split’ (original pattern-based method).
  - ‘Fixed-length Character Split’ (splitting based on a fixed character length).
  - ‘Max-Character Smart Split’ (considers a maximum number of characters but cuts the text at a paragraph or sentence boundary to avoid abrupt splits).

February 2025

02/28/2025: Added an option for concurrencyJobs in bulkMode, allowing users to specify how many processes will run in parallel.
02/28/2025: Introduction of a new node ‘Render Engine’, which includes the following methods:
- HTML to Image
- HTML to PDF
- Markdown to PDF
- Merge PDFs
02/28/2025: Addition of new AI models:
- OpenRouter models:
  - ‘google/gemini-2.0-flash-lite-001’
  - ‘openai/gpt-4.5-preview’
- OpenAI models:
  - ‘gpt-4.5-preview’
- Google models:
  - ‘gemini-2.0-flash-lite’
- Vertex AI models:
  - ‘gemini-2.0-flash-lite-001’
- Perplexity models:
  - ‘sonar-deep-research’
- Azure models:
  - ‘gpt-4.5-preview’
- Fal.ai models:
  - ‘fal-ai/minimax-music’
  - ‘fal-ai/f5-tts’
  - ‘fal-ai/zonos’
  - ‘fal-ai/kokoro/american-english’
  - ‘fal-ai/kokoro/british-english’
  - ‘fal-ai/kokoro/japanese’
  - ‘fal-ai/kokoro/mandarin-chinese’
  - ‘fal-ai/kokoro/spanish’
  - ‘fal-ai/kokoro/french’
  - ‘fal-ai/kokoro/hindi’
  - ‘fal-ai/kokoro/italian’
  - ‘fal-ai/kokoro/brazilian-portuguese’
  - ‘fal-ai/playai/tts/v3’
  - ‘fal-ai/playai/tts/dialog’
  - ‘fal-ai/mmaudio-v2’
  - ‘fal-ai/stable-audio’
  - ‘fal-ai/yue’
  - ‘fal-ai/mmaudio-v2’
  - ‘fal-ai/ltx-video’
- Minimax models:
  - ‘speech-01-turbo’
  - ‘speech-01-hd’
  - ‘speech-01-turbo|large’
  - ‘music-01’
  - ‘image-01’
  - ‘T2V-01-Director’
  - ‘I2V-01-Director’
  - ‘S2V-01’
  - ‘I2V-01’
  - ‘I2V-01-live’
  - ‘T2V-01’
02/28/2025: Now, in multiple-type inputs, you can specify the maximum number of selectable values.

02/24/2025: A new AI model provider has been added:
- Minimax with the following text models:
  - ‘MiniMax-Text-01’
  - ‘DeepSeek-R1’
  - ‘abab6.5s-chat’
02/24/2025: New AI models have been added:
- Anthropic Models:
  - ‘claude-3-7-sonnet-20250219’
- Perplexity Models:
  - ‘r1-1776’
- OpenAI Models:
  - ‘gpt-4o-audio-preview-2024-10-01’
  - ‘gpt-4o-mini-audio-preview’
- Azure Models:
  - ‘gpt-4o-audio-preview’
  - ‘gpt-4o-mini-audio-preview’
- OpenRouter Models:
  - ‘mistralai/mistral-saba’
  - ‘perplexity/r1-1776’
  - ‘anthropic/claude-3.7-sonnet’
- Fal.AI Models:
  - Text to Image:
    - ‘fal-ai/imagen3’
    - ‘fal-ai/imagen3/fast’
    - ‘fal-ai/bria/text-to-image/hd’
    - ‘fal-ai/bria/text-to-image/base’
    - ‘fal-ai/bria/text-to-image/fast’
    - ‘fal-ai/luma-photon’
    - ‘fal-ai/luma-photon/flash’
    - ‘fal-ai/sana’
    - ‘fal-ai/recraft-20b’
  - Image to Image:
    - ‘fal-ai/bria/product-shot’
  - Video AI:
    - ‘fal-ai/minimax/video-01/image-to-video’
    - ‘fal-ai/minimax/video-01-subject-reference’
    - ‘fal-ai/minimax/video-01-live/image-to-video’
    - ‘fal-ai/minimax/video-01-live’
    - ‘fal-ai/minimax/video-01-director’
    - ‘fal-ai/minimax/video-01’
    - ‘fal-ai/hunyuan-video’
    - ‘fal-ai/hunyuan-video-img2vid-lora’
    - ‘fal-ai/veo2’
    - ‘fal-ai/skyreels-i2v’
    - ‘fal-ai/haiper-video/v2/image-to-video’
    - ‘fal-ai/haiper-video/v2.5/image-to-video/fast’
    - ‘fal-ai/haiper-video/v2’
    - ‘fal-ai/haiper-video/v2.5/fast’
  - Image Utilities:
    - ‘fal-ai/bria/background/replace’
    - ‘fal-ai/bria/background/remove’

