mirrors/gpt4free
1
Fork 0
mirror of https://github.com/xtekky/gpt4free.git synced 2025-12-06 02:30:41 -08:00
Code Issues Projects Releases Packages Wiki Activity

Standardize model configurations and enhance error handling (#2818)

Browse source 
* feat(docs/providers-and-models.md): add TypeGPT provider and update model support

* feat(g4f/models.py): add TypeGPT provider and enhance model configurations

* refactor(g4f/Provider/hf_space/BlackForestLabs_Flux1Dev.py): update model aliases and image models definition

* refactor(g4f/Provider/hf_space/BlackForestLabs_Flux1Schnell.py): adjust model configuration and aliases

* refactor(g4f/Provider/hf_space/CohereForAI_C4AI_Command.py): update model configuration and aliases

* refactor(g4f/Provider/hf_space/DeepseekAI_JanusPro7b.py): reorganize model classification attributes

* feat(g4f/Provider/hf_space/Microsoft_Phi_4.py): add model aliases and update vision model handling

* refactor(g4f/Provider/hf_space/Qwen_QVQ_72B.py): restructure model configuration and aliases

* feat(g4f/Provider/hf_space/Qwen_Qwen_2_5M_Demo.py): add model alias support for Qwen provider

* refactor(g4f/Provider/hf_space/Qwen_Qwen_2_72B_Instruct.py): derive model list from aliases

* refactor(g4f/Provider/hf_space/StabilityAI_SD35Large.py): adjust model list definitions using aliases

* fix(g4f/Provider/hf_space/Voodoohop_Flux1Schnell.py): correct image_models definition in Voodoohop provider

* feat(g4f/Provider/DDG.py): enhance request handling and error recovery

* feat(g4f/Provider/DeepInfraChat.py): update model configurations and request handling

* feat(g4f/Provider/TypeGPT.py): enhance TypeGPT API client with media support and async capabilities

* refactor(docs/providers-and-models.md): remove streaming column from provider tables

* Update docs/providers-and-models.md

* added(g4f/Provider/hf_space/Qwen_Qwen_2_5_Max.py): new provider

* Update g4f/Provider/hf_space/Qwen_Qwen_2_72B_Instruct.py

* added(g4f/Provider/hf_space/Qwen_Qwen_2_5.py): new provider

* Update g4f/Provider/DeepInfraChat.py g4f/Provider/TypeGPT.py

* Update g4f/Provider/LambdaChat.py

* Update g4f/Provider/DDG.py

* Update g4f/Provider/DeepInfraChat.py

* Update g4f/Provider/TypeGPT.py

* Add audio generation model and update documentation

* Update providers-and-models documentation and include ARTA in flux best providers

* Update ARTA provider details and adjust documentation for image models

* Remove redundant text_models assignment in LambdaChat provider

---------

Co-authored-by: kqlio67 <>
This commit is contained in:
kqlio67 2025-03-22 09:49:25 +00:00 • committed by GitHub
parent 3cbcbe1047
commit 97f1964bb6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
20 changed files with 657 additions and 274 deletions
Download patch file Download diff file Expand all files Collapse all files

