* feat: introduce AnyProvider & LM Arena, overhaul model/provider logic
- **Provider additions & removals**
- Added `Provider/LMArenaProvider.py` with full async stream implementation and vision model support
- Registered `LMArenaProvider` in `Provider/__init__.py`; removed old `hf_space/LMArenaProvider.py`
- Created `providers/any_provider.py`; registers `AnyProvider` dynamically in `Provider`
- **Provider framework enhancements**
- `providers/base_provider.py`
- Added `video_models` and `audio_models` attributes
- `providers/retry_provider.py`
- Introduced `is_content()` helper; now treats `AudioResponse` as stream content
- **Cloudflare provider refactor**
- `Provider/Cloudflare.py`
- Re‑implemented `get_models()` with `read_models()` helper, `fallback_models`, robust nodriver/curl handling and model‑name cleaning
- **Other provider tweaks**
- `Provider/Copilot.py` – removed `"reasoning"` alias and initial `setOptions` WS message
- `Provider/PollinationsAI.py` & `PollinationsImage.py`
- Converted `audio_models` from list to dict, adjusted usage checks and labels
- `Provider/hf/__init__.py` – applies `model_aliases` remap before dispatch
- `Provider/hf_space/DeepseekAI_JanusPro7b.py` – now merges media before upload
- `needs_auth/Gemini.py` – dropped obsolete Gemini model entries
- `needs_auth/GigaChat.py` – added lowercase `"gigachat"` alias
- **API & client updates**
- Replaced `ProviderUtils` with new `Provider` map usage throughout API and GUI server
- Integrated `AnyProvider` as default fallback in `g4f/client` sync & async flows
- API endpoints now return counts of providers per model and filter by `x_ignored` header
- **GUI improvements**
- Updated JS labels with emoji icons, provider ignore logic, model count display
- **Model registry**
- Renamed base model `"GigaChat:latest"` ➜ `"gigachat"` in `models.py`
- **Miscellaneous**
- Added audio/video flags to GUI provider list
- Tightened error propagation in `retry_provider.raise_exceptions`
* Fix unittests
* fix: handle None conversation when accessing provider-specific data
- Modified `AnyProvider` class in `g4f/providers/any_provider.py`
- Updated logic to check if `conversation` is not None before accessing `provider.__name__` attribute
- Wrapped `getattr(conversation, provider.__name__, None)` block in an additional `if conversation is not None` condition
- Changed `setattr(conversation, provider.__name__, chunk)` to use `chunk.get_dict()` instead of the object directly
- Ensured consistent use of `JsonConversation` when modifying or assigning `conversation` data
* ```
feat: add provider string conversion & update IterListProvider call
- In g4f/client/__init__.py, within both Completions and AsyncCompletions, added a check to convert the provider from a string using convert_to_provider(provider) when applicable.
- In g4f/providers/any_provider.py, removed the second argument (False) from the IterListProvider constructor call in the async for loop.
```
---------
Co-authored-by: hlohaus <983577+hlohaus@users.noreply.github.com>
- Add new FreeRouter provider (based on OpenaiTemplate)
- Add new OpenRouter provider (needs auth) to access OpenRouter.ai service
- Update CablyAI provider imports to use Messages and AsyncResult
- Add support for new Gemini models including gemini-2.5-pro-exp, gemini-2.0-flash-thinking-exp, and gemini-deep-research
- Add processing for <think> tags in Gemini provider output by replacing <ctrl94>thought and <ctrl95> markers
- Update provider imports in __init__.py files to include the new providers
- Mark FreeRouter as not working initially
Add new default HuggingFace provider
Add format_image_prompt and get_last_user_message helper
Add stop_browser callable to get_nodriver function
Fix content type response in images route
Update demo model list
Disable upload cookies in demo
Track usage in demo mode
Add messages without asking the ai
Add hint for browser usage in provider list
Add qwen2 prompt template to HuggingFace provider
Trim automatic messages in HuggingFaceAPI
* Update model configurations, provider implementations, and documentation