02/15/2025: Changes and improvements in the flow editor:
- Ability to test different models simultaneously in image nodes (text-to-image and image-to-image), video, audio, multimedia tools, web scraper, and web search, just as it is done with prompt nodes.
- Option to pause flow execution in the editor (ongoing processes will complete before pausing). Execution can later be resumed unless node dependencies change.
- Editing preliminary flow results in the editor to test variations in outcomes.
- Ability to re-execute a node’s result without needing to restart the flow.
- Display of the final result of concatenated nodes and an option to send it to a webhook directly from the editor interface.
- Available models in text-to-image, web extractor, and web search nodes are added as tools available in Prompt nodes.
02/15/2025: Integration of new AI models:
- OpenRouter models:
  - ‘qwen/qwen-turbo’
  - ‘qwen/qwen2.5-vl-72b-instruct:free’
  - ‘qwen/qwen-plus’
  - ‘qwen/qwen-max’
  - ‘google/gemini-2.0-flash-001’
  - ‘google/gemini-2.0-flash-lite-preview-02-05:free’
  - ‘google/gemini-2.0-pro-exp-02-05:free’
  - ‘openai/o3-mini-high’
  - ‘openai/o3-mini’
  - ‘openai/o1’
- Vertex AI models:
  - ‘gemini-2.0-flash-001’
  - ‘gemini-2.0-flash-lite-preview-02-05’
  - ‘gemini-2.0-pro-exp-02-05’
  - ‘imagen-3.0-generate-002’
- Google models:
  - ‘gemini-2.0-flash’
  - ‘gemini-2.0-pro-exp-02-05’
  - ‘gemini-2.0-flash-lite-preview-02-05’
- Perplexity models:
  - ‘sonar-reasoning-pro’
  - ‘sonar-reasoning’
- Leonardo AI models:
  - ‘Leonardo Phoenix 0.9’
  - ‘Flux Dev’
  - ‘Flux Schnell’
02/15/2025: Removal of obsolete and discontinued models:
- Models removed from OpenRouter:
  - ‘perplexity/llama-3.1-sonar-huge-128k-online’
  - ‘perplexity/llama-3.1-sonar-small-128k-online’
  - ‘perplexity/llama-3.1-sonar-small-128k-chat’
  - ‘perplexity/llama-3.1-sonar-large-128k-online’
  - ‘perplexity/llama-3.1-sonar-large-128k-chat’
  - ‘perplexity/llama-3-sonar-small-32k-chat’
  - ‘perplexity/llama-3-sonar-small-32k-online’
  - ‘perplexity/llama-3-sonar-large-32k-chat’
  - ‘perplexity/llama-3-sonar-large-32k-online’
- Models removed from Perplexity:
  - ‘llama-3.1-sonar-small-128k-online’
  - ‘llama-3.1-sonar-large-128k-online’
  - ‘llama-3.1-sonar-huge-128k-online’

