- Added "transparent" to `image_models` in `PollinationsAI` and mapped it to "gptimage"
- Modified transparent flag handling in `_generate_image` call in `PollinationsAI`
- Removed unused `cls.get_models()` call from image generation method in `PollinationsAI`
- Replaced `AsyncGeneratorProvider` with `AsyncAuthedProvider` in `HarProvider`
- Implemented `on_auth_async` in `HarProvider` to support browser-based auth via `nodriver`
- Replaced `create_async_generator` with `create_authed` in `HarProvider` to support `AuthResult`
- Removed custom `headers` in HAR post requests; used `auth_result.get_dict()` for `StreamSession`
- Refactored `Video` provider to support optional search in `get_response`
- Added `search` parameter to `RequestConfig.get_response` and `Video.create_async_generator`
- Improved browser automation and element interaction logic in `Video` provider
- Extracted video request interception to collect URLs using `nodriver`
- Reduced video polling loop timeout from 600 to 300 iterations in `Video`
- Updated CLI `client.py` to fix handling of `conversation.conversation` assignment
- Fixed argparse config: removed `nargs='?'` and added `metavar` for `--conversation-file`
- Improved image metadata extraction in API and backend when Pillow is available
- Modified `ImageResponse.__str__` to output HTML anchor/image tags with dimensions if present
- Added support for returning `target_path` from `copy_media` if `return_target` is True
- Changed default image processing size in `process_image` from 800x400 to 400x400
- Disabled RGBA-to-RGB flattening in `process_image`
- Improved `get_args_from_nodriver` to ensure proper referer and cookie handling
- Added helper `get_target_paths_and_urls` in `Api` to extract image dimensions from disk paths
- Introduced `clean_name` function in `Cloudflare.py` to format model names by removing specific suffixes.
- Updated `model_aliases` in `Cloudflare` class with new model mappings, and cleaned up redundant entries.
- Set `models` in the `Cloudflare` class to use keys from `model_aliases`.
- Adjusted the caching logic in `Cloudflare` to include new headers for requests.
- Added `parent` and `login_url` attributes in `DeepInfraChat` class.
- Updated `PollinationsAI` to clean up model retrieval logic and fixed handling of existing checks.
- Refactored `HarProvider` to inherit models and aliases from `LegacyLMArena`.
- Implemented loading environment variables from `.env` file in `cookies.py`.
- Updated default headers in `defaults.py` for user agent and `sec-ch-ua`.
- Cleaned up various model references in `any_model_map.py` to reflect differences in audio, vision, and other model types.
- Added a more centralized handling for API key management in `run_tools.py` to accommodate new nomenclature.
- Enhanced existing logic to allow for more granular loading and utilization of API keys from environment variables.
- In `PollinationsImage.py`, added a new parameter `media` of type `MediaListType` to the class method.
- Changed the default value of `aspect_ratio` in `PollinationsImage.py` from `"1:1"` to `None`.
- Updated the call to `_generate_image` in `PollinationsImage.py` to include the new `media` parameter.
- In `Local.py`, changed the `working` attribute from `True` to `has_requirements` and set `active_by_default` to `False`.
- In `Ollama.py`, set `active_by_default` to `False`.
- In `DeepSeekAPI.py`, set `active_by_default` to `has_dsk` and `needs_auth` to `True`.
- Modified the logic in `DeepSeekAPI.py` to yield `conversation` if `message_id` is present in the chunk.
- In `api.py`, added a new key `active_by_default` to the provider dictionary, determining its value based on `needs_auth`.
- In `types.py`, added a new attribute `active_by_default` to the `BaseProvider` class, initializing it to `None`.
- In `web_search.py`, added a type check for `prompt` to ensure it is a string before proceeding with the search logic.
- Added `--max-retries` argument to `parse_arguments()` in `commit.py` with default `MAX_RETRIES`
- Updated `generate_commit_message()` to accept a `max_retries` parameter and iterate accordingly
- Included check to raise immediately if `max_retries` is 1 within `generate_commit_message()`
- Passed `args.max_retries` when calling `generate_commit_message()` in `main()`
- In `g4f/Provider/har/__init__.py`, imported `ResponseError` and added check for network error to raise `ResponseError`
- In `g4f/Provider/hf_space/Qwen_Qwen_3.py`, changed default model string and updated system prompt handling to use `get_system_prompt()`
- In `g4f/Provider/needs_auth/LMArenaBeta.py`, modified callback to wait for cookie and turnstile response
- In `g4f/Provider/needs_auth/PuterJS.py`, adjusted `get_models()` to filter out certain models
- In `g4f/gui/server/api.py`, adjusted `get_model_data()` to handle models starting with "openrouter:"
- In `g4f/providers/any_provider.py`, imported and used `ResponseError`; added logic to process `model_aliases` with updated model name resolution
- Refined model name cleaning logic to handle additional patterns and replaced multiple regex patterns to better match version strings
- Updated list of providers `PROVIERS_LIST_1`, `PROVIERS_LIST_2`, `PROVIERS_LIST_3`, and their usage to include new providers and adjust filtering
- In `g4f/version.py`, added `get_git_version()` function, retrieved version with `git describe` command, instead of only relying on `get_github_version()`, increasing robustness
- Updated `PollinationsAI.py` to import `quote` and `ClientTimeout` from `aiohttp`.