- Updated model names and aliases for Qwen QVQ 72B and Qwen 2 72B (@TheFirstNoob)
- Revised HuggingSpace class configuration, added default_image_model
- Added llama-3.2-70b alias for Llama 3.2 70B model in AutonomousAI
- Removed BlackboxCreateAgent class
- Added gpt-4o alias for Copilot model
- Moved api_key to Mhystical class attribute
- Added models property with default_model value for Free2GPT
- Simplified Jmuz class implementation
- Improved image generation and model handling in DeepInfra
- Standardized default models and removed aliases in Gemini
- Replaced model aliases with direct model list in GlhfChat (@TheFirstNoob)
- Removed trailing slash from image generation URL in PollinationsAI (https://github.com/xtekky/gpt4free/issues/2571)
- Updated llama and qwen model configurations
- Enhanced provider documentation and model details
* Removed from (g4f/models.py) 'Yqcloud' provider from Default due to error 'ResponseStatusError: Response 429: 文字过长，请删减后重试。'
* Update docs/providers-and-models.md
* refactor(g4f/Provider/DDG.py): Add error handling and rate limiting to DDG provider
- Add custom exception classes for rate limits, timeouts, and conversation limits
- Implement rate limiting with sleep between requests (0.75s minimum delay)
- Add model validation method to check supported models
- Add proper error handling for API responses with custom exceptions
- Improve session cookie handling for conversation persistence
- Clean up User-Agent string and remove redundant code
- Add proper error propagation through async generator
Breaking changes:
- New custom exceptions may require updates to error handling code
- Rate limiting affects request timing and throughput
- Model validation is now stricter
Related:
- Adds error handling similar to standard API clients
- Improves reliability and robustness of chat interactions
* Update g4f/models.py g4f/Provider/PollinationsAI.py
* Update g4f/models.py
* Restored provider which was not working and was disabled (g4f/Provider/DeepInfraChat.py)
* Fixing a bug with Streaming Completions
* Update g4f/Provider/PollinationsAI.py
* Update g4f/Provider/Blackbox.py g4f/Provider/DDG.py
* Added another model for generating images 'ImageGeneration2' to the 'Blackbox' provider
* Update docs/providers-and-models.md
* Update g4f/models.py g4f/Provider/Blackbox.py
* Added a new OIVSCode provider from the Text Models and Vision (Image Upload) model
* Update docs/providers-and-models.md
* docs: add Conversation Memory class with context handling requested by @TheFirstNoob
* Simplified README.md documentation added new docs/configuration.md documentation
* Update add README.md docs/configuration.md
* Update README.md
* Update docs/providers-and-models.md g4f/models.py g4f/Provider/PollinationsAI.py
* Added new model deepseek-r1 to Blackbox provider. @TheFirstNoob
* Fixed bugs and updated docs/providers-and-models.md etc/unittest/client.py g4f/models.py g4f/Provider/.
---------
Co-authored-by: kqlio67 <>
Co-authored-by: H Lohaus <hlohaus@users.noreply.github.com>
* Add Path and PathLike support when uploading images
Improve raise_for_status in special cases
Move ImageResponse to providers.response module
Improve OpenaiChat and OpenaiAccount providers
Add Sources for web_search in OpenaiChat
Add JsonConversation for import and export conversations to js
Add RequestLogin response type
Add TitleGeneration support in OpenaiChat and gui
* Improve Docker Container Guide in README.md
* Add tool calls api support, add search tool support
- **Cloudflare Provider**: Added error handling for missing requirements when fetching arguments.
- **Copilot Provider**: Updated the prompt formatting to use a maximum length function, improving message handling.
- **PollinationsAI Provider**: Adjusted the prompt length to a maximum of 5000 characters.
- **GitHub Copilot Provider**: Updated to use `ClientSession` for better session management.
- **CSS Updates**: Enhanced the gradient styling in the GUI for a more visually appealing interface.
- **JavaScript Updates**: Added functionality to toggle search options in the chat interface.