January 2025

01/31/2025: New models added:
- OpenRouter:
  - ‘deepseek/deepseek-r1-distill-qwen-32b’
  - ‘deepseek/deepseek-r1-distill-qwen-14b’
  - ‘deepseek/deepseek-r1-distill-qwen-1.5b’
  - ‘perplexity/sonar’
  - ‘perplexity/sonar-reasoning’
- OpenAI: ‘o3-mini’
- Perplexity:
  - ‘sonar-reasoning’
  - ‘sonar-pro’
  - ‘sonar’
- Groq: ‘deepseek-r1-distill-llama-70b’
- Azure: ‘o3-mini’
01/31/2025: For the ‘o1’ and ‘o3-mini’ models, the option to select the reasoning Effort has been added.
01/27/2025: Addition of new AI models:
- OpenRouter models:
  - ‘deepseek/deepseek-r1’
  - ‘deepseek/deepseek-r1-distill-llama-70b’
  - ‘mistralai/codestral-2501’
- Deepseek model:
  - ‘deepseek-reasoner’
- Mistral model:
  - ‘codestral-latest’

01/27/2025: Changes to nodes and improvements in multimedia tools:
- The ‘Image Tools’ node has been renamed to ‘Multimedia Tools’.
- New actions added to the ‘Multimedia Tools’ node:
  - Resize|fit
  - Resize|fill
  - Resize|force
  - Crop
  - Blur
  - Sharpen
  - Convert format
  - Background color
  - Brightness
  - Contrast
  - Equalize
  - Resize and fill with color
  - Grayscale
  - Noise
  - Reduce proportion
  - RGB color adjustment
  - Rotate
  - Round corners
  - Saturation
  - Watermark
  - Flip horizontally
  - Flip vertically
  - Add text
  - Set background for transparent image

01/14/2025: Improvements to the default AICL scraper:
- It is now possible to select CSS elements.
01/14/2025: Addition of new AI providers and models:
- The provider DeepSeek is added with its model ‘deepseek-chat’.
- Models from OpenRouter:
  - ‘deepseek/deepseek-chat’
  - ‘x-ai/grok-2-1212’
  - ‘x-ai/grok-2-vision-1212’
  - ‘google/gemini-2.0-flash-thinking-exp:free’
  - ‘cohere/command-r7b-12-2024’
- Models from Vertex AI:
  - ‘gemini-2.0-flash-thinking-exp-1219’
- Models from Google AI Studio:
  - ‘gemini-2.0-flash-thinking-exp-1219’
- Models from xAI:
  - ‘grok-2-1212’
  - ‘grok-2-vision-1212’
- Model from Cohere:
  - ‘command-r7b-12-2024’
- New video models from FalAI:
  - ‘fal-ai/kling-video/v1.6/pro/image-to-video’
  - ‘fal-ai/kling-video/v1.6/standard/image-to-video’
  - ‘fal-ai/kling-video/v1.6/standard/text-to-video’
01/14/2025: Workflow improvements:
- The ‘Text Merger’ node is introduced, allowing you to combine results from multi-output nodes.
- The ‘files’ input type can now accept up to 20 files.

December 2024

17/12/2024: Addition of new AI models: ‘fal-ai/leffa/virtual-tryon’, ‘fal-ai/leffa/pose-transfer’, ‘fashn/tryon’.
17/12/2024: Removal of the ‘gemma-7b-it’ model from Grok.
12/12/2024: Addition of new AI providers and models:
- Support for XAI has been added with the models ‘grok-beta’, ‘grok-vision-beta’.
- Integration of JoggAI with the models ‘create_video_from_url’, ‘create_video_from_talking_avatar’.
- Straico has been added with the models ‘anthropic/claude-3-haiku:beta’, ‘anthropic/claude-3-opus’, ‘anthropic/claude-3-sonnet’, ‘anthropic/claude-3.5-sonnet’, ‘google/gemini-pro-1.5’, ‘openai/gpt-4o-2024-08-06’, ‘openai/gpt-4o’, ‘openai/gpt-4o-mini’, ‘openai/o1-mini’, ‘openai/o1-preview’.
- Google models included: ‘gemini-exp-1206’, ‘gemini-2.0-flash-exp’.
- Vertex AI models added: ‘claude-3-5-sonnet-v2@20241022’, ‘claude-3-5-sonnet@20240620’, ‘gemini-2.0-flash-exp’, ‘gemini-exp-1206’.
- Azure models added: ‘o1-preview’, ‘o1-mini’.
- OpenRouter models added: ‘amazon/nova-pro-v1’, ‘amazon/nova-lite-v1’, ‘amazon/nova-micro-v1’, ‘google/gemini-2.0-flash-exp:free’, ‘google/gemini-exp-1206:free’, ‘meta-llama/llama-3.3-70b-instruct’.
- FalAI models included: ‘fal-ai/ideogram/v2’, ‘fal-ai/ideogram/v2/remix’, ‘fal-ai/kling-video/v1.5/pro/image-to-video’, ‘fal-ai/kling-video/v1.5/pro/text-to-video’, ‘fal-ai/kling-video/v1/pro/image-to-video’, ‘fal-ai/kling-video/v1/pro/text-to-video’, ‘fal-ai/kling-video/v1/standard/image-to-video’, ‘fal-ai/kling-video/v1/standard/text-to-video’.