- Added `MissingAuthError` to error imports in `PollinationsAI.py`.
- Included `AudioResponse` in response imports in `PollinationsAI.py`.
- Expanded `image_models` in `PollinationsAI` to include "turbo" and "gptimage".
- Changed the initialization of `image_models` to use `cls.image_models.copy()`.
- Introduced `download_media` parameter in the `_generate_image` method.
- Added a condition to set `n = 1` if the model is "gptimage".
- Renamed `get_image_url` to `get_url_with_seed` and modified its logic to return the URL for "gptimage".
- Updated the session creation in `_generate_image` to include a timeout.
- Enhanced error handling in the image fetching logic to yield `Reasoning` status.
- Modified the media handling in `save_response_media` to yield `AudioResponse` based on `download_media`.
- Updated `OpenAIFM.py` to include `quote` and `AudioResponse` imports.
- Added `styles` to the `OpenAIFM` class and created a method to group models.
- Introduced `download_media` parameter in the `synthesize` method of `OpenAIFM`.
- Updated the `create_app` function in `api/__init__.py` to check for `a2wsgi` availability.
- Removed unused file handling routes in `api/__init__.py`.
- Updated `secure_filename` function in `files.py` to handle encoding more robustly.
- Added `download_media` to the `RequestConfig` model in `stubs.py`.
- Updated imports to use format_media_prompt in g4f/Provider/ARTA.py, PollinationsAI.py, PollinationsImage.py, Websim.py, audio/OpenAIFM.py, hf_space/BlackForestLabs_Flux1Dev.py, hf_space/DeepseekAI_JanusPro7b.py, hf_space/G4F.py, hf_space/Microsoft_Phi_4_Multimodal.py, hf_space/StabilityAI_SD35Large.py, needs_auth/BingCreateImages.py, needs_auth/BlackboxPro.py, needs_auth/DeepInfra.py, needs_auth/Gemini.py, needs_auth/MicrosoftDesigner.py, needs_auth/OpenaiChat.py, needs_auth/hf/HuggingChat.py, needs_auth/hf/HuggingFaceInference.py, needs_auth/hf/HuggingFaceMedia.py, not_working/AllenAI.py, template/OpenaiTemplate.py, api.py, and gui/server/api.py
- Replaced calls to format_image_prompt with format_media_prompt in relevant locations
- Changed media prompt handling in various providers to ensure consistent usage of format_media_prompt
- Modified the __aenter__ and __aexit__ methods of requests/aiohttp.py to properly manage ClientSession lifecycle
- Changed the default value of `extra_body` from an empty dictionary to `None` in `ImageLabs` and `PollinationsAI` classes.
- Added a check to initialize `extra_body` to an empty dictionary if it is `None` in the `ImageLabs` class.
- Removed the `extra_image_models` list from the `PollinationsAI` class.
- Updated the way image models are combined in the `PollinationsAI` class to avoid duplicates.
- Changed the error handling for unsupported models from `ModelNotSupportedError` to `ModelNotFoundError` in multiple classes including `OpenaiChat`, `HuggingFaceAPI`, and `HuggingFaceInference`.
- Updated the `save_response_media` function to handle both string and bytes responses.
- Adjusted the handling of audio data in the `PollinationsAI` class to ensure proper processing of audio responses.
- Introduced a new provider class `LMArenaBeta` in `g4f/Provider/LMArenaBeta.py` with capabilities for text and image models.
- Updated `g4f/Provider/Cloudflare.py` to remove an unused import of `Cookies`.
- Modified `g4f/Provider/PollinationsAI.py` to change the condition for checking the action in the `next` command.
- Added a new provider `PuterJS` in `g4f/Provider/PuterJS.py` with various model handling and authentication logic.
- Removed the old `PuterJS` implementation from `g4f/Provider/not_working/PuterJS.py`.