* Add multiple images support
* Add multiple images support in gui
* Support multiple images in legacy client and in the api
Fix some model names in provider model list
* Fix unittests
* Add vision and providers docs
* refactor(g4f/Provider/Airforce.py): improve model handling and filtering
- Add hidden_models set to exclude specific models
- Add evil alias for uncensored model handling
- Extend filtering for model-specific response tokens
- Add response buffering for streamed content
- Update model fetching with error handling
* refactor(g4f/Provider/Blackbox.py): improve caching and model handling
- Add caching system for validated values with file-based storage
- Rename 'flux' model to 'ImageGeneration' and update references
- Add temperature, top_p and max_tokens parameters to generator
- Simplify HTTP headers and remove redundant options
- Add model alias mapping for ImageGeneration
- Add file system utilities for cache management
* feat(g4f/Provider/RobocodersAPI.py): add caching and error handling
- Add file-based caching system for access tokens and sessions
- Add robust error handling with specific error messages
- Add automatic dialog continuation on resource limits
- Add HTML parsing with BeautifulSoup for token extraction
- Add debug logging for error tracking
- Add timeout configuration for API requests
* refactor(g4f/Provider/DarkAI.py): update DarkAI default model and aliases
- Change default model from llama-3-405b to llama-3-70b
- Remove llama-3-405b from supported models list
- Remove llama-3.1-405b from model aliases
* feat(g4f/Provider/Blackbox2.py): add image generation support
- Add image model 'flux' with dedicated API endpoint
- Refactor generator to support both text and image outputs
- Extract headers into reusable static method
- Add type hints for AsyncGenerator return type
- Split generation logic into _generate_text and _generate_image methods
- Add ImageResponse handling for image generation results
BREAKING CHANGE: create_async_generator now returns AsyncGenerator instead of AsyncResult
* refactor(g4f/Provider/ChatGptEs.py): update ChatGptEs model configuration
- Update models list to include gpt-3.5-turbo
- Remove chatgpt-4o-latest from supported models
- Remove model_aliases mapping for gpt-4o
* feat(g4f/Provider/DeepInfraChat.py): add Accept-Language header support
- Add Accept-Language header for internationalization
- Maintain existing header configuration
- Improve request compatibility with language preferences
* refactor(g4f/Provider/needs_auth/Gemini.py): add ProviderModelMixin inheritance
- Add ProviderModelMixin to class inheritance
- Import ProviderModelMixin from base_provider
- Move BaseConversation import to base_provider imports
* refactor(g4f/Provider/Liaobots.py): update model details and aliases
- Add version suffix to o1 model IDs
- Update model aliases for o1-preview and o1-mini
- Standardize version format across model definitions
* refactor(g4f/Provider/PollinationsAI.py): enhance model support and generation
- Split generation logic into dedicated image/text methods
- Add additional text models including sur and claude
- Add width/height parameters for image generation
- Add model existence validation
- Add hasattr checks for model lists initialization
* chore(gitignore): add provider cache directory
- Add g4f/Provider/.cache to gitignore patterns
* refactor(g4f/Provider/ReplicateHome.py): update model configuration
- Update default model to gemma-2b-it
- Add default_image_model configuration
- Remove llava-13b from supported models
- Simplify request headers
* feat(g4f/models.py): expand provider and model support
- Add new providers DarkAI and PollinationsAI
- Add new models for Mistral, Flux and image generation
- Update provider lists for existing models
- Add P1 and Evil models with experimental providers
BREAKING CHANGE: Remove llava-13b model support
* refactor(Airforce): Update type hint for split_message return
- Change return type of from to for consistency with import.
- Maintain overall functionality and structure of the class.
- Ensure compatibility with type hinting standards in Python.
* refactor(g4f/Provider/Airforce.py): Update type hint for split_message return
- Change return type of 'split_message' from 'list[str]' to 'List[str]' for consistency with import.
- Maintain overall functionality and structure of the 'Airforce' class.
- Ensure compatibility with type hinting standards in Python.
* feat(g4f/Provider/RobocodersAPI.py): Add support for optional BeautifulSoup dependency
- Introduce a check for the BeautifulSoup library and handle its absence gracefully.
- Raise a if BeautifulSoup is not installed, prompting the user to install it.
- Remove direct import of BeautifulSoup to avoid import errors when the library is missing.