203
docs/providers-and-models.md
View file

@ -1,13 +1,9 @@
# G4F - Providers and Models # G4F - Providers and Models
This document provides an overview of various AI providers and models, including text generation, image generation, and vision capabilities. It aims to help users navigate the diverse landscape of AI services and choose the most suitable option for their needs. This document provides an overview of various AI providers and models, including text generation, image generation, and vision capabilities. It aims to help users navigate the diverse landscape of AI services and choose the most suitable option for their needs.
> **Note**: See our [Authentication Guide](authentication.md) for authentication instructions for the provider. > **Note**: See our [Authentication Guide](authentication.md) for authentication instructions for the provider.
## Table of Contents ## Table of Contents
- [Providers](#providers) - [Providers](#providers)
- [No auth required](#providers-not-needs-auth) - [No auth required](#providers-not-needs-auth)
@ -38,106 +34,108 @@ This document provides an overview of various AI providers and models, including
--- ---
### Providers No auth required ### Providers No auth required
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Streaming | Status | | Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Status |
|----------|-------------|--------------|---------------|--------|--------|------|------|------| |----------|-------------|--------------|---------------|--------|--------|------|------|
|[playground.allenai.org](https://playground.allenai.org)|No auth required|`g4f.Provider.AllenAI`|`tulu-3-405b, olmo-2-13b, tulu-3-1-8b, tulu-3-70b, olmoe-0125`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[playground.allenai.org](https://playground.allenai.org)|No auth required|`g4f.Provider.AllenAI`|`tulu-3-405b, olmo-2-13b, tulu-3-1-8b, tulu-3-70b, olmoe-0125`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[ai-arta.com](https://ai-arta.com)|No auth required|`g4f.Provider.ARTA`|❌|✔ _**(17+)**_|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)| |[ai-arta.com](https://ai-arta.com)|No auth required|`g4f.Provider.ARTA`|❌|✔ _**(17+)**_|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[blackbox.ai](https://www.blackbox.ai)|No auth required|`g4f.Provider.Blackbox`|`blackboxai, gpt-4o-mini, deepseek-chat, deepseek-v3, deepseek-r1, gpt-4o, o1, o3-mini, claude-3.7-sonnet` _**(40+)**_|`flux`|❌|`blackboxai, gpt-4o, o1, o3-mini, deepseek-v3` _**(7+)**_|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[blackbox.ai](https://www.blackbox.ai)|No auth required|`g4f.Provider.Blackbox`|`blackboxai, gpt-4o-mini, deepseek-chat, deepseek-v3, deepseek-r1, gpt-4o, o1, o3-mini, claude-3.7-sonnet` _**(40+)**_|`flux`|❌|`blackboxai, gpt-4o, o1, o3-mini, deepseek-v3` _**(7+)**_|![](https://img.shields.io/badge/Active-brightgreen)|
|[chatglm.cn](https://chatglm.cn)|No auth required|`g4f.Provider.ChatGLM`|`glm-4`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[chatglm.cn](https://chatglm.cn)|No auth required|`g4f.Provider.ChatGLM`|`glm-4`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[chatgpt.com](https://chatgpt.com)|No auth required|`g4f.Provider.ChatGpt`|✔ _**(7+)**_|❌|❌|❌|✔|![Error](https://img.shields.io/badge/HTTPError-f48d37)| |[chatgpt.com](https://chatgpt.com)|No auth required|`g4f.Provider.ChatGpt`|✔ _**(7+)**_|❌|❌|❌|![Error](https://img.shields.io/badge/HTTPError-f48d37)|
|[chatgpt.es](https://chatgpt.es)|No auth required|`g4f.Provider.ChatGptEs`|`gpt-4, gpt-4o, gpt-4o-mini`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[chatgpt.es](https://chatgpt.es)|No auth required|`g4f.Provider.ChatGptEs`|`gpt-4, gpt-4o, gpt-4o-mini`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[playground.ai.cloudflare.com](https://playground.ai.cloudflare.com)|[Automatic cookies](https://playground.ai.cloudflare.com)|`g4f.Provider.Cloudflare`|`llama-2-7b, llama-3-8b, llama-3.1-8b, llama-3.2-1b, qwen-1.5-7b`|❌|❌|❌|✔|![Error](https://img.shields.io/badge/Active-brightgreen)|❌| |[playground.ai.cloudflare.com](https://playground.ai.cloudflare.com)|[Automatic cookies](https://playground.ai.cloudflare.com)|`g4f.Provider.Cloudflare`|`llama-2-7b, llama-3-8b, llama-3.1-8b, llama-3.2-1b, qwen-1.5-7b`|❌|❌|❌|![Error](https://img.shields.io/badge/Active-brightgreen)|
|[copilot.microsoft.com](https://copilot.microsoft.com)|Optional API key|`g4f.Provider.Copilot`|`gpt-4, o1`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[copilot.microsoft.com](https://copilot.microsoft.com)|Optional API key|`g4f.Provider.Copilot`|`gpt-4, o1`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[duckduckgo.com/aichat](https://duckduckgo.com/aichat)|No auth required|`g4f.Provider.DDG`|`gpt-4, gpt-4o-mini, llama-3.3-70b, claude-3-haiku, o3-mini, mixtral-small-24b`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[duckduckgo.com/aichat](https://duckduckgo.com/aichat)|No auth required|`g4f.Provider.DDG`|`gpt-4, gpt-4o-mini, llama-3.3-70b, claude-3-haiku, o3-mini, mixtral-small-24b`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[deepinfra.com/chat](https://deepinfra.com/chat)|No auth required|`g4f.Provider.DeepInfraChat`|`llama-3.1-8b, llama-3.2-90b, llama-3.3-70b, deepseek-v3, mixtral-small-24b, deepseek-r1, phi-4, wizardlm-2-8x22b, qwen-2.5-72b, yi-34b, qwen-2-72b, dolphin-2.6, dolphin-2.9, dbrx-instruct, airoboros-70b, lzlv-70b, wizardlm-2-7b, mixtral-8x22b, minicpm-2.5`|❌|❌|`llama-3.2-90b, minicpm-2.5`|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[deepinfra.com/chat](https://deepinfra.com/chat)|No auth required|`g4f.Provider.DeepInfraChat`|`llama-3.1-8b, llama-3.2-90b, llama-3.3-70b, deepseek-v3, mixtral-small-24b, deepseek-r1, phi-4, wizardlm-2-8x22b, qwen-2.5-72b, yi-34b, qwen-2-72b, dolphin-2.6, dolphin-2.9, dbrx-instruct, airoboros-70b, lzlv-70b, wizardlm-2-7b, mixtral-8x22b, minicpm-2.5`|❌|❌|`llama-3.2-90b, minicpm-2.5`|![](https://img.shields.io/badge/Active-brightgreen)|
|[dynaspark.onrender.com](https://dynaspark.onrender.com)|No auth required|`g4f.Provider.Dynaspark`|`gemini-1.5-flash, gemini-2.0-flash`|❌|❌|`gemini-1.5-flash, gemini-2.0-flash`|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[dynaspark.onrender.com](https://dynaspark.onrender.com)|No auth required|`g4f.Provider.Dynaspark`|`gemini-1.5-flash, gemini-2.0-flash`|❌|❌|`gemini-1.5-flash, gemini-2.0-flash`|![](https://img.shields.io/badge/Active-brightgreen)|
|[chat10.free2gpt.xyz](https://chat10.free2gpt.xyz)|No auth required|`g4f.Provider.Free2GPT`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[chat10.free2gpt.xyz](https://chat10.free2gpt.xyz)|No auth required|`g4f.Provider.Free2GPT`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[freegptsnav.aifree.site](https://freegptsnav.aifree.site)|No auth required|`g4f.Provider.FreeGpt`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[freegptsnav.aifree.site](https://freegptsnav.aifree.site)|No auth required|`g4f.Provider.FreeGpt`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[app.giz.ai/assistant](https://app.giz.ai/assistant)|No auth required|`g4f.Provider.GizAI`|`gemini-1.5-flash`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[app.giz.ai/assistant](https://app.giz.ai/assistant)|No auth required|`g4f.Provider.GizAI`|`gemini-1.5-flash`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[glider.so](https://glider.so)|No auth required|`g4f.Provider.Glider`|`llama-3.1-70b, llama-3.1-8b, llama-3.2-3b, deepseek-r1`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[glider.so](https://glider.so)|No auth required|`g4f.Provider.Glider`|`llama-3.1-70b, llama-3.1-8b, llama-3.2-3b, deepseek-r1`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[goabror.uz](https://goabror.uz)|No auth required|`g4f.Provider.Goabror`|`gpt-4`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[goabror.uz](https://goabror.uz)|No auth required|`g4f.Provider.Goabror`|`gpt-4`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[hailuo.ai](https://www.hailuo.ai)|No auth required|`g4f.Provider.HailuoAI`|`MiniMax` _**(1+)**_|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[hailuo.ai](https://www.hailuo.ai)|No auth required|`g4f.Provider.HailuoAI`|`MiniMax` _**(1+)**_|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[editor.imagelabs.net](editor.imagelabs.net)|No auth required|`g4f.Provider.ImageLabs`|❌|`sdxl-turbo`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[editor.imagelabs.net](editor.imagelabs.net)|No auth required|`g4f.Provider.ImageLabs`|❌|`sdxl-turbo`|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[huggingface.co/spaces](https://huggingface.co/spaces)|Optional API key|`g4f.Provider.HuggingSpace`|`qvq-72b, qwen-2-72b, command-r, command-r-plus, command-r7b, command-a`|`flux-dev, flux-schnell, sd-3.5`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[huggingface.co/spaces](https://huggingface.co/spaces)|Optional API key|`g4f.Provider.HuggingSpace`|`qvq-72b, qwen-2-72b, command-r, command-r-plus, command-r7b, command-a`|`flux-dev, flux-schnell, sd-3.5`|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[jmuz.me](https://jmuz.me)|Optional API key|`g4f.Provider.Jmuz`|`claude-3-haiku, claude-3-opus, claude-3.5-sonnet, deepseek-r1, deepseek-chat, gemini-exp, gemini-1.5-flash, gemini-1.5-pro, gemini-2.0-flash-thinking, gpt-4, gpt-4o, gpt-4o-mini, llama-3-70b, llama-3-8b, llama-3.1-405b, llama-3.1-70b, llama-3.1-8b, llama-3.2-11b, llama-3.2-90b, llama-3.3-70b, mixtral-8x7b, qwen-2.5-72b, qwen-2.5-coder-32b, qwq-32b, wizardlm-2-8x22b`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[jmuz.me](https://jmuz.me)|Optional API key|`g4f.Provider.Jmuz`|`claude-3-haiku, claude-3-opus, claude-3.5-sonnet, deepseek-r1, deepseek-chat, gemini-exp, gemini-1.5-flash, gemini-1.5-pro, gemini-2.0-flash-thinking, gpt-4, gpt-4o, gpt-4o-mini, llama-3-70b, llama-3-8b, llama-3.1-405b, llama-3.1-70b, llama-3.1-8b, llama-3.2-11b, llama-3.2-90b, llama-3.3-70b, mixtral-8x7b, qwen-2.5-72b, qwen-2.5-coder-32b, qwq-32b, wizardlm-2-8x22b`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[lambda.chat](https://lambda.chat)|No auth required|`g4f.Provider.LambdaChat`|`deepseek-v3, deepseek-r1, hermes-3, nemotron-70b, llama-3.3-70b`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[lambda.chat](https://lambda.chat)|No auth required|`g4f.Provider.LambdaChat`|`deepseek-v3, deepseek-r1, hermes-3, nemotron-70b, llama-3.3-70b`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[liaobots.work](https://liaobots.work)|[Automatic cookies](https://liaobots.work)|`g4f.Provider.Liaobots`|`claude-3.5-sonnet, claude-3.7-sonnet, claude-3.7-sonnet-thinking, claude-3-opus, claude-3-sonnet, deepseek-r1, deepseek-v3, gemini-2.0-flash, gemini-2.0-flash-thinking, gemini-2.0-pro, gpt-4, gpt-4o, gpt-4o-mini, grok-3, grok-3-r1, o3-mini`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[liaobots.work](https://liaobots.work)|[Automatic cookies](https://liaobots.work)|`g4f.Provider.Liaobots`|`claude-3.5-sonnet, claude-3.7-sonnet, claude-3.7-sonnet-thinking, claude-3-opus, claude-3-sonnet, deepseek-r1, deepseek-v3, gemini-2.0-flash, gemini-2.0-flash-thinking, gemini-2.0-pro, gpt-4, gpt-4o, gpt-4o-mini, grok-3, grok-3-r1, o3-mini`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[oi-vscode-server.onrender.com](https://oi-vscode-server.onrender.com)|No auth required|`g4f.Provider.OIVSCode`|`gpt-4o-mini, deepseek-v3`|❌|❌|`gpt-4o-mini`|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[oi-vscode-server.onrender.com](https://oi-vscode-server.onrender.com)|No auth required|`g4f.Provider.OIVSCode`|`gpt-4o-mini, deepseek-v3`|❌|❌|`gpt-4o-mini`|![](https://img.shields.io/badge/Active-brightgreen)|
|[labs.perplexity.ai](https://labs.perplexity.ai)|No auth required|`g4f.Provider.PerplexityLabs`|`sonar, sonar-pro, sonar-reasoning, sonar-reasoning-pro`|❌|❌|❌|✔|![Error](https://img.shields.io/badge/Active-brightgreen)| |[labs.perplexity.ai](https://labs.perplexity.ai)|No auth required|`g4f.Provider.PerplexityLabs`|`sonar, sonar-pro, sonar-reasoning, sonar-reasoning-pro`|❌|❌|❌|![Error](https://img.shields.io/badge/Active-brightgreen)|
|[pi.ai/talk](https://pi.ai/talk)|[Manual cookies](https://pi.ai/talk)|`g4f.Provider.Pi`|`pi`|❌|❌|❌|✔|![Error](https://img.shields.io/badge/Active-brightgreen)| |[pi.ai/talk](https://pi.ai/talk)|[Manual cookies](https://pi.ai/talk)|`g4f.Provider.Pi`|`pi`|❌|❌|❌|![Error](https://img.shields.io/badge/Active-brightgreen)|
|[pizzagpt.it](https://www.pizzagpt.it)|No auth required|`g4f.Provider.Pizzagpt`|`gpt-4o-mini`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[pizzagpt.it](https://www.pizzagpt.it)|No auth required|`g4f.Provider.Pizzagpt`|`gpt-4o-mini`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[pollinations.ai](https://pollinations.ai)|No auth required|`g4f.Provider.PollinationsAI`|`gpt-4o-mini, gpt-4o, o1-mini, qwen-2.5-coder-32b, llama-3.3-70b, mistral-nemo, llama-3.1-8b, deepseek-r1, phi-4` _**(9+)**_|`flux, flux-pro, flux-dev, flux-schnell, dall-e-3, sdxl-turbo`|✔ _**(1+)**_|`gpt-4o, gpt-4o-mini, o1-mini, o3-mini`|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[pollinations.ai](https://pollinations.ai)|No auth required|`g4f.Provider.PollinationsAI`|`gpt-4o-mini, gpt-4o, o1-mini, qwen-2.5-coder-32b, llama-3.3-70b, mistral-nemo, llama-3.1-8b, deepseek-r1, phi-4` _**(9+)**_|`flux, flux-pro, flux-dev, flux-schnell, dall-e-3, sdxl-turbo`|`gpt-4o-audio`|`gpt-4o, gpt-4o-mini, o1-mini, o3-mini`|![](https://img.shields.io/badge/Active-brightgreen)|
|[pollinations.ai](https://pollinations.ai)|No auth required|`g4f.Provider.PollinationsImage`|❌|`flux, flux-pro, flux-dev, flux-schnell, dall-e-3, sdxl-turbo`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[pollinations.ai](https://pollinations.ai)|No auth required|`g4f.Provider.PollinationsImage`|❌|`flux, flux-pro, flux-dev, flux-schnell, dall-e-3, sdxl-turbo`|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[teach-anything.com](https://www.teach-anything.com)|No auth required|`g4f.Provider.TeachAnything`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[teach-anything.com](https://www.teach-anything.com)|No auth required|`g4f.Provider.TeachAnything`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[you.com](https://you.com)|[Manual cookies](https://you.com)|`g4f.Provider.You`|✔|✔|❌|✔|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[chat.typegpt.net](https://chat.typegpt.net)|No auth required|`g4f.Provider.TypeGPT`|`gpt-3.5-turbo, o3-mini, deepseek-r1, deepseek-v3, evil, o1`|❌|❌|`gpt-3.5-turbo, o3-mini`|![](https://img.shields.io/badge/Active-brightgreen)|