12/12/2024: AI provider removal:
- AlephAlpha has been removed as a provider due to the closure of its operations.

November 2024

11/28/2024: Integration of new AI providers and model updates:
- Support for Vertex AI has been added, enabling text and image generation.
- Ideogram has been integrated, specializing in image generation.
- ElevenLabs is now included as a provider for audio content generation.
- It is now possible to use the ‘gpt-4o-audio-preview’ model from OpenAI for audio creation.
- The TTS and Whisper models from OpenAI are also supported for text-to-speech generation and speech-to-text transcriptions, respectively.
- Image creation using the DALL-E model from Azure is now supported.
- New text generation models from compatible providers have been incorporated.
11/28/2024: Improvements to the prompt and workflow creation interface:
- Variable creation visualization has been optimized for better clarity.
- A new option to include citations has been added for models that support it: Perplexity, Gemini, and Vertex. Cohere already included this functionality previously.
- It is now possible to attach images, audio, and other files to compatible models during execution.
11/28/2024: Updates to the interface and workflow features:
- The ‘AI Image’ node has been replaced with a more descriptive node called ‘Text to Image’.
- New nodes have been added to expand functionality:
  - ‘Image to Image’ allows transforming an existing image using an AI model.
  - ‘Image Utilities’ provides tools such as resolution enhancement (upscale) and background removal, among others.
  - ‘AI Video’ enables the creation of videos from text and/or images.
  - ‘AI Audio’ allows generating audio from text or transcribing the content of an audio file.
- The visualization for testing workflow execution has been improved, allowing switching between HTML format and the standard format.
- The input node now supports file uploads and handling.

October 2024

10/23/2024: New AI Models Available
- OpenRouter: ‘x-ai/grok-beta’, ‘nvidia/llama-3.1-nemotron-70b-instruct’, ‘mistralai/ministral-8b’, ‘mistralai/ministral-3b’, ‘anthropic/claude-3.5-sonnet-20240620’, ‘anthropic/claude-3.5-sonnet-20240620:bet’.
- Anthropic: ‘claude-3-5-sonnet-20241022’.
- Mistral: ‘ministral-8b-latest’, ‘ministral-3b-latest’.