- Updated `g4f/Provider/__init__.py` to include the new `LMArenaBeta` and `PuterJS` providers.
- Changed the label of `HarProvider` in `g4f/Provider/har/__init__.py` to "LMArena (Har)".
- Adjusted the model list in `g4f/Provider/openai/models.py` to ensure consistency in model definitions.
- Updated the API response handling in `g4f/providers/response.py` to calculate total tokens in the `Usage` class constructor.
- Modified g4f/providers/response.py to ensure format_images_markdown returns the result directly without additional flags in the 'format_images_markdown' function.
- Updated g4f/gui/server/api.py to add 'tempfiles' parameter with default empty list to '_create_response_stream' method.
- Changed or added code in API response handling to iterate over 'tempfiles' and attempt to remove each file after response completion, with exception handling (try-except block with logger.exception).
- Adjusted g4f/Tools/files.py to fix tempfile creation: corrected the 'suffix' parameter in 'get_tempfile' to use 'suffix' directly instead of splitting.
- In g4f/tools/media.py, changed 'render_part' function to handle 'text' key properly, checking 'part.get("text")' and returning a dictionary with 'type': 'text' and 'text': value, if present.
- Updated error handling in g4f/Provider/DDG.py to raise ResponseError instead of yield error strings
- Replaced yield statements with raises in g4f/Provider/DDG.py for HTTP and response errors
- Added response raising in g4f/Provider/DeepInfraChat.py for image upload responses
- Included model alias validation and error raising in g4f/Provider/hf/HuggingFaceMedia.py
- Corrected model alias dictionary key in g4f/Provider/hf_space/StabilityAI_SD35Large.py
- Ensured referrer parameter default value in g4f/Provider/PollinationsImage.py
- Removed duplicate imports and adjusted get_models method in g4f/Provider/har/__init__.py
- Modified g4f/gui/server/api.py to remove unused conversation parameter in _create_response_stream
- Fixed logic to handle single exception in g4f/providers/retry_provider.py
- Added missing import of JsonConversation in g4f/providers/retry_provider.py
- Corrected stream_read_files to replace extension in return string in g4f/tools/files.py
- Fixed duplicate model entries in Blackbox provider model_aliases
- Added meta-llama- to llama- name cleaning in Cloudflare provider
- Enhanced PollinationsAI provider with improved vision model detection
- Added reasoning support to PollinationsAI provider
- Fixed HuggingChat authentication to include headers and impersonate
- Removed unused max_inputs_length parameter from HuggingFaceAPI
- Renamed extra_data to extra_body for consistency across providers
- Added Puter provider with grouped model support
- Enhanced AnyProvider with grouped model display and better model organization
- Fixed model cleaning in AnyProvider to handle more model name variations
- Added api_key handling for HuggingFace providers in AnyProvider
- Added see_stream helper function to parse event streams
- Updated GUI server to handle JsonConversation properly
- Fixed aspect ratio handling in image generation functions
- Added ResponsesConfig and ClientResponse for new API endpoint
- Updated requirements to include markitdown
- Changed `DEFAULT_MODEL` from `"o1"` to `"gpt-4o"` in `etc/tool/commit.py`
- Replaced `FALLBACK_MODELS` list with an empty list in `etc/tool/commit.py`
- Moved spinner stop logic inside content-checking block in `generate_commit_message` in `etc/tool/commit.py`
- Trimmed trailing characters "` \n" from returned content in `generate_commit_message` in `etc/tool/commit.py`
- Wrapped cache check in `g4f/gui/server/api.py` in a `try` block to catch `RuntimeError`
- Ensured fallback to `version.utils.latest_version` if cache access fails in `g4f/gui/server/api.py
- Removed default `tool_calls` assignment from `Api.__call__` in `api.py`
- Removed `debug.error()` logging in two exception blocks in `api.py`
- Fixed malformed URL in `CohereForAI_C4AI_Command.url` by removing leading tab in `CohereForAI_C4AI_Command.py`
- Replaced incorrect `result.text_content` access with just `result` in `Backend_Api.upload_bucket` in `backend_api.py`
- Replaced `shutil.copyfile` with `os.rename`, and added fallback to `shutil.copyfile` on failure in `Backend_Api.upload_bucket` in `backend_api.py
- **g4f/Provider/har/__init__.py**
- `get_models`/`create_async`: iterate over `(domain, harFile)` and filter with `domain in request_url`
- `read_har_files` now yields `(domain, har_data)`; fixes file variable shadowing and uses `json.load`
- remove stray `print`, add type hint for `find_str`, replace manual loops with `yield from`
- small whitespace clean-up
- **g4f/Provider/needs_auth/Grok.py**
- `ImagePreview` now passes `auth_result.cookies` and `auth_result.headers`