|[websim.ai](https://websim.ai)|No auth required|`g4f.Provider.Websim`|`gemini-1.5-pro, gemini-1.5-flash`|`flux`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[you.com](https://you.com)|[Manual cookies](https://you.com)|`g4f.Provider.You`|✔|✔|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|
|[chat9.yqcloud.top](https://chat9.yqcloud.top)|No auth required|`g4f.Provider.Yqcloud`|`gpt-4`|✔|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[websim.ai](https://websim.ai)|No auth required|`g4f.Provider.Websim`|`gemini-1.5-pro, gemini-1.5-flash`|`flux`|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[chat9.yqcloud.top](https://chat9.yqcloud.top)|No auth required|`g4f.Provider.Yqcloud`|`gpt-4`|✔|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
--- ---
### Providers HuggingFace ### Providers HuggingFace
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Streaming | Status | | Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Status |
|----------|-------------|--------------|---------------|--------|--------|------|------|------| |----------|-------------|--------------|---------------|--------|--------|------|------|
|[huggingface.co/chat](https://huggingface.co/chat)|[Manual cookies](https://huggingface.co/chat)|`g4f.Provider.HuggingChat`|`qwen-2.5-72b, llama-3.3-70b, command-r-plus, deepseek-r1, qwq-32b, nemotron-70b, llama-3.2-11b, mistral-nemo, phi-3.5-mini`|`flux-dev, flux-schnell`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[huggingface.co/chat](https://huggingface.co/chat)|[Manual cookies](https://huggingface.co/chat)|`g4f.Provider.HuggingChat`|`qwen-2.5-72b, llama-3.3-70b, command-r-plus, deepseek-r1, qwq-32b, nemotron-70b, llama-3.2-11b, mistral-nemo, phi-3.5-mini`|`flux-dev, flux-schnell`|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[huggingface.co/chat](https://huggingface.co/chat)|[API key / Cookies](https://huggingface.co/settings/tokens)|`g4f.Provider.HuggingFace`|✔ _**(47+)**_|✔ _**(9+)**_|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[huggingface.co/chat](https://huggingface.co/chat)|[API key / Cookies](https://huggingface.co/settings/tokens)|`g4f.Provider.HuggingFace`|✔ _**(47+)**_|✔ _**(9+)**_|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[api-inference.huggingface.co](https://api-inference.huggingface.co)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.HuggingFaceAPI`|✔ _**(9+)**_|✔ _**(2+)**_|❌|✔ _**(1+)**_|❌|![](https://img.shields.io/badge/Active-brightgreen)|✔| |[api-inference.huggingface.co](https://api-inference.huggingface.co)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.HuggingFaceAPI`|✔ _**(9+)**_|✔ _**(2+)**_|❌|✔ _**(1+)**_|![](https://img.shields.io/badge/Active-brightgreen)|
--- ---
### Providers HuggingSpace ### Providers HuggingSpace
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Streaming | Status | | Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Status |
|----------|-------------|--------------|---------------|--------|--------|------|------|------| |----------|-------------|--------------|---------------|--------|--------|------|------|
|[black-forest-labs-flux-1-dev.hf.space](https://black-forest-labs-flux-1-dev.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.BlackForestLabs_Flux1Dev`|❌|`flux-dev`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[black-forest-labs-flux-1-dev.hf.space](https://black-forest-labs-flux-1-dev.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.BlackForestLabs_Flux1Dev`|❌|`flux, flux-dev`|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[black-forest-labs-flux-1-schnell.hf.space](https://black-forest-labs-flux-1-schnell.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.BlackForestLabs_Flux1Schnell`|❌|`flux-schnell`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[black-forest-labs-flux-1-schnell.hf.space](https://black-forest-labs-flux-1-schnell.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.BlackForestLabs_Flux1Schnell`|❌|`flux, flux-schnell`|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[cohereforai-c4ai-command.hf.space](https://cohereforai-c4ai-command.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.CohereForAI_C4AI_Command`|`command-r, command-r-plus, command-r7b`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[cohereforai-c4ai-command.hf.space](https://cohereforai-c4ai-command.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.CohereForAI_C4AI_Command`|`command-r, command-r-plus, command-r7b`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[huggingface.co/spaces/deepseek-ai/Janus-Pro-7B](https://huggingface.co/spaces/deepseek-ai/Janus-Pro-7B)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.DeepseekAI_Janus_Pro_7b`|✔|✔|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[huggingface.co/spaces/deepseek-ai/Janus-Pro-7B](https://huggingface.co/spaces/deepseek-ai/Janus-Pro-7B)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.DeepseekAI_Janus_Pro_7b`|✔|✔|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[roxky-flux-1-dev.hf.space](https://roxky-flux-1-dev.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.G4F`|✔ _**(1+)**_|✔ _**(4+)**_|❌|✔ _**(1+)**_|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[roxky-flux-1-dev.hf.space](https://roxky-flux-1-dev.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.G4F`|✔ _**(1+)**_|✔ _**(4+)**_|❌|✔ _**(1+)**_|![](https://img.shields.io/badge/Active-brightgreen)|
|[microsoft-phi-4-multimodal.hf.space](https://microsoft-phi-4-multimodal.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.Microsoft_Phi_4`|✔ _**(1+)**_|❌|❌|✔ _**(1+)**_|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[microsoft-phi-4-multimodal.hf.space](https://microsoft-phi-4-multimodal.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.Microsoft_Phi_4`|`phi-4`|❌|❌|`phi-4`|![](https://img.shields.io/badge/Active-brightgreen)|
|[qwen-qvq-72b-preview.hf.space](https://qwen-qvq-72b-preview.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.Qwen_QVQ_72B`|`qvq-72b`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[qwen-qvq-72b-preview.hf.space](https://qwen-qvq-72b-preview.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.Qwen_QVQ_72B`|`qvq-72b`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[qwen-qwen2-5-1m-demo.hf.space](https://qwen-qwen2-5-1m-demo.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.Qwen_Qwen_2_5M_Demo`|`qwen-2.5-1m-demo`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[qwen-qwen2-5.hf.space](https://qwen-qwen2-5.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.Qwen_Qwen_2_5`|`qwen-2.5`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[qwen-qwen2-72b-instruct.hf.space](https://qwen-qwen2-72b-instruct.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.Qwen_Qwen_2_72B_Instruct`|`qwen-2-72b`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[qwen-qwen2-5-1m-demo.hf.space](https://qwen-qwen2-5-1m-demo.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.Qwen_Qwen_2_5M`|`qwen-2.5-1m`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[stabilityai-stable-diffusion-3-5-large.hf.space](https://stabilityai-stable-diffusion-3-5-large.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.StabilityAI_SD35Large`|❌|`sd-3.5`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[qwen-qwen2-5-max-demo.hf.space](https://qwen-qwen2-5-max-demo.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.Qwen_Qwen_2_5_Max`|`qwen-2-5-max`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[voodoohop-flux-1-schnell.hf.space](https://voodoohop-flux-1-schnell.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.Voodoohop_Flux1Schnell`|❌|`flux-schnell`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[qwen-qwen2-72b-instruct.hf.space](https://qwen-qwen2-72b-instruct.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.Qwen_Qwen_2_72B`|`qwen-2-72b`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[stabilityai-stable-diffusion-3-5-large.hf.space](https://stabilityai-stable-diffusion-3-5-large.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.StabilityAI_SD35Large`|❌|`sd-3.5`|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[voodoohop-flux-1-schnell.hf.space](https://voodoohop-flux-1-schnell.hf.space)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.Voodoohop_Flux1Schnell`|❌|`flux, flux-schnell`|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
### Providers Local ### Providers Local
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Streaming | Status | | Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Status |
|----------|-------------|--------------|---------------|--------|--------|------|------|------| |----------|-------------|--------------|---------------|--------|--------|------|------|
|[]( )|No auth required|`g4f.Provider.Local`|✔|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[]( )|No auth required|`g4f.Provider.Local`|✔|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[ollama.com](https://ollama.com)|No auth required|`g4f.Provider.Ollama`|✔|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[ollama.com](https://ollama.com)|No auth required|`g4f.Provider.Ollama`|✔|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
--- ---
### Providers MiniMax ### Providers MiniMax
| Website | API Credentials | Provider | Text generation | Image generation| Audio generation | Vision (Image Upload) | Stream | Status | | Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Status |
|----------|-------------|--------------|---------------|--------|--------|------|------|------| |----------|-------------|--------------|---------------|--------|--------|------|------|
|[hailuo.ai/chat](https://www.hailuo.ai/chat)|[Get API key](https://intl.minimaxi.com/user-center/basic-information/interface-key)|`g4f.Provider.MiniMax`|`MiniMax` _**(1)**_|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[hailuo.ai/chat](https://www.hailuo.ai/chat)|[Get API key](https://intl.minimaxi.com/user-center/basic-information/interface-key)|`g4f.Provider.MiniMax`|`MiniMax` _**(1+)**_|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
--- ---
### Providers Needs Auth ### Providers Needs Auth
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Streaming | Status | | Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Status |
|----------|-------------|--------------|---------------|--------|--------|------|------|------| |----------|-------------|--------------|---------------|--------|--------|------|------|
|[console.anthropic.com](https://console.anthropic.com)|[Get API key](https://console.anthropic.com/settings/keys)|`g4f.Provider.Anthropic`|✔ _**(8+)**_|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[console.anthropic.com](https://console.anthropic.com)|[Get API key](https://console.anthropic.com/settings/keys)|`g4f.Provider.Anthropic`|✔ _**(8+)**_|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[bing.com/images/create](https://www.bing.com/images/create)|[Manual cookies](https://www.bing.com)|`g4f.Provider.BingCreateImages`|❌|`dall-e-3`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)| |[bing.com/images/create](https://www.bing.com/images/create)|[Manual cookies](https://www.bing.com)|`g4f.Provider.BingCreateImages`|❌|`dall-e-3`|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[cablyai.com/chat](https://cablyai.com/chat)|[Get API key](https://cablyai.com)|`g4f.Provider.CablyAI`|✔|✔|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[cablyai.com/chat](https://cablyai.com/chat)|[Get API key](https://cablyai.com)|`g4f.Provider.CablyAI`|✔|✔|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|
|[inference.cerebras.ai](https://inference.cerebras.ai/)|[Get API key](https://cloud.cerebras.ai)|`g4f.Provider.Cerebras`|✔ _**(3+)**_|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[inference.cerebras.ai](https://inference.cerebras.ai/)|[Get API key](https://cloud.cerebras.ai)|`g4f.Provider.Cerebras`|✔ _**(3+)**_|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[copilot.microsoft.com](https://copilot.microsoft.com)|[Manual cookies](https://copilot.microsoft.com)|`g4f.Provider.CopilotAccount`|✔ _**(1+)**_|✔ _**(1+)**_|❌|✔ _**(1+)**_|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[copilot.microsoft.com](https://copilot.microsoft.com)|[Manual cookies](https://copilot.microsoft.com)|`g4f.Provider.CopilotAccount`|✔ _**(1+)**_|✔ _**(1+)**_|❌|✔ _**(1+)**_|![](https://img.shields.io/badge/Active-brightgreen)|
|[deepinfra.com](https://deepinfra.com)|[Get API key](https://deepinfra.com/dash/api_keys)|`g4f.Provider.DeepInfra`|✔ _**(17+)**_|✔ _**(6+)**_|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[deepinfra.com](https://deepinfra.com)|[Get API key](https://deepinfra.com/dash/api_keys)|`g4f.Provider.DeepInfra`|✔ _**(17+)**_|✔ _**(6+)**_|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[platform.deepseek.com](https://platform.deepseek.com)|[Get API key](https://platform.deepseek.com/api_keys)|`g4f.Provider.DeepSeek`|✔ _**(1+)**_|❌|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)| |[platform.deepseek.com](https://platform.deepseek.com)|[Get API key](https://platform.deepseek.com/api_keys)|`g4f.Provider.DeepSeek`|✔ _**(1+)**_|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[gemini.google.com](https://gemini.google.com)|[Manual cookies](https://gemini.google.com)|`g4f.Provider.Gemini`|`gemini-2.0`|`gemini-2.0`|❌|`gemini-2.0`|❌|![](https://img.shields.io/badge/Active-brightgreen)| |[gemini.google.com](https://gemini.google.com)|[Manual cookies](https://gemini.google.com)|`g4f.Provider.Gemini`|`gemini-2.0`|`gemini-2.0`|❌|`gemini-2.0`|![](https://img.shields.io/badge/Active-brightgreen)|
|[ai.google.dev](https://ai.google.dev)|[Get API key](https://aistudio.google.com/u/0/apikey)|`g4f.Provider.GeminiPro`|`gemini-1.5-flash, gemini-1.5-pro, gemini-2.0-flash`|❌|❌|`gemini-1.5-pro`|❌|![](https://img.shields.io/badge/Active-brightgreen)| |[ai.google.dev](https://ai.google.dev)|[Get API key](https://aistudio.google.com/u/0/apikey)|`g4f.Provider.GeminiPro`|`gemini-1.5-flash, gemini-1.5-pro, gemini-2.0-flash`|❌|❌|`gemini-1.5-pro`|![](https://img.shields.io/badge/Active-brightgreen)|