10/06/2024: Optimization in workflow execution:
- Nodes are now grouped by levels and executed in parallel, significantly improving processing times.
- Divided nodes are now processed in groups of 5 to avoid rate limits in APIs.
- An option has been added to use the previous sibling node’s result as context. Note that activating this option will cause sequential execution instead of parallel for each division, which may increase the total workflow processing time.
- Results generated by image nodes can now be used as input for other nodes.
- A new node «Text Transformer» has been added for text manipulation and transformation, including: slug conversion, specific part extraction, uppercase/lowercase changes, extra space removal, text replacement, punctuation removal, word/character counting, conversion to specific formats, duplicate removal, HTML escape, HTML tag removal, normalization, Markdown format removal, word frequency analysis, and text trimming.
10/06/2024: Improvements in bulk workflow and template execution:
- It is now possible to select which specific nodes should be included in the returned results.
- Results generated in CSV format, such as those sent to the webhook, are available as plain text and with HTML tags, offering greater flexibility for subsequent analysis.
- Markdown to HTML formatting has been refined in workflow and template outputs, improving readability and structure of the information.
10/06/2024: Expansion of capabilities in models and plugins:
- Google models are now compatible with plugin usage.
- Introduction of two new plugins: Web search with SpaceSerp and Python Code Interpreter (beta version).
- The ability to process image URLs as input for models with vision capabilities has been introduced. This option must be manually activated by the user and will only work with models that support visual analysis.
10/06/2024: User interface updates:
- New icons to quickly identify model capabilities (vision, web search, plugin usage).
- Implementation of open/closed lock icons to easily distinguish between open-source and private templates and workflows.
10/06/2024: Addition of new AI models:
- OpenRouter: ‘gemini-flash-1.5-8b’, ‘meta-llama/llama-3.2-3b-instruct:free’, ‘meta-llama/llama-3.2-3b-instruct’, ‘meta-llama/llama-3.2-1b-instruct:free’, ‘meta-llama/llama-3.2-1b-instruct’, ‘meta-llama/llama-3.2-90b-vision-instruct’, ‘meta-llama/llama-3.2-11b-vision-instruct:free’, ‘meta-llama/llama-3.2-11b-vision-instruct’, ‘o1-mini’, ‘o1-preview’.
- OpenAI: ‘gpt-4o-2024-05-13’, ‘o1-mini’, ‘o1-preview’.
- Google: ‘gemini-1.5-pro-002’, ‘gemini-1.5-flash-002’, ‘gemini-1.5-flash-8b’, ‘gemini-1.5-flash-8b-exp-0924’.
- Groq: ‘mixtral-8x7b-32768’, ‘llama-3.1-70b-versatile’, ‘llava-v1.5-7b-4096-preview’, ‘llama-guard-3-8b’, ‘llama-3.2-11b-vision-preview’, ‘llama-3.2-1b-preview’, ‘llama3-groq-8b-8192-tool-use-preview’, ‘llama3-groq-70b-8192-tool-use-preview’.
- Mistral: ‘pixtral-12b-2409’, ‘open-codestral-mamba’.
10/06/2024: Additional improvements and fixes:
- Detection of uncommon or potentially problematic URLs in the scraper has been refined.
- Improved visualization of agent results when step-by-step option is selected.
- Fixed UI errors in templates that displayed inaccurate creation dates.

September 2024

09/04/2024: New AI models added: ‘jamba-1-5-mini’, ‘jamba-1-5-large’ (AI21Labs and Open Router), ‘gemini-flash-1.5-exp’, ‘gemini-flash-8b-1.5-exp’ (Google Gemini and Open Router), ‘gemini-1.5-pro-exp-0827’ (Google Gemini), ‘command-r-08-2024’ and ‘command-r-plus-08-2024’ (Cohere and Open Router), ‘yi-1.5-34b-chat’, and ‘phi-3.5-mini-128k-instruct’ (Open Router).
09/04/2024: Fixed an issue when saving templates with Google models.
09/03/2024: Resolved an issue when running bulk executions of templates and flows with multiple choice input types.
09/01/2024: Reactivated the option for webhooks. You can now send the execution of your flows and templates, either individually or in bulk, to other applications.
09/01/2024: Bulk execution of templates now allows plugin selection and changes to the default model. In flows, it allows replacing the main execution model.