* fix: Updating provider documentation and small fixes in providers
* Disabled the provider (RobocodersAPI)
* Fix: Conflicting file g4f/models.py
* Update g4f/models.py g4f/Provider/Airforce.py
* Update docs/providers-and-models.md g4f/models.py g4f/Provider/Airforce.py g4f/Provider/PollinationsAI.py
* Update docs/providers-and-models.md
* Update .gitignore
* Update g4f/models.py
* Update g4f/Provider/PollinationsAI.py
---------
Co-authored-by: kqlio67 <>
* refactor(g4f/Provider/Airforce.py): improve model handling and filtering
- Add hidden_models set to exclude specific models
- Add evil alias for uncensored model handling
- Extend filtering for model-specific response tokens
- Add response buffering for streamed content
- Update model fetching with error handling
* refactor(g4f/Provider/Blackbox.py): improve caching and model handling
- Add caching system for validated values with file-based storage
- Rename 'flux' model to 'ImageGeneration' and update references
- Add temperature, top_p and max_tokens parameters to generator
- Simplify HTTP headers and remove redundant options
- Add model alias mapping for ImageGeneration
- Add file system utilities for cache management
* feat(g4f/Provider/RobocodersAPI.py): add caching and error handling
- Add file-based caching system for access tokens and sessions
- Add robust error handling with specific error messages
- Add automatic dialog continuation on resource limits
- Add HTML parsing with BeautifulSoup for token extraction
- Add debug logging for error tracking
- Add timeout configuration for API requests
* refactor(g4f/Provider/DarkAI.py): update DarkAI default model and aliases
- Change default model from llama-3-405b to llama-3-70b
- Remove llama-3-405b from supported models list
- Remove llama-3.1-405b from model aliases
* feat(g4f/Provider/Blackbox2.py): add image generation support
- Add image model 'flux' with dedicated API endpoint
- Refactor generator to support both text and image outputs
- Extract headers into reusable static method
- Add type hints for AsyncGenerator return type
- Split generation logic into _generate_text and _generate_image methods
- Add ImageResponse handling for image generation results
BREAKING CHANGE: create_async_generator now returns AsyncGenerator instead of AsyncResult
* refactor(g4f/Provider/ChatGptEs.py): update ChatGptEs model configuration
- Update models list to include gpt-3.5-turbo
- Remove chatgpt-4o-latest from supported models
- Remove model_aliases mapping for gpt-4o
* feat(g4f/Provider/DeepInfraChat.py): add Accept-Language header support
- Add Accept-Language header for internationalization
- Maintain existing header configuration
- Improve request compatibility with language preferences
* refactor(g4f/Provider/needs_auth/Gemini.py): add ProviderModelMixin inheritance
- Add ProviderModelMixin to class inheritance
- Import ProviderModelMixin from base_provider
- Move BaseConversation import to base_provider imports
* refactor(g4f/Provider/Liaobots.py): update model details and aliases
- Add version suffix to o1 model IDs
- Update model aliases for o1-preview and o1-mini
- Standardize version format across model definitions
* refactor(g4f/Provider/PollinationsAI.py): enhance model support and generation
- Split generation logic into dedicated image/text methods
- Add additional text models including sur and claude
- Add width/height parameters for image generation
- Add model existence validation
- Add hasattr checks for model lists initialization
* chore(gitignore): add provider cache directory
- Add g4f/Provider/.cache to gitignore patterns
* refactor(g4f/Provider/ReplicateHome.py): update model configuration
- Update default model to gemma-2b-it
- Add default_image_model configuration
- Remove llava-13b from supported models
- Simplify request headers
* feat(g4f/models.py): expand provider and model support
- Add new providers DarkAI and PollinationsAI
- Add new models for Mistral, Flux and image generation
- Update provider lists for existing models
- Add P1 and Evil models with experimental providers
BREAKING CHANGE: Remove llava-13b model support
* refactor(Airforce): Update type hint for split_message return
- Change return type of from to for consistency with import.
- Maintain overall functionality and structure of the class.
- Ensure compatibility with type hinting standards in Python.
* refactor(g4f/Provider/Airforce.py): Update type hint for split_message return
- Change return type of 'split_message' from 'list[str]' to 'List[str]' for consistency with import.
- Maintain overall functionality and structure of the 'Airforce' class.
- Ensure compatibility with type hinting standards in Python.
* feat(g4f/Provider/RobocodersAPI.py): Add support for optional BeautifulSoup dependency
- Introduce a check for the BeautifulSoup library and handle its absence gracefully.
- Raise a if BeautifulSoup is not installed, prompting the user to install it.
- Remove direct import of BeautifulSoup to avoid import errors when the library is missing.
---------
Co-authored-by: kqlio67 <>
* Add web_search function to OpenaiChat provider
* GithubCopilot provider added, it need a api_key
* Remove nodriver login in Gemini synthesize
* Update api / add a synthesize and upload_cookies endpoint
* Improve slim docker image example, clean up OpenaiChat provider
* Enhance event loop management for asynchronous generators
* Fix attribute " shutdown_default_executor" not found in old python versions
* asyncio file created with all async helpers
* Add speech synthesize from Gemini. You can use it without a account