|[developers.sber.ru/gigachat](https://developers.sber.ru/gigachat)|[Manual cookies](https://developers.sber.ru/gigachat)|`g4f.Provider.GigaChat`|✔ _**(3+)**_|❌|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)| |[developers.sber.ru/gigachat](https://developers.sber.ru/gigachat)|[Manual cookies](https://developers.sber.ru/gigachat)|`g4f.Provider.GigaChat`|✔ _**(3+)**_|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[github.com/copilot](https://github.com/copilot)|[Manual cookies](https://github.com/copilot)|`g4f.Provider.GithubCopilot`|✔ _**(4+)**_|❌|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)| |[github.com/copilot](https://github.com/copilot)|[Manual cookies](https://github.com/copilot)|`g4f.Provider.GithubCopilot`|✔ _**(4+)**_|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[glhf.chat](https://glhf.chat)|[Get API key](https://glhf.chat/user-settings/api)|`g4f.Provider.GlhfChat`|✔ _**(22+)**_|❌|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)| |[glhf.chat](https://glhf.chat)|[Get API key](https://glhf.chat/user-settings/api)|`g4f.Provider.GlhfChat`|✔ _**(22+)**_|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[console.groq.com/playground](https://console.groq.com/playground)|[Get API key](https://console.groq.com/keys)|`g4f.Provider.Groq`|✔ _**(18+)**_|❌|❌|✔|❌|![](https://img.shields.io/badge/Active-brightgreen)| |[console.groq.com/playground](https://console.groq.com/playground)|[Get API key](https://console.groq.com/keys)|`g4f.Provider.Groq`|✔ _**(18+)**_|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|
|[meta.ai](https://www.meta.ai)|[Manual cookies](https://www.meta.ai)|`g4f.Provider.MetaAI`|`meta-ai`|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|✔| |[meta.ai](https://www.meta.ai)|[Manual cookies](https://www.meta.ai)|`g4f.Provider.MetaAI`|`meta-ai`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[meta.ai](https://www.meta.ai)|[Manual cookies](https://www.meta.ai)|`g4f.Provider.MetaAIAccount`|❌|`meta-ai`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[meta.ai](https://www.meta.ai)|[Manual cookies](https://www.meta.ai)|`g4f.Provider.MetaAIAccount`|❌|`meta-ai`|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[designer.microsoft.com](https://designer.microsoft.com)|[Manual cookies](https://designer.microsoft.com)|`g4f.Provider.MicrosoftDesigner`|❌|`dall-e-3`|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)| |[designer.microsoft.com](https://designer.microsoft.com)|[Manual cookies](https://designer.microsoft.com)|`g4f.Provider.MicrosoftDesigner`|❌|`dall-e-3`|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[platform.openai.com](https://platform.openai.com)|[Get API key](https://platform.openai.com/settings/organization/api-keys)|`g4f.Provider.OpenaiAPI`|✔|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[platform.openai.com](https://platform.openai.com)|[Get API key](https://platform.openai.com/settings/organization/api-keys)|`g4f.Provider.OpenaiAPI`|✔|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[chatgpt.com](https://chatgpt.com)|[Manual cookies](https://chatgpt.com)|`g4f.Provider.OpenaiChat`|`gpt-4o, gpt-4o-mini, gpt-4` _**(8+)**_|✔ _**(1)**_|❌|✔ _**(8+)**_|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[chatgpt.com](https://chatgpt.com)|[Manual cookies](https://chatgpt.com)|`g4f.Provider.OpenaiChat`|`gpt-4o, gpt-4o-mini, gpt-4` _**(8+)**_|✔ _**(1)**_|❌|✔ _**(8+)**_|![](https://img.shields.io/badge/Active-brightgreen)|
|[perplexity.ai](https://www.perplexity.ai)|[Get API key](https://www.perplexity.ai/settings/api)|`g4f.Provider.PerplexityApi`|✔ _**(6+)**_|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[perplexity.ai](https://www.perplexity.ai)|[Get API key](https://www.perplexity.ai/settings/api)|`g4f.Provider.PerplexityApi`|✔ _**(6+)**_|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[chat.reka.ai](https://chat.reka.ai)|[Manual cookies](https://chat.reka.ai)|`g4f.Provider.Reka`|`reka-core`|✔|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[chat.reka.ai](https://chat.reka.ai)|[Manual cookies](https://chat.reka.ai)|`g4f.Provider.Reka`|`reka-core`|✔|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[replicate.com](https://replicate.com)|[Get API key](https://replicate.com/account/api-tokens)|`g4f.Provider.Replicate`|✔ _**(1+)**_|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[replicate.com](https://replicate.com)|[Get API key](https://replicate.com/account/api-tokens)|`g4f.Provider.Replicate`|✔ _**(1+)**_|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[beta.theb.ai](https://beta.theb.ai)|[Get API key](https://beta.theb.ai)|`g4f.Provider.ThebApi`|✔ _**(21+)**_|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[beta.theb.ai](https://beta.theb.ai)|[Get API key](https://beta.theb.ai)|`g4f.Provider.ThebApi`|✔ _**(21+)**_|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[whiterabbitneo.com](https://www.whiterabbitneo.com)|[Manual cookies](https://www.whiterabbitneo.com)|`g4f.Provider.WhiteRabbitNeo`|✔|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[whiterabbitneo.com](https://www.whiterabbitneo.com)|[Manual cookies](https://www.whiterabbitneo.com)|`g4f.Provider.WhiteRabbitNeo`|✔|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
|[console.x.ai](https://console.x.ai)|[Get API key](https://console.x.ai)|`g4f.Provider.xAI`|✔|❌|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)| |[console.x.ai](https://console.x.ai)|[Get API key](https://console.x.ai)|`g4f.Provider.xAI`|✔|❌|❌|❌|![](https://img.shields.io/badge/Active-brightgreen)|
--- ---
## Models ## Models
@ -145,12 +143,13 @@ This document provides an overview of various AI providers and models, including
### Text generation models ### Text generation models
| Model | Base Provider | Providers | Website | | Model | Base Provider | Providers | Website |
|-------|---------------|-----------|---------| |-------|---------------|-----------|---------|
|gpt-3.5-turbo|OpenAI|1+ Providers|[platform.openai.com](https://platform.openai.com/docs/engines/gpt-3.5-turbo)|
|gpt-4|OpenAI|9+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4)| |gpt-4|OpenAI|9+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4)|
|gpt-4o|OpenAI|6+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4o)| |gpt-4o|OpenAI|6+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4o)|
|gpt-4o-mini|OpenAI|8+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4o-mini)| |gpt-4o-mini|OpenAI|9+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4o-mini)|
|o1|OpenAI|3+ Providers|[openai.com](https://openai.com/index/introducing-openai-o1-preview/)| |o1|OpenAI|4+ Providers|[openai.com](https://openai.com/index/introducing-openai-o1-preview/)|
|o1-mini|OpenAI|1+ Providers|[openai.com](https://openai.com/index/openai-o1-mini-advancing-cost-efficient-reasoning/)| |o1-mini|OpenAI|1+ Providers|[openai.com](https://openai.com/index/openai-o1-mini-advancing-cost-efficient-reasoning/)|
|o3-mini|OpenAI|3+ Providers|[openai.com](https://openai.com/index/openai-o3-mini/)| |o3-mini|OpenAI|4+ Providers|[openai.com](https://openai.com/index/openai-o3-mini/)|
|gigachat|GigaChat|1+ Providers|[developers.sber.ru/gigachat](https://developers.sber.ru/gigachat)| |gigachat|GigaChat|1+ Providers|[developers.sber.ru/gigachat](https://developers.sber.ru/gigachat)|
|meta-ai|Meta|1+ Providers|[ai.meta.com](https://ai.meta.com/)| |meta-ai|Meta|1+ Providers|[ai.meta.com](https://ai.meta.com/)|
|llama-2-7b|Meta Llama|1+ Providers|[huggingface.co](https://huggingface.co/meta-llama/Llama-2-7b)| |llama-2-7b|Meta Llama|1+ Providers|[huggingface.co](https://huggingface.co/meta-llama/Llama-2-7b)|
@ -170,7 +169,7 @@ This document provides an overview of various AI providers and models, including
|mixtral-small-24b|Mistral|2+ Providers|[huggingface.co](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501)| |mixtral-small-24b|Mistral|2+ Providers|[huggingface.co](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501)|
|hermes-3|NousResearch|1+ Providers|[huggingface.co](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B-FP8)| |hermes-3|NousResearch|1+ Providers|[huggingface.co](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B-FP8)|
|phi-3.5-mini|Microsoft|1+ Providers|[huggingface.co](https://huggingface.co/microsoft/Phi-3.5-mini-instruct)| |phi-3.5-mini|Microsoft|1+ Providers|[huggingface.co](https://huggingface.co/microsoft/Phi-3.5-mini-instruct)|
|phi-4|Microsoft|2+ Providers|[techcommunity.microsoft.com](https://techcommunity.microsoft.com/blog/aiplatformblog/introducing-phi-4-microsoft%E2%80%99s-newest-small-language-model-specializing-in-comple/4357090)| |phi-4|Microsoft|3+ Providers|[techcommunity.microsoft.com](https://techcommunity.microsoft.com/blog/aiplatformblog/introducing-phi-4-microsoft%E2%80%99s-newest-small-language-model-specializing-in-comple/4357090)|
|wizardlm-2-7b|Microsoft|1+ Providers|[wizardlm.github.io](https://wizardlm.github.io/WizardLM2/)| |wizardlm-2-7b|Microsoft|1+ Providers|[wizardlm.github.io](https://wizardlm.github.io/WizardLM2/)|
|wizardlm-2-8x22b|Microsoft|2+ Providers|[wizardlm.github.io](https://wizardlm.github.io/WizardLM2/)| |wizardlm-2-8x22b|Microsoft|2+ Providers|[wizardlm.github.io](https://wizardlm.github.io/WizardLM2/)|
|gemini-exp|Google DeepMind|1+ Providers|[blog.google](https://blog.google/feed/gemini-exp-1206/)| |gemini-exp|Google DeepMind|1+ Providers|[blog.google](https://blog.google/feed/gemini-exp-1206/)|
@ -197,13 +196,14 @@ This document provides an overview of various AI providers and models, including
|qwen-2-vl-7b|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2-VL-7B)| |qwen-2-vl-7b|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2-VL-7B)|
|qwen-2.5-72b|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)| |qwen-2.5-72b|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)|
|qwen-2.5-coder-32b|Qwen|3+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2.5-Coder-32B)| |qwen-2.5-coder-32b|Qwen|3+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2.5-Coder-32B)|
|qwen-2.5-1m-demo|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2.5-1M-Demo)| |qwen-2.5-1m|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2.5-1M-Demo)|
|qwen-2-5-max|Qwen|1+ Providers|[qwen-ai.com](https://www.qwen-ai.com/2-5-max/)|
|qwq-32b|Qwen|2+ Providers|[huggingface.co](https://huggingface.co/Qwen/QwQ-32B-Preview)| |qwq-32b|Qwen|2+ Providers|[huggingface.co](https://huggingface.co/Qwen/QwQ-32B-Preview)|
|qvq-72b|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/QVQ-72B-Preview)| |qvq-72b|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/QVQ-72B-Preview)|
|pi|Inflection|1+ Providers|[inflection.ai](https://inflection.ai/blog/inflection-2-5)| |pi|Inflection|1+ Providers|[inflection.ai](https://inflection.ai/blog/inflection-2-5)|
|deepseek-chat|DeepSeek|2+ Providers|[huggingface.co](https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat)| |deepseek-chat|DeepSeek|2+ Providers|[huggingface.co](https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat)|
|deepseek-v3|DeepSeek|4+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/news/news250120)| |deepseek-v3|DeepSeek|5+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/news/news250120)|
|deepseek-r1|DeepSeek|9+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/news/news250120)| |deepseek-r1|DeepSeek|10+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/news/news250120)|
|janus-pro-7b|DeepSeek|2+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/docs/janus-pro-7b)| |janus-pro-7b|DeepSeek|2+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/docs/janus-pro-7b)|
|grok-3|x.ai|1+ Providers|[x.ai](https://x.ai/blog/grok-3)| |grok-3|x.ai|1+ Providers|[x.ai](https://x.ai/blog/grok-3)|
|grok-3-r1|x.ai|1+ Providers|[x.ai](https://x.ai/blog/grok-3)| |grok-3-r1|x.ai|1+ Providers|[x.ai](https://x.ai/blog/grok-3)|
@ -228,7 +228,7 @@ This document provides an overview of various AI providers and models, including
|tulu-3-70b|Ai2|1+ Providers|[allenai.org](https://allenai.org/documentation)| |tulu-3-70b|Ai2|1+ Providers|[allenai.org](https://allenai.org/documentation)|
|olmoe-0125|Ai2|1+ Providers|[allenai.org](https://allenai.org/documentation)| |olmoe-0125|Ai2|1+ Providers|[allenai.org](https://allenai.org/documentation)|
|lfm-40b|Liquid AI|1+ Providers|[liquid.ai](https://www.liquid.ai/liquid-foundation-models)| |lfm-40b|Liquid AI|1+ Providers|[liquid.ai](https://www.liquid.ai/liquid-foundation-models)|
|evil|Evil Mode - Experimental|1+ Providers|[]( )| |evil|Evil Mode - Experimental|2+ Providers|[]( )|
--- ---
### Image generation models ### Image generation models
@ -243,14 +243,19 @@ This document provides an overview of various AI providers and models, including
|dall-e-3|OpenAI|5+ Providers|[openai.com](https://openai.com/index/dall-e/)| |dall-e-3|OpenAI|5+ Providers|[openai.com](https://openai.com/index/dall-e/)|
|midjourney|Midjourney|1+ Providers|[docs.midjourney.com](https://docs.midjourney.com/docs/model-versions)| |midjourney|Midjourney|1+ Providers|[docs.midjourney.com](https://docs.midjourney.com/docs/model-versions)|
---
### Audio generation models
| Model | Base Provider | Providers | Website |
|-------|---------------|-----------|---------|
|gpt-4o-audio|Stability AI|1+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4o-audio)|
## Conclusion and Usage Tips ## Conclusion and Usage Tips
This document provides a comprehensive overview of various AI providers and models available for text generation, image generation, and vision tasks. **When choosing a provider or model, consider the following factors:** This document provides a comprehensive overview of various AI providers and models available for text generation, image generation, and vision tasks. **When choosing a provider or model, consider the following factors:**
1. **Availability**: Check the status of the provider to ensure it's currently active and accessible. 1. **Availability**: Check the status of the provider to ensure it's currently active and accessible.
2. **Model Capabilities**: Different models excel at different tasks. Choose a model that best fits your specific needs, whether it's text generation, image creation, or vision-related tasks. 2. **Model Capabilities**: Different models excel at different tasks. Choose a model that best fits your specific needs, whether it's text generation, image creation, or vision-related tasks.
3. **Authentication**: Some providers require authentication, while others don't. Consider this when selecting a provider for your project. 3. **Authentication**: Some providers require authentication, while others don't. Consider this when selecting a provider for your project.
4. **Streaming Support**: If real-time responses are important for your application, prioritize providers that offer streaming capabilities. 4. **Vision Models**: For tasks requiring image understanding or multimodal interactions, look for providers offering vision models.
5. **Vision Models**: For tasks requiring image understanding or multimodal interactions, look for providers offering vision models.
Remember to stay updated with the latest developments in the AI field, as new models and providers are constantly emerging and evolving. Remember to stay updated with the latest developments in the AI field, as new models and providers are constantly emerging and evolving.

