AI Provider and Model Updates: Adding New, Removing Deprecated, and Enhancing Functionality (#2739)

* docs(docs/providers-and-models.md): Update provider listings and model information * feat(g4f/models.py): update model configurations and expand provider support * fix(g4f/gui/client/static/js/chat.v1.js): correct provider checkbox initialization logic * feat(g4f/Provider/Blackbox.py): update model configurations and premium handling * feat(g4f/Provider/ChatGLM.py): add finish reason handling and update default model * chore(g4f/Provider/DDG.py): Reorder model entries for consistency * feat(g4f/Provider/ImageLabs.py): Update default image model to sdxl-turbo * feat(g4f/Provider/Liaobots.py): update supported model configurations and aliases * feat(g4f/Provider/OIVSCode.py): Update API endpoint and expand model support * fix(g4f/Provider/needs_auth/CablyAI.py): Enforce authentication requirement * Removed the provider (g4f/Provider/BlackboxAPI.py) * fix(g4f/providers/base_provider.py): improve cache validation in AsyncAuthedProvider * Update g4f/models.py * fix(g4f/Provider/Liaobots.py): remove deprecated Gemini model aliases * chore(g4f/models.py): Remove Grok-2 and update Gemini provider configurations * chore