August 2024

08/30/2024: New providers added: NeuronWriter, SpaceSerp, ValueSerp, Exa.ai, Tavily, and ScrapeDo.
08/30/2024: New «Search Engine» node added to the flows.
08/30/2024: Option to obtain the full HTML content when scraping a URL added.
08/30/2024: Fixed an issue with the «Exclude images» option in the Scraper, which was returning the «alt» text of the images.
08/19/2024: New AI models added: ‘hermes-3-llama-3.1-405b’, ‘hermes-3-llama-3.1-405b:extended’ in Open Router; ‘llama-3.1-sonar-huge-128k-online’ in Open Router and Perplexity; ‘gpt-4o-2024-08-06’, ‘chatgpt-4o-latest’ in OpenAI and Open Router.
08/19/2024: ScrapeOwl added as a web scraping provider.
08/19/2024: Scraper node added to the flows.
08/19/2024: The «Google Custom Search» plugin now includes a filter to restrict results by date.
08/19/2024: Implemented a maximum of 3 retries in case of Fal.ai service failure.
08/19/2024: Fixed an issue in flows composed solely of image models where one of the services failed.
08/04/2024: FalAI added as a plugin in templates and as a node in flows.
08/04/2024: New models added: gemini-pro-1.5-exp, available both on Google and OpenRouter.
08/04/2024: New models added: 01-ai/yi-large-turbo, available on OpenRouter.
08/04/2024: New models added: 01-ai/yi-large-fc, available on OpenRouter.
08/04/2024: New models added: 01-ai/yi-vision, available on OpenRouter.
08/03/2024: Multiple plugins for statistical graphics added.
08/03/2024: Leonard.ai now available as a plugin for an agent.
08/03/2024: YouTube search node added, with the ability to return auto-generated captions if available.
08/03/2024: YouTube search now available as a plugin for an agent.
08/03/2024: New models ‘mistral-large’ and ‘mistral-nemo’ available on OpenRouter and Mistral.
08/03/2024: New models ‘llama-3.1-sonar-small-128k-online’, ‘llama-3.1-sonar-large-128k-online’, ‘llama-3.1-8b-instruct’, ‘llama-3.1-70b-instruct’, ‘llama-3.1-sonar-small-128k-chat’, ‘llama-3.1-sonar-large-128k-chat’ now available on Perplexity.
08/03/2024: Previous models on Perplexity removed as they will be retired on 12/08/2024.

July 2024

Product Improvements:

07/24/2024: Error messages are improved in case of a service execution failure in a flow or template.
07/24/2024: A caching layer is added to reuse results from some APIs (Google Custom Search, Frase, etc.)
07/24/2024: Dalle and Stability are added as plugins in templates and nodes.
You can now indicate which input will appear first when creating your flows.
When selecting a connection in the flow interface, you can add a new node without breaking the sequence. Similarly, when deleting an intermediate node, the created sequence is maintained.
The «Frase Search» node is added, which allows obtaining entity clusters from search results in the SERPs of a keyword, as well as statistics and content.
The «Image picker» node is added, which selects the first image search result based on a query. It supports Pixabay and Pexels repositories.
New plugins are added to generate statistical charts and various diagrams.
The web search plugin performs one of the following tasks upon execution: scraping, summarizing, or performing a semantic search within the content. The agent determines the best action. In the case of summarizing, it uses the ‘gpt-4o-mini’ model, and for semantic search, it uses the ‘text-embedding-3-small’ model.
The option is provided to know the steps followed by an agent when using plugins.
Multiple URLs can now be scraped and displayed as a single result in the quick access tool.
Sources can be chosen to be displayed in the results of Cohere’s ‘command-r’ and ‘command-r-plus’ models.
URL handling within prompts can now be configured.
Fixed error when saving flows that contained a prompt with multiple-type variables.
Other minor bugs are fixed.

Models Added:

07/24 /2024: Llama 3.1 models are added to Groq and OpenRouter providers.
AI21Labs: ‘jamba-instruct-preview’ model.
OpenAI: ‘gpt-4o-mini’ model.
Stability: ‘core’ and ‘ultra’ models.

New Integrations with AI Providers:

07/24/2024: Added Leonardo.ai text-to-image integration.
OpenRouter: Multiple models added.

April – June 2024

Product Improvements:

Node Duplication: Now it is possible to duplicate AI prompt nodes in flows.
New Node Type: The «Fixed Text» node has been added.
External Sharing: Flow outputs and templates can now be shared externally.
Plugins in Templates: The ability to use plugins in templates that utilize some Anthropic models has been added.

Added Models:

OpenAI: ‘gpt-4o’ model.
Stable Diffusion: ‘sd3’ and ‘sd3-turbo’ models.
Cohere: ‘command-r’ and ‘command-r-plus’ models, which include up-to-date web information search.
Anthropic: ‘claude-3.5-sonnet’ model.