2
g4f/Provider/ARTA.py
View file

@ -75,7 +75,7 @@ class ARTA(AsyncGeneratorProvider, ProviderModelMixin):
"professional": "Professional", "professional": "Professional",
"black_ink": "Black Ink" "black_ink": "Black Ink"
} }
image_models = [*model_aliases.keys()] image_models = list(model_aliases.keys())
models = image_models models = image_models
@classmethod @classmethod

156
g4f/Provider/DDG.py
View file

@ -5,19 +5,22 @@ from aiohttp import ClientSession, ClientTimeout
import json import json
import asyncio import asyncio
import random import random
from yarl import URL
from ..typing import AsyncResult, Messages, Cookies from ..typing import AsyncResult, Messages, Cookies
from ..requests.raise_for_status import raise_for_status from ..requests.raise_for_status import raise_for_status
from .base_provider import AsyncGeneratorProvider, ProviderModelMixin from .base_provider import AsyncGeneratorProvider, ProviderModelMixin
from .helper import format_prompt from .helper import format_prompt, get_last_user_message
from ..providers.response import FinishReason, JsonConversation from ..providers.response import FinishReason, JsonConversation
from ..errors import ModelNotSupportedError, ResponseStatusError, RateLimitError, TimeoutError, ConversationLimitError from ..errors import ModelNotSupportedError, ResponseStatusError, RateLimitError, TimeoutError, ConversationLimitError
class DuckDuckGoSearchException(Exception): class DuckDuckGoSearchException(Exception):
"""Base exception class for duckduckgo_search.""" """Base exception class for duckduckgo_search."""
class Conversation(JsonConversation): class Conversation(JsonConversation):
vqd: str = None vqd: str = None
vqd_hash_1: str = None
message_history: Messages = [] message_history: Messages = []
cookies: dict = {} cookies: dict = {}
@ -30,7 +33,7 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
api_endpoint = "https://duckduckgo.com/duckchat/v1/chat" api_endpoint = "https://duckduckgo.com/duckchat/v1/chat"
status_url = "https://duckduckgo.com/duckchat/v1/status" status_url = "https://duckduckgo.com/duckchat/v1/status"
working = False working = True
supports_stream = True supports_stream = True
supports_system_message = True supports_system_message = True
supports_message_history = True supports_message_history = True
@ -46,6 +49,8 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
} }
last_request_time = 0 last_request_time = 0
max_retries = 3
base_delay = 2
@classmethod @classmethod
def validate_model(cls, model: str) -> str: def validate_model(cls, model: str) -> str:
@ -59,43 +64,78 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
return model return model
@classmethod @classmethod
async def sleep(cls): async def sleep(cls, multiplier=1.0):
"""Implements rate limiting between requests""" """Implements rate limiting between requests"""
now = time.time() now = time.time()
if cls.last_request_time > 0: if cls.last_request_time > 0:
delay = max(0.0, 0.75 - (now - cls.last_request_time)) delay = max(0.0, 1.5 - (now - cls.last_request_time)) * multiplier
if delay > 0: if delay > 0:
await asyncio.sleep(delay) await asyncio.sleep(delay)
cls.last_request_time = now cls.last_request_time = time.time()
@classmethod @classmethod
async def fetch_vqd(cls, session: ClientSession, max_retries: int = 3) -> str: async def get_default_cookies(cls, session: ClientSession) -> dict:
"""Fetches the required VQD token for the chat session with retries.""" """Obtains default cookies needed for API requests"""
headers = {
"accept": "text/event-stream",
"content-type": "application/json",
"x-vqd-accept": "1",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
}
for attempt in range(max_retries):
try: try:
await cls.sleep() await cls.sleep()
# Make initial request to get cookies
async with session.get(cls.url) as response:
# We also manually set required cookies
cookies = {}
cookies_dict = {'dcs': '1', 'dcm': '3'}
for name, value in cookies_dict.items():
cookies[name] = value
url_obj = URL(cls.url)
session.cookie_jar.update_cookies({name: value}, url_obj)
return cookies
except Exception as e:
return {}
@classmethod
async def fetch_vqd_and_hash(cls, session: ClientSession, retry_count: int = 0) -> tuple[str, str]:
"""Fetches the required VQD token and hash for the chat session with retries."""
headers = {
"accept": "text/event-stream",
"accept-language": "en-US,en;q=0.9",
"cache-control": "no-cache",
"content-type": "application/json",
"pragma": "no-cache",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36",
"origin": "https://duckduckgo.com",
"referer": "https://duckduckgo.com/",
"x-vqd-accept": "1",
}
# Make sure we have cookies first
if len(session.cookie_jar) == 0:
await cls.get_default_cookies(session)
try:
await cls.sleep(multiplier=1.0 + retry_count * 0.5)
async with session.get(cls.status_url, headers=headers) as response: async with session.get(cls.status_url, headers=headers) as response:
await raise_for_status(response) await raise_for_status(response)
vqd = response.headers.get("x-vqd-4", "")
if vqd:
return vqd
response_text = await response.text()
raise RuntimeError(f"Failed to fetch VQD token: {response.status} {response_text}")
except ResponseStatusError as e:
if attempt < max_retries - 1:
wait_time = random.uniform(1, 3) * (attempt + 1)
await asyncio.sleep(wait_time)
else:
raise RuntimeError(f"Failed to fetch VQD token after {max_retries} attempts: {str(e)}")
raise RuntimeError("Failed to fetch VQD token: Maximum retries exceeded") vqd = response.headers.get("x-vqd-4", "")
vqd_hash_1 = response.headers.get("x-vqd-hash-1", "")
if vqd and vqd_hash_1:
return vqd, vqd_hash_1
if vqd and not vqd_hash_1:
return vqd, ""
response_text = await response.text()
raise RuntimeError(f"Failed to fetch VQD token and hash: {response.status} {response_text}")
except Exception as e:
if retry_count < cls.max_retries:
wait_time = cls.base_delay * (2 ** retry_count) * (1 + random.random())
await asyncio.sleep(wait_time)
return await cls.fetch_vqd_and_hash(session, retry_count + 1)
else:
raise RuntimeError(f"Failed to fetch VQD token and hash after {cls.max_retries} attempts: {str(e)}")
@classmethod @classmethod
async def create_async_generator( async def create_async_generator(
@ -103,40 +143,69 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
model: str, model: str,
messages: Messages, messages: Messages,
proxy: str = None, proxy: str = None,
timeout: int = 30, timeout: int = 60,
cookies: Cookies = None, cookies: Cookies = None,
conversation: Conversation = None, conversation: Conversation = None,
return_conversation: bool = False, return_conversation: bool = False,
**kwargs **kwargs
) -> AsyncResult: ) -> AsyncResult:
model = cls.validate_model(model) model = cls.validate_model(model)
retry_count = 0
if cookies is None and conversation is not None: while retry_count <= cls.max_retries:
cookies = conversation.cookies
try: try:
async with ClientSession(timeout=ClientTimeout(total=timeout), cookies=cookies) as session: session_timeout = ClientTimeout(total=timeout)
async with ClientSession(timeout=session_timeout, cookies=cookies) as session:
if conversation is None: if conversation is None:
# Get initial cookies if not provided
if not cookies:
await cls.get_default_cookies(session)
conversation = Conversation(model) conversation = Conversation(model)
conversation.vqd = await cls.fetch_vqd(session) vqd, vqd_hash_1 = await cls.fetch_vqd_and_hash(session)
conversation.vqd = vqd
conversation.vqd_hash_1 = vqd_hash_1
conversation.message_history = [{"role": "user", "content": format_prompt(messages)}] conversation.message_history = [{"role": "user", "content": format_prompt(messages)}]
else: else:
conversation.message_history.append(messages[-1]) last_message = get_last_user_message(messages.copy())
conversation.message_history.append({"role": "user", "content": last_message})
headers = { headers = {
"accept": "text/event-stream", "accept": "text/event-stream",
"accept-language": "en-US,en;q=0.9",
"content-type": "application/json", "content-type": "application/json",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36", "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36",
"origin": "https://duckduckgo.com",
"referer": "https://duckduckgo.com/",
"x-vqd-4": conversation.vqd, "x-vqd-4": conversation.vqd,
} }
# Add the x-vqd-hash-1 header if available
if conversation.vqd_hash_1:
headers["x-vqd-hash-1"] = conversation.vqd_hash_1
data = { data = {
"model": model, "model": model,
"messages": conversation.message_history, "messages": conversation.message_history,
} }
await cls.sleep() await cls.sleep(multiplier=1.0 + retry_count * 0.5)
async with session.post(cls.api_endpoint, json=data, headers=headers, proxy=proxy) as response: async with session.post(cls.api_endpoint, json=data, headers=headers, proxy=proxy) as response:
# Handle 429 errors specifically
if response.status == 429:
response_text = await response.text()
if retry_count < cls.max_retries:
retry_count += 1
wait_time = cls.base_delay * (2 ** retry_count) * (1 + random.random())
await asyncio.sleep(wait_time)
# Get fresh tokens and cookies
cookies = await cls.get_default_cookies(session)
continue
else:
raise RateLimitError(f"Rate limited after {cls.max_retries} retries")
await raise_for_status(response) await raise_for_status(response)
reason = None reason = None
full_message = "" full_message = ""
@ -169,14 +238,27 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
if return_conversation: if return_conversation:
conversation.message_history.append({"role": "assistant", "content": full_message}) conversation.message_history.append({"role": "assistant", "content": full_message})
conversation.vqd = response.headers.get("x-vqd-4", conversation.vqd) conversation.vqd = response.headers.get("x-vqd-4", conversation.vqd)
conversation.vqd_hash_1 = response.headers.get("x-vqd-hash-1", conversation.vqd_hash_1)
conversation.cookies = { conversation.cookies = {
n: c.value n: c.value
for n, c in session.cookie_jar.filter_cookies(cls.url).items() for n, c in session.cookie_jar.filter_cookies(URL(cls.url)).items()
} }
yield conversation yield conversation
if reason is not None: if reason is not None:
yield FinishReason(reason) yield FinishReason(reason)
# If we got here, the request was successful
break
except (RateLimitError, ResponseStatusError) as e:
if "429" in str(e) and retry_count < cls.max_retries:
retry_count += 1
wait_time = cls.base_delay * (2 ** retry_count) * (1 + random.random())
await asyncio.sleep(wait_time)
else:
raise
except asyncio.TimeoutError as e: except asyncio.TimeoutError as e:
raise TimeoutError(f"Request timed out: {str(e)}") raise TimeoutError(f"Request timed out: {str(e)}")
except Exception as e:
raise