- **g4f/Provider/needs_auth/OpenaiChat.py**
- add `Union` import; rename/refactor `get_generated_images` → `get_generated_image`
- support `file-service://` and `sediment://` pointers; choose correct download URL
- return `ImagePreview` or `ImageResponse` accordingly and stream each image part
- propagate 422 errors, update prompt assignment and image handling paths
- **g4f/client/__init__.py**
- drop unused `ignore_working` parameter in sync/async `Completions`
- normalise `media` argument: accept single tuple, infer filename when missing, fix index loop
- `Images.create_variation` updated to use the new media logic
- **g4f/gui/server/api.py**
- expose `latest_version_cached` via `?cache=` query parameter
- **g4f/gui/server/backend_api.py**
- optional Markdown extraction via `MarkItDown`; save rendered text as `<file>.md`
- upload flow rewrites: copy to temp file, move to bucket/media dir, clean temp, store filenames
- introduce `has_markitdown` guard and improved logging/exception handling
- **g4f/tools/files.py**
- remove trailing spaces in HAR code-block header string
- **g4f/version.py**
- add `latest_version_cached` `@cached_property` for memoised version lookup
* 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>
- Added "No auth / HAR file" authentication type in providers-and-models.md
- Added "Video generation" column to provider tables for future capability
- Updated model counts and provider capabilities throughout documentation
- Fixed ARTA provider with improved error handling and response validation
- Enhanced AllenAI provider with vision model support and proper image handling
- Significantly improved Blackbox provider:
- Added HAR file authentication support
- Added subscription status checking
- Added premium/demo model differentiation
- Improved session handling and error recovery
- Enhanced DDG provider with better error handling for challenges
- Improved PollinationsAI and PollinationsImage providers' model handling
- Added VideoModel class in g4f/models.py
- Added audio/video generation indicators in GUI components
- Added new Ai2 models: olmo-1-7b, olmo-2-32b, olmo-4-synthetic
- Added new commit message generation tool in etc/tool/commit.py
* New provider added(g4f/Provider/Websim.py)
* New provider added(g4f/Provider/Dynaspark.py)
* feat(g4f/gui/client/static/js/chat.v1.js): Enhance provider labeling for HuggingFace integrations
* feat(g4f/gui/server/api.py): add Hugging Face Space compatibility flag to provider data
* feat(g4f/models.py): add new providers and update model configurations
* Update g4f/Provider/__init__.py
* feat(g4f/Provider/AllenAI.py): expand model alias mappings for AllenAI provider
* feat(g4f/Provider/Blackbox.py): restructure image model handling and response processing
* feat(g4f/Provider/PollinationsAI.py): add new model aliases and streamline headers
* Update g4f/Provider/hf_space/*
* refactor(g4f/Provider/Copilot.py): update model alias mapping
* chore(g4f/models.py): update provider configurations for OpenAI models
* docs(docs/providers-and-models.md): update provider tables and model categorization
* fix(etc/examples/vision_images.py): update model and simplify client configuration
* fix(docs/providers-and-models.md): correct streaming status for GlhfChat provider
* docs(docs/providers-and-models.md): update provider capabilities and model documentation
* fix(models): update provider configurations for Mistral models
* fix(g4f/Provider/Blackbox.py): correct model alias key for Mistral variant
* feat(g4f/Provider/hf_space/CohereForAI_C4AI_Command.py): update supported model versions and aliases (close#2802)
* fix(documentation): correct model names and provider counts (https://github.com/xtekky/gpt4free/pull/2805#issuecomment-2727489835)
* fix(g4f/models.py): correct mistral model configurations
* fix(g4f/Provider/DeepInfraChat.py): correct mixtral-small alias key
* New provider added(g4f/Provider/LambdaChat.py)
* feat(g4f/models.py): add new providers and enhance model configurations
* docs(docs/providers-and-models.md): add LambdaChat provider and update model listings
* feat(g4f/models.py): add new Liquid AI model and enhance providers
* docs(docs/providers-and-models.md): update model listings and provider counts
* feat(g4f/Provider/LambdaChat.py): add conditional reasoning processing based on model
* fix(g4f/tools/run_tools.py): handle combined thinking tags in single chunk
* New provider added(g4f/Provider/Goabror.py)
* feat(g4f/Provider/Blackbox.py): implement dynamic session management and model access control
* refactor(g4f/models.py): update provider configurations and model entries
* docs(docs/providers-and-models.md): update model listings and provider counts
---------
Co-authored-by: kqlio67 <>
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