New Integrations with AI Providers:

Google Gemini: ‘gemini-pro’, ‘gemini-1.5-pro-latest’ and ‘gemini-1.5-flash-latest’ models.
Groq: ‘llama3-8b-8192’, ‘llama3-70b-8192’, ‘mixtral-8x7b-32768’, and ‘gemma-7b-it’ models.
Mistral: ‘open-mistral-7b’, ‘open-mixtral-8x7b’, ‘open-mixtral-8x22b’, ‘mistral-small-latest’, ‘mistral-medium-latest’, and ‘mistral-large-latest’ models.
Azure: ‘gpt-4o’, ‘gpt-35-turbo’, and ‘gpt-35-turbo-instruct’ models.
Perplexity: ‘llama-3-sonar-small-32k-chat’, ‘llama-3-sonar-large-32k-chat’, ‘llama-3-8b-instruct’, ‘llama-3-70b-instruct’, ‘mixtral-8x7b-instruct’, ‘llama-3-sonar-small-32k-online’, and ‘llama-3-sonar-large-32k-online’ models, the latter two allow obtaining up-to-date information from the web.

Bulk Jobs (Beta):

The beta option to execute templates and flows in batches of 100, known as «bulk jobs», has been introduced. These executions use a credit system, where executing a template consumes one credit and a flow ten credits. This functionality may vary as it progresses to a stable version.

January – March 2024

Templates and Flows Update:

Stable Version of Templates: After an extensive beta testing period, templates have been optimized and now form the stable version. For those who prefer the previous version, it remains accessible through the legacy menu.
Stable Version of Flows: Similarly to templates, flows have been corrected for bugs identified during their beta phase and have now progressed to a stable version. The previous version continues to be available in the legacy menu for use.

Integration and Functionality Improvements:

Import Templates and Flows: A new feature has been introduced that allows importing previous versions of templates and flows into the new version, making the transition and updating of your projects smoother.
Claude Model Update: The latest versions of Claude models have been incorporated, ensuring access to the most recent advancements in artificial intelligence.
Predefined Prompts: We have added a wide selection of predefined prompts designed to boost your creativity and efficiency in content generation.
Quick Interface for AI Tools: We present a new interface that allows you to translate, summarize, and rewrite text efficiently, supported by multiple AI models to perform these tasks more effectively and accurately.

Launch of Our New Website:

AI Content Labs: We are excited to announce the launch of our new website www.aicontentlabs.com, where you can find detailed information about all our tools, services, and the latest updates. We invite you to explore it and discover everything we have prepared for you.

These improvements are aimed at enriching your experience and expanding the capabilities of our services, ensuring that you have the most advanced tools for your content projects.

August – December 2023

A new interface for template creation (beta) has been introduced, featuring the following improvements:

Differentiation between «chat» and «completion» models for adding system messages.
Ability to test template functionality from the editing interface.
Both simple and advanced settings to adjust artificial intelligence parameters.
Option to test multiple AI models simultaneously.
Integration of Anthropic and Google models, in addition to those previously included.
Advanced configuration for various types of variables, such as text, URL, selection lists, and random value selection.
Support for using plugins in templates.

The launch of a new interface for flow creation (beta) highlights the following features:

Flows operate independently of templates, allowing for direct creation of prompts.
Ability to incorporate image creation within flows.
Support for text division in flows up to three levels.
Creation of repeatable and connected inputs, ideal for individual outlines.
Functionality to test flows directly in the creation interface.
Possibility to overwrite the specific AI model for flow execution.
Option to duplicate nodes within the flow from the interface.

OpenAI Model Update: The latest OpenAI models have been updated on the platform.

A foundation for integrating complementary services as plugins has been added, facilitating integration with Google Search, Wikipedia, and Wolfram Alpha.

Jul 15, 2023

Launch of Addon for Google Sheets.

Jul 7, 2023

Reactivation of generation history for flows and templates.
Quick access to generation history during the session added, accessible from the widget in the bottom-right corner of your screen.