39
g4f/Provider/DeepInfraChat.py
View file

@ -1,8 +1,6 @@
from __future__ import annotations from __future__ import annotations
from ..typing import AsyncResult, Messages, MediaListType
from .template import OpenaiTemplate from .template import OpenaiTemplate
from ..image import to_data_uri
class DeepInfraChat(OpenaiTemplate): class DeepInfraChat(OpenaiTemplate):
url = "https://deepinfra.com/chat" url = "https://deepinfra.com/chat"
@ -10,8 +8,8 @@ class DeepInfraChat(OpenaiTemplate):
working = True working = True
default_model = 'deepseek-ai/DeepSeek-V3' default_model = 'deepseek-ai/DeepSeek-V3'
default_vision_model = 'meta-llama/Llama-3.2-90B-Vision-Instruct' default_vision_model = 'openbmb/MiniCPM-Llama3-V-2_5'
vision_models = [default_vision_model, 'openbmb/MiniCPM-Llama3-V-2_5'] vision_models = [default_vision_model, 'meta-llama/Llama-3.2-90B-Vision-Instruct']
models = [ models = [
'meta-llama/Meta-Llama-3.1-8B-Instruct', 'meta-llama/Meta-Llama-3.1-8B-Instruct',
'meta-llama/Llama-3.3-70B-Instruct-Turbo', 'meta-llama/Llama-3.3-70B-Instruct-Turbo',
@ -59,36 +57,3 @@ class DeepInfraChat(OpenaiTemplate):
"mixtral-8x22b": "mistralai/Mixtral-8x22B-Instruct-v0.1", "mixtral-8x22b": "mistralai/Mixtral-8x22B-Instruct-v0.1",
"minicpm-2.5": "openbmb/MiniCPM-Llama3-V-2_5", "minicpm-2.5": "openbmb/MiniCPM-Llama3-V-2_5",
} }
@classmethod
async def create_async_generator(
cls,
model: str,
messages: Messages,
stream: bool = True,
top_p: float = 0.9,
temperature: float = 0.7,
max_tokens: int = None,
headers: dict = {},
**kwargs
) -> AsyncResult:
headers = {
'Accept-Language': 'en-US,en;q=0.9',
'Origin': 'https://deepinfra.com',
'Referer': 'https://deepinfra.com/',
'X-Deepinfra-Source': 'web-page',
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
**headers
}
async for chunk in super().create_async_generator(
model,
messages,
headers=headers,
stream=stream,
top_p=top_p,
temperature=temperature,
max_tokens=max_tokens,
**kwargs
):
yield chunk

3
g4f/Provider/LambdaChat.py
View file

@ -14,7 +14,6 @@ class LambdaChat(HuggingChat):
default_model = "deepseek-llama3.3-70b" default_model = "deepseek-llama3.3-70b"
reasoning_model = "deepseek-r1" reasoning_model = "deepseek-r1"
image_models = [] image_models = []
models = []
fallback_models = [ fallback_models = [
default_model, default_model,
reasoning_model, reasoning_model,
@ -23,6 +22,8 @@ class LambdaChat(HuggingChat):
"lfm-40b", "lfm-40b",
"llama3.3-70b-instruct-fp8" "llama3.3-70b-instruct-fp8"
] ]
models = fallback_models.copy()
model_aliases = { model_aliases = {
"deepseek-v3": default_model, "deepseek-v3": default_model,
"hermes-3": "hermes-3-llama-3.1-405b-fp8", "hermes-3": "hermes-3-llama-3.1-405b-fp8",

11
g4f/Provider/TypeGPT.py
View file

@ -5,13 +5,14 @@ from .template import OpenaiTemplate
class TypeGPT(OpenaiTemplate): class TypeGPT(OpenaiTemplate):
label = "TypeGpt" label = "TypeGpt"
url = "https://chat.typegpt.net" url = "https://chat.typegpt.net"
api_endpoint = "https://chat.typegpt.net/api/openai/typegpt/v1/chat/completions" api_base = "https://chat.typegpt.net/api/openai/typegpt/v1"
working = True working = True
default_model = "gpt-4o-mini-2024-07-18" default_model = 'gpt-4o-mini-2024-07-18'
models = [ default_vision_model = default_model
default_model, "o1", "o3-mini", "gemini-1.5-flash", "deepseek-r1", "deepseek-v3", "gemini-pro", "evil" vision_models = ['gpt-3.5-turbo', 'gpt-3.5-turbo-202201', default_vision_model, "o3-mini"]
] models = vision_models + ["deepseek-r1", "deepseek-v3", "evil", "o1"]
model_aliases = { model_aliases = {
"gpt-3.5-turbo": "gpt-3.5-turbo-202201",
"gpt-4o-mini": "gpt-4o-mini-2024-07-18", "gpt-4o-mini": "gpt-4o-mini-2024-07-18",
} }

4
g4f/Provider/hf_space/BlackForestLabs_Flux1Dev.py
View file

@ -22,8 +22,8 @@ class BlackForestLabs_Flux1Dev(AsyncGeneratorProvider, ProviderModelMixin):
default_model = 'black-forest-labs-flux-1-dev' default_model = 'black-forest-labs-flux-1-dev'
default_image_model = default_model default_image_model = default_model
model_aliases = {"flux-dev": default_model, "flux": default_model} model_aliases = {"flux-dev": default_image_model, "flux": default_image_model}
image_models = [default_image_model, *model_aliases.keys()] image_models = list(model_aliases.keys())
models = image_models models = image_models
@classmethod @classmethod

4
g4f/Provider/hf_space/BlackForestLabs_Flux1Schnell.py
View file

@ -19,8 +19,8 @@ class BlackForestLabs_Flux1Schnell(AsyncGeneratorProvider, ProviderModelMixin):
default_model = "black-forest-labs-flux-1-schnell" default_model = "black-forest-labs-flux-1-schnell"
default_image_model = default_model default_image_model = default_model
model_aliases = {"flux-schnell": default_model, "flux": default_model} model_aliases = {"flux-schnell": default_image_model, "flux": default_image_model}
image_models = [default_image_model, *model_aliases.keys()] image_models = list(model_aliases.keys())
models = image_models models = image_models
@classmethod @classmethod

14
g4f/Provider/hf_space/CohereForAI_C4AI_Command.py
View file

@ -17,22 +17,16 @@ class CohereForAI_C4AI_Command(AsyncGeneratorProvider, ProviderModelMixin):
working = True working = True
default_model = "command-a-03-2025" default_model = "command-a-03-2025"
models = [
default_model,
"command-r-plus-08-2024",
"command-r-08-2024",
"command-r-plus",
"command-r",
"command-r7b-12-2024",
"command-r7b-arabic-02-2025",
]
model_aliases = { model_aliases = {
"command-a": "command-a-03-2025", "command-a": default_model,
"command-r-plus": "command-r-plus-08-2024", "command-r-plus": "command-r-plus-08-2024",
"command-r": "command-r-08-2024", "command-r": "command-r-08-2024",
"command-r": "command-r",
"command-r7b": "command-r7b-12-2024", "command-r7b": "command-r7b-12-2024",
} }
models = list(model_aliases.keys())
@classmethod @classmethod
async def create_async_generator( async def create_async_generator(
cls, model: str, messages: Messages, cls, model: str, messages: Messages,

3
g4f/Provider/hf_space/DeepseekAI_JanusPro7b.py
View file

@ -34,8 +34,9 @@ class DeepseekAI_JanusPro7b(AsyncGeneratorProvider, ProviderModelMixin):
default_model = "janus-pro-7b" default_model = "janus-pro-7b"
default_image_model = "janus-pro-7b-image" default_image_model = "janus-pro-7b-image"
default_vision_model = default_model default_vision_model = default_model
models = [default_model, default_image_model]
image_models = [default_image_model] image_models = [default_image_model]
vision_models = [default_vision_model]
models = vision_models + image_models
@classmethod @classmethod
def run(cls, method: str, session: StreamSession, prompt: str, conversation: JsonConversation, image: dict = None, seed: int = 0): def run(cls, method: str, session: StreamSession, prompt: str, conversation: JsonConversation, image: dict = None, seed: int = 0):

4
g4f/Provider/hf_space/Microsoft_Phi_4.py
View file

@ -29,7 +29,9 @@ class Microsoft_Phi_4(AsyncGeneratorProvider, ProviderModelMixin):
default_model = "phi-4-multimodal" default_model = "phi-4-multimodal"
default_vision_model = default_model default_vision_model = default_model
models = [default_model] model_aliases = {"phi-4": default_vision_model}
vision_models = list(model_aliases.keys())
models = vision_models
@classmethod @classmethod
def run(cls, method: str, session: StreamSession, prompt: str, conversation: JsonConversation, media: list = None): def run(cls, method: str, session: StreamSession, prompt: str, conversation: JsonConversation, media: list = None):

7
g4f/Provider/hf_space/Qwen_QVQ_72B.py
View file

@ -18,9 +18,10 @@ class Qwen_QVQ_72B(AsyncGeneratorProvider, ProviderModelMixin):
working = True working = True
default_model = "qwen-qvq-72b-preview" default_model = "qwen-qvq-72b-preview"
models = [default_model] default_vision_model = default_model
model_aliases = {"qvq-72b": default_model} model_aliases = {"qvq-72b": default_vision_model}
vision_models = models vision_models = list(model_aliases.keys())
models = vision_models
@classmethod @classmethod
async def create_async_generator( async def create_async_generator(

146
g4f/Provider/hf_space/Qwen_Qwen_2_5.py Normal file
View file

@ -0,0 +1,146 @@
from __future__ import annotations
import aiohttp
import json
import uuid
import re
from ...typing import AsyncResult, Messages
from ..base_provider import AsyncGeneratorProvider, ProviderModelMixin
from ..helper import format_prompt
from ... import debug
class Qwen_Qwen_2_5(AsyncGeneratorProvider, ProviderModelMixin):
label = "Qwen Qwen-2.5"
url = "https://qwen-qwen2-5.hf.space"
api_endpoint = "https://qwen-qwen2-5.hf.space/queue/join"
working = True
supports_stream = True
supports_system_message = True
supports_message_history = False
default_model = "qwen-qwen2-5"
model_aliases = {"qwen-2.5": default_model}
models = list(model_aliases.keys())
@classmethod
async def create_async_generator(
cls,
model: str,
messages: Messages,
proxy: str = None,
**kwargs
) -> AsyncResult:
def generate_session_hash():
"""Generate a unique session hash."""
return str(uuid.uuid4()).replace('-', '')[:10]
# Generate a unique session hash
session_hash = generate_session_hash()
headers_join = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:136.0) Gecko/20100101 Firefox/136.0',
'Accept': '*/*',
'Accept-Language': 'en-US,en;q=0.5',
'Accept-Encoding': 'gzip, deflate, br, zstd',
'Referer': f'{cls.url}/?__theme=system',
'content-type': 'application/json',
'Origin': cls.url,
'Connection': 'keep-alive',
'Sec-Fetch-Dest': 'empty',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Site': 'same-origin',
'Pragma': 'no-cache',
'Cache-Control': 'no-cache',
}
# Prepare the prompt
system_prompt = "\n".join([message["content"] for message in messages if message["role"] == "system"])
if not system_prompt:
system_prompt = "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."
messages = [message for message in messages if message["role"] != "system"]
prompt = format_prompt(messages)
payload_join = {
"data": [prompt, [], system_prompt, "72B"],
"event_data": None,
"fn_index": 3,
"trigger_id": 25,
"session_hash": session_hash
}
async with aiohttp.ClientSession() as session:
# Send join request
async with session.post(cls.api_endpoint, headers=headers_join, json=payload_join) as response:
event_id = (await response.json())['event_id']
# Prepare data stream request
url_data = f'{cls.url}/queue/data'
headers_data = {
'Accept': 'text/event-stream',
'Accept-Language': 'en-US,en;q=0.5',
'Referer': f'{cls.url}/?__theme=system',
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:136.0) Gecko/20100101 Firefox/136.0',
}
params_data = {
'session_hash': session_hash
}
# Send data stream request
async with session.get(url_data, headers=headers_data, params=params_data) as response:
full_response = ""
async for line in response.content:
decoded_line = line.decode('utf-8')
if decoded_line.startswith('data: '):
try:
json_data = json.loads(decoded_line[6:])
# Look for generation stages
if json_data.get('msg') == 'process_generating':
if 'output' in json_data and 'data' in json_data['output']:
output_data = json_data['output']['data']
if len(output_data) > 1 and len(output_data[1]) > 0:
for item in output_data[1]:
if isinstance(item, list) and len(item) > 1:
# Extract the fragment, handling both string and dict types
fragment = item[1]
if isinstance(fragment, dict) and 'text' in fragment:
# For the first chunk, extract only the text part
fragment = fragment['text']
else:
fragment = str(fragment)
# Ignore [0, 1] type fragments and duplicates
if not re.match(r'^\[.*\]$', fragment) and not full_response.endswith(fragment):
full_response += fragment
yield fragment
# Check for completion
if json_data.get('msg') == 'process_completed':
# Final check to ensure we get the complete response
if 'output' in json_data and 'data' in json_data['output']:
output_data = json_data['output']['data']
if len(output_data) > 1 and len(output_data[1]) > 0:
# Get the final response text
response_item = output_data[1][0][1]
if isinstance(response_item, dict) and 'text' in response_item:
final_full_response = response_item['text']
else:
final_full_response = str(response_item)
# Clean up the final response
if isinstance(final_full_response, str) and final_full_response.startswith(full_response):
final_text = final_full_response[len(full_response):]
else:
final_text = final_full_response
# Yield the remaining part of the final response
if final_text and final_text != full_response:
yield final_text
break
except json.JSONDecodeError:
debug.log("Could not parse JSON:", decoded_line)

7
g4f/Provider/hf_space/Qwen_Qwen_2_5M_Demo.py → g4f/Provider/hf_space/Qwen_Qwen_2_5M.py
View file

@ -11,8 +11,8 @@ from ...providers.response import JsonConversation, Reasoning
from ..helper import get_last_user_message from ..helper import get_last_user_message
from ... import debug from ... import debug
class Qwen_Qwen_2_5M_Demo(AsyncGeneratorProvider, ProviderModelMixin): class Qwen_Qwen_2_5M(AsyncGeneratorProvider, ProviderModelMixin):
label = "Qwen Qwen-2.5M-Demo" label = "Qwen Qwen-2.5M"
url = "https://qwen-qwen2-5-1m-demo.hf.space" url = "https://qwen-qwen2-5-1m-demo.hf.space"
api_endpoint = f"{url}/run/predict?__theme=light" api_endpoint = f"{url}/run/predict?__theme=light"
@ -22,7 +22,8 @@ class Qwen_Qwen_2_5M_Demo(AsyncGeneratorProvider, ProviderModelMixin):
supports_message_history = False supports_message_history = False
default_model = "qwen-2.5-1m-demo" default_model = "qwen-2.5-1m-demo"
models = [default_model] model_aliases = {"qwen-2.5-1m": default_model}
models = list(model_aliases.keys())
@classmethod @classmethod
async def create_async_generator( async def create_async_generator(

133
g4f/Provider/hf_space/Qwen_Qwen_2_5_Max.py Normal file
View file

@ -0,0 +1,133 @@
from __future__ import annotations
import aiohttp
import json
import uuid
import re
from ...typing import AsyncResult, Messages
from ..base_provider import AsyncGeneratorProvider, ProviderModelMixin
from ..helper import format_prompt
from ... import debug
class Qwen_Qwen_2_5_Max(AsyncGeneratorProvider, ProviderModelMixin):
label = "Qwen Qwen-2.5-Max"
url = "https://qwen-qwen2-5-max-demo.hf.space"
api_endpoint = "https://qwen-qwen2-5-max-demo.hf.space/gradio_api/queue/join?"
working = True
supports_stream = True
supports_system_message = True
supports_message_history = False
default_model = "qwen-qwen2-5-max"
model_aliases = {"qwen-2-5-max": default_model}
models = list(model_aliases.keys())
@classmethod
async def create_async_generator(
cls,
model: str,
messages: Messages,
proxy: str = None,
**kwargs
) -> AsyncResult:
def generate_session_hash():
"""Generate a unique session hash."""
return str(uuid.uuid4()).replace('-', '')[:8] + str(uuid.uuid4()).replace('-', '')[:4]
# Generate a unique session hash
session_hash = generate_session_hash()
headers_join = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:136.0) Gecko/20100101 Firefox/136.0',
'Accept': '*/*',
'Accept-Language': 'en-US,en;q=0.5',
'Accept-Encoding': 'gzip, deflate, br, zstd',
'Referer': f'{cls.url}/?__theme=system',
'content-type': 'application/json',
'Origin': cls.url,
'Connection': 'keep-alive',
'Sec-Fetch-Dest': 'empty',
'Sec-Fetch-Mode': 'cors',
'Sec-Fetch-Site': 'same-origin',
'Pragma': 'no-cache',
'Cache-Control': 'no-cache',
}
# Prepare the prompt
system_prompt = "\n".join([message["content"] for message in messages if message["role"] == "system"])
if not system_prompt:
system_prompt = "You are a helpful assistant."
messages = [message for message in messages if message["role"] != "system"]
prompt = format_prompt(messages)
payload_join = {
"data": [prompt, [], system_prompt],
"event_data": None,
"fn_index": 0,
"trigger_id": 11,
"session_hash": session_hash
}
async with aiohttp.ClientSession() as session:
# Send join request
async with session.post(cls.api_endpoint, headers=headers_join, json=payload_join) as response:
event_id = (await response.json())['event_id']
# Prepare data stream request
url_data = f'{cls.url}/gradio_api/queue/data'
headers_data = {
'Accept': 'text/event-stream',
'Accept-Language': 'en-US,en;q=0.5',
'Referer': f'{cls.url}/?__theme=system',
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:136.0) Gecko/20100101 Firefox/136.0',
}
params_data = {
'session_hash': session_hash
}
# Send data stream request
async with session.get(url_data, headers=headers_data, params=params_data) as response:
full_response = ""
final_full_response = ""
async for line in response.content:
decoded_line = line.decode('utf-8')
if decoded_line.startswith('data: '):
try:
json_data = json.loads(decoded_line[6:])
# Look for generation stages
if json_data.get('msg') == 'process_generating':
if 'output' in json_data and 'data' in json_data['output']:
output_data = json_data['output']['data']
if len(output_data) > 1 and len(output_data[1]) > 0:
for item in output_data[1]:
if isinstance(item, list) and len(item) > 1:
fragment = str(item[1])
# Ignore [0, 1] type fragments and duplicates
if not re.match(r'^\[.*\]$', fragment) and not full_response.endswith(fragment):
full_response += fragment
yield fragment
# Check for completion
if json_data.get('msg') == 'process_completed':
# Final check to ensure we get the complete response
if 'output' in json_data and 'data' in json_data['output']:
output_data = json_data['output']['data']
if len(output_data) > 1 and len(output_data[1]) > 0:
final_full_response = output_data[1][0][1]
# Clean up the final response
if final_full_response.startswith(full_response):
final_full_response = final_full_response[len(full_response):]
# Yield the remaining part of the final response
if final_full_response:
yield final_full_response
break
except json.JSONDecodeError:
debug.log("Could not parse JSON:", decoded_line)

6
g4f/Provider/hf_space/Qwen_Qwen_2_72B_Instruct.py → g4f/Provider/hf_space/Qwen_Qwen_2_72B.py
View file

@ -10,8 +10,8 @@ from ..base_provider import AsyncGeneratorProvider, ProviderModelMixin
from ..helper import format_prompt from ..helper import format_prompt
from ... import debug from ... import debug
class Qwen_Qwen_2_72B_Instruct(AsyncGeneratorProvider, ProviderModelMixin): class Qwen_Qwen_2_72B(AsyncGeneratorProvider, ProviderModelMixin):
label = "Qwen Qwen-2.72B-Instruct" label = "Qwen Qwen-2.72B"
url = "https://qwen-qwen2-72b-instruct.hf.space" url = "https://qwen-qwen2-72b-instruct.hf.space"
api_endpoint = "https://qwen-qwen2-72b-instruct.hf.space/queue/join?" api_endpoint = "https://qwen-qwen2-72b-instruct.hf.space/queue/join?"
@ -21,8 +21,8 @@ class Qwen_Qwen_2_72B_Instruct(AsyncGeneratorProvider, ProviderModelMixin):
supports_message_history = False supports_message_history = False
default_model = "qwen-qwen2-72b-instruct" default_model = "qwen-qwen2-72b-instruct"
models = [default_model]
model_aliases = {"qwen-2-72b": default_model} model_aliases = {"qwen-2-72b": default_model}
models = list(model_aliases.keys())
@classmethod @classmethod
async def create_async_generator( async def create_async_generator(

4
g4f/Provider/hf_space/StabilityAI_SD35Large.py
View file

@ -18,9 +18,9 @@ class StabilityAI_SD35Large(AsyncGeneratorProvider, ProviderModelMixin):
default_model = 'stabilityai-stable-diffusion-3-5-large' default_model = 'stabilityai-stable-diffusion-3-5-large'
default_image_model = default_model default_image_model = default_model
image_models = [default_model]
models = image_models
model_aliases = {"sd-3.5": default_model} model_aliases = {"sd-3.5": default_model}
image_models = list(model_aliases.keys())
models = image_models
@classmethod @classmethod
async def create_async_generator( async def create_async_generator(

2
g4f/Provider/hf_space/Voodoohop_Flux1Schnell.py
View file

@ -20,7 +20,7 @@ class Voodoohop_Flux1Schnell(AsyncGeneratorProvider, ProviderModelMixin):
default_model = "voodoohop-flux-1-schnell" default_model = "voodoohop-flux-1-schnell"
default_image_model = default_model default_image_model = default_model
model_aliases = {"flux-schnell": default_model, "flux": default_model} model_aliases = {"flux-schnell": default_model, "flux": default_model}
image_models = [default_image_model, *model_aliases.keys()] image_models = list(model_aliases.keys())
models = image_models models = image_models
@classmethod @classmethod