Jun 22, 2023

Added a button to transfer all API Keys from the team leader to a member.
Now, when adding a service API, a check will be performed to verify if it is a valid API.
It is now feasible to scrape, summarize, and rewrite from any part of the application via the button located in the bottom-right corner.

Jun 13, 2023

Added new models from OpenAI (gpt-4-32k and gpt-3.5-turbo-16k), AI21labs (j2-ultra, j2-mid and j2-light), and Aleph Alpha (Luminous-Base-Control, Luminous-Extended-Control, and Luminous-Supreme-Control).
If you have the API Key for AI21Labs or Frase configured, you will be able to scrape URLs. For YouTube URLs, these services will not be necessary (information will only be obtained from YouTube if the video has subtitles).
URLs can now be processed within the document editor, templates, and flows (Note: To be processed, the content of the URLs will be summarized using either the gpt-3.5-turbo-16k model from OpenAI or the summary model from Cohere).
Team leaders are now required to set up their API key for each of their team members.

May 30, 2023

Reactivated the Summarizer in the document editor, accessible from the editor’s button list and by selecting a text or using the Frase integration’s search functionality.
Added support for multiple models including Cohere, AI21Labs (English-only), Aleph Alpha, and OpenAI (gpt-3.5-turbo, gpt-4, text-davinci-003) for summarization.
Enabled the Frase option for team members.
Introduced voice tones in the document editor and Summarizer feature.

May 15, 2023

We now provide the option to offer customized API keys to team members.
We have added a view of credit usage history for team members.
Now, specific access can be granted to each team member for the administrator’s templates and workflows.

May 7, 2023

We have added team functionality.
The ability to add more webhooks based on the number of team members is now available.

March 24, 2023

Added GPT-4 model.
Increased the maximum template execution time to 270 seconds.
Added auto-save functionality to documents. This change has also affected autosaving for text generations in the document editor, where content produced with the «Compose» and «Generate» button will no longer be saved in the history to avoid duplicates. However, this modification does not apply to templates or flows executed in the document editor, which will continue to appear in the history.
In Easy mode of the document editor, users can now change the provider and model to generate content. Note: Only the most advanced models of each provider are included.

March 10, 2023

Jurassic-2 models from AI21Labs have been added.
Template and flow outputs now interpret mermaid syntax.
Outputs generated in the document editor interpret Markdown syntax.
Minor bugs fixed when deleting a template that was associated with a flow.

March 01, 2023

ChatGPT API is integrated into the document editor, templates, and flows.
Added the ability to share templates and flows between platform users.
You can now make the step-by-step execution of a flow optional.
Added auto-formatting for Markdown in flow outputs, templates, and history view.
Added Aleph Alpha’s Supreme-control model.
You can now delete up to 15 documents at once.
Open-source flows allow duplication of the templates they comprise.
Added Aleph Alpha and Cohere summary models in the document editor.

February 04, 2023

Results divided by paragraph nodes can now be hidden in flows.
Added flow and template search within the document editor.
Cohere models were updated.

January 16, 2023

Images and YouTube videos can now be added to the document editor using links.
Increased the character limit for input marked as divided into paragraphs to 20,000.
Flows can now chain up to 10 templates and include 15 inputs.
Negative weights can now be added in the image playground for the Stability provider.
All keywords from Frase can now be copied to the document editor.
Quick Markdown formatting can be applied to content in documents.
Added paraphrasing option with AI21 Labs’ API in the document editor.
Added summarization option in the document editor (Up to 50,000 characters).
Added rewriting option in the document editor (Up to 50,000 characters).
You can now execute multiple flows, templates, summaries, rewriting, and images with a single click in the document editor using shortcodes.

December 16, 2022

Added the option to execute flows step by step for debugging purposes.
Integration options with DeepL and Google Translate APIs for translation within the platform were added.
Added the keyboard shortcut Ctrl+Shift+Enter to execute a command.
Added an easy mode in the document editor.

November 30, 2022

Added the option to change the model at the time of template execution.
Added a dark mode.
Added integration with the Frase API.