14
g4f/Provider/hf_space/__init__.py
View file

@ -13,8 +13,10 @@ from .DeepseekAI_JanusPro7b import DeepseekAI_JanusPro7b
from .G4F import G4F from .G4F import G4F
from .Microsoft_Phi_4 import Microsoft_Phi_4 from .Microsoft_Phi_4 import Microsoft_Phi_4
from .Qwen_QVQ_72B import Qwen_QVQ_72B from .Qwen_QVQ_72B import Qwen_QVQ_72B
from .Qwen_Qwen_2_5M_Demo import Qwen_Qwen_2_5M_Demo from .Qwen_Qwen_2_5 import Qwen_Qwen_2_5
from .Qwen_Qwen_2_72B_Instruct import Qwen_Qwen_2_72B_Instruct from .Qwen_Qwen_2_5M import Qwen_Qwen_2_5M
from .Qwen_Qwen_2_5_Max import Qwen_Qwen_2_5_Max
from .Qwen_Qwen_2_72B import Qwen_Qwen_2_72B
from .StabilityAI_SD35Large import StabilityAI_SD35Large from .StabilityAI_SD35Large import StabilityAI_SD35Large
from .Voodoohop_Flux1Schnell import Voodoohop_Flux1Schnell from .Voodoohop_Flux1Schnell import Voodoohop_Flux1Schnell
@ -23,7 +25,7 @@ class HuggingSpace(AsyncGeneratorProvider, ProviderModelMixin):
working = True working = True
default_model = Qwen_Qwen_2_72B_Instruct.default_model default_model = Qwen_Qwen_2_72B.default_model
default_image_model = BlackForestLabs_Flux1Dev.default_model default_image_model = BlackForestLabs_Flux1Dev.default_model
default_vision_model = Qwen_QVQ_72B.default_model default_vision_model = Qwen_QVQ_72B.default_model
providers = [ providers = [
@ -34,8 +36,10 @@ class HuggingSpace(AsyncGeneratorProvider, ProviderModelMixin):
G4F, G4F,
Microsoft_Phi_4, Microsoft_Phi_4,
Qwen_QVQ_72B, Qwen_QVQ_72B,
Qwen_Qwen_2_5M_Demo, Qwen_Qwen_2_5,
Qwen_Qwen_2_72B_Instruct, Qwen_Qwen_2_5M,
Qwen_Qwen_2_5_Max,
Qwen_Qwen_2_72B,
StabilityAI_SD35Large, StabilityAI_SD35Large,
Voodoohop_Flux1Schnell, Voodoohop_Flux1Schnell,
] ]

69
g4f/models.py
View file

@ -30,6 +30,7 @@ from .Provider import (
Pi, Pi,
PollinationsAI, PollinationsAI,
PollinationsImage, PollinationsImage,
TypeGPT,
TeachAnything, TeachAnything,
Websim, Websim,
Yqcloud, Yqcloud,
@ -73,6 +74,9 @@ class Model:
class ImageModel(Model): class ImageModel(Model):
pass pass
class AudioModel(Model):
pass
class VisionModel(Model): class VisionModel(Model):
pass pass
@ -87,6 +91,7 @@ default = Model(
DeepInfraChat, DeepInfraChat,
AllenAI, AllenAI,
PollinationsAI, PollinationsAI,
TypeGPT,
OIVSCode, OIVSCode,
ChatGptEs, ChatGptEs,
Free2GPT, Free2GPT,
@ -105,6 +110,7 @@ default_vision = Model(
best_provider = IterListProvider([ best_provider = IterListProvider([
Blackbox, Blackbox,
OIVSCode, OIVSCode,
TypeGPT,
DeepInfraChat, DeepInfraChat,
PollinationsAI, PollinationsAI,
Dynaspark, Dynaspark,
@ -117,11 +123,18 @@ default_vision = Model(
], shuffle=False) ], shuffle=False)
) )
################### ##########################
### Text/Vision ### ### Text//Audio/Vision ###
################### ##########################
### OpenAI ### ### OpenAI ###
# gpt-3.5
gpt_3_5_turbo = Model(
name = 'gpt-3.5-turbo',
base_provider = 'OpenAI',
best_provider = TypeGPT
)
# gpt-4 # gpt-4
gpt_4 = Model( gpt_4 = Model(
name = 'gpt-4', name = 'gpt-4',
@ -139,14 +152,20 @@ gpt_4o = VisionModel(
gpt_4o_mini = Model( gpt_4o_mini = Model(
name = 'gpt-4o-mini', name = 'gpt-4o-mini',
base_provider = 'OpenAI', base_provider = 'OpenAI',
best_provider = IterListProvider([DDG, Blackbox, ChatGptEs, Jmuz, PollinationsAI, OIVSCode, Liaobots, OpenaiChat]) best_provider = IterListProvider([DDG, Blackbox, ChatGptEs, TypeGPT, PollinationsAI, OIVSCode, Liaobots, Jmuz, OpenaiChat])
)
gpt_4o_audio = AudioModel(
name = 'gpt-4o-audio',
base_provider = 'OpenAI',
best_provider = PollinationsAI
) )
# o1 # o1
o1 = Model( o1 = Model(
name = 'o1', name = 'o1',
base_provider = 'OpenAI', base_provider = 'OpenAI',
best_provider = IterListProvider([Blackbox, Copilot, OpenaiAccount]) best_provider = IterListProvider([Blackbox, Copilot, TypeGPT, OpenaiAccount])
) )
o1_mini = Model( o1_mini = Model(
@ -159,7 +178,7 @@ o1_mini = Model(
o3_mini = Model( o3_mini = Model(
name = 'o3-mini', name = 'o3-mini',
base_provider = 'OpenAI', base_provider = 'OpenAI',
best_provider = IterListProvider([DDG, Blackbox, Liaobots, PollinationsAI]) best_provider = IterListProvider([DDG, Blackbox, TypeGPT, PollinationsAI, Liaobots])
) )
### GigaChat ### ### GigaChat ###
@ -294,7 +313,7 @@ phi_3_5_mini = Model(
phi_4 = Model( phi_4 = Model(
name = "phi-4", name = "phi-4",
base_provider = "Microsoft", base_provider = "Microsoft",
best_provider = IterListProvider([DeepInfraChat, PollinationsAI]) best_provider = IterListProvider([DeepInfraChat, PollinationsAI, HuggingSpace])
) )
# wizardlm # wizardlm
@ -438,11 +457,14 @@ command_a = Model(
) )
### Qwen ### ### Qwen ###
# qwen-1.5
qwen_1_5_7b = Model( qwen_1_5_7b = Model(
name = 'qwen-1.5-7b', name = 'qwen-1.5-7b',
base_provider = 'Qwen', base_provider = 'Qwen',
best_provider = Cloudflare best_provider = Cloudflare
) )
# qwen-2
qwen_2_72b = Model( qwen_2_72b = Model(
name = 'qwen-2-72b', name = 'qwen-2-72b',
base_provider = 'Qwen', base_provider = 'Qwen',
@ -453,6 +475,14 @@ qwen_2_vl_7b = VisionModel(
base_provider = 'Qwen', base_provider = 'Qwen',
best_provider = HuggingFaceAPI best_provider = HuggingFaceAPI
) )
# qwen-2.5
qwen_2_5 = Model(
name = 'qwen-2.5',
base_provider = 'Qwen',
best_provider = HuggingSpace
)
qwen_2_5_72b = Model( qwen_2_5_72b = Model(
name = 'qwen-2.5-72b', name = 'qwen-2.5-72b',
base_provider = 'Qwen', base_provider = 'Qwen',
@ -464,7 +494,13 @@ qwen_2_5_coder_32b = Model(
best_provider = IterListProvider([PollinationsAI, Jmuz, HuggingChat]) best_provider = IterListProvider([PollinationsAI, Jmuz, HuggingChat])
) )
qwen_2_5_1m = Model( qwen_2_5_1m = Model(
name = 'qwen-2.5-1m-demo', name = 'qwen-2.5-1m',
base_provider = 'Qwen',
best_provider = HuggingSpace
)
qwen_2_5_max = Model(
name = 'qwen-2-5-max',
base_provider = 'Qwen', base_provider = 'Qwen',
best_provider = HuggingSpace best_provider = HuggingSpace
) )
@ -498,13 +534,13 @@ deepseek_chat = Model(
deepseek_v3 = Model( deepseek_v3 = Model(
name = 'deepseek-v3', name = 'deepseek-v3',
base_provider = 'DeepSeek', base_provider = 'DeepSeek',
best_provider = IterListProvider([Blackbox, DeepInfraChat, LambdaChat, OIVSCode, Liaobots]) best_provider = IterListProvider([Blackbox, DeepInfraChat, LambdaChat, OIVSCode, TypeGPT, Liaobots])
) )
deepseek_r1 = Model( deepseek_r1 = Model(
name = 'deepseek-r1', name = 'deepseek-r1',
base_provider = 'DeepSeek', base_provider = 'DeepSeek',
best_provider = IterListProvider([Blackbox, DeepInfraChat, Glider, LambdaChat, PollinationsAI, Jmuz, Liaobots, HuggingChat, HuggingFace]) best_provider = IterListProvider([Blackbox, DeepInfraChat, Glider, LambdaChat, PollinationsAI, TypeGPT, Liaobots, Jmuz, HuggingChat, HuggingFace])
) )
janus_pro_7b = VisionModel( janus_pro_7b = VisionModel(
@ -667,7 +703,7 @@ lfm_40b = Model(
evil = Model( evil = Model(
name = 'evil', name = 'evil',
base_provider = 'Evil Mode - Experimental', base_provider = 'Evil Mode - Experimental',
best_provider = PollinationsAI best_provider = IterListProvider([PollinationsAI, TypeGPT])
) )
@ -741,12 +777,16 @@ class ModelUtils:
############ ############
### OpenAI ### ### OpenAI ###
# gpt-3.5
gpt_3_5_turbo.name: gpt_3_5_turbo,
# gpt-4 # gpt-4
gpt_4.name: gpt_4, gpt_4.name: gpt_4,
# gpt-4o # gpt-4o
gpt_4o.name: gpt_4o, gpt_4o.name: gpt_4o,
gpt_4o_mini.name: gpt_4o_mini, gpt_4o_mini.name: gpt_4o_mini,
gpt_4o_audio.name: gpt_4o_audio,
# o1 # o1
o1.name: o1, o1.name: o1,
@ -837,12 +877,19 @@ class ModelUtils:
gigachat.name: gigachat, gigachat.name: gigachat,
### Qwen ### ### Qwen ###
# qwen-1.5
qwen_1_5_7b.name: qwen_1_5_7b, qwen_1_5_7b.name: qwen_1_5_7b,
# qwen-2
qwen_2_72b.name: qwen_2_72b, qwen_2_72b.name: qwen_2_72b,
qwen_2_vl_7b.name: qwen_2_vl_7b, qwen_2_vl_7b.name: qwen_2_vl_7b,
# qwen-2.5
qwen_2_5.name: qwen_2_5,
qwen_2_5_72b.name: qwen_2_5_72b, qwen_2_5_72b.name: qwen_2_5_72b,
qwen_2_5_coder_32b.name: qwen_2_5_coder_32b, qwen_2_5_coder_32b.name: qwen_2_5_coder_32b,
qwen_2_5_1m.name: qwen_2_5_1m, qwen_2_5_1m.name: qwen_2_5_1m,
qwen_2_5_max.name: qwen_2_5_max,
# qwq/qvq # qwq/qvq
qwq_32b.name: qwq_32b, qwq_32b.name: qwq_32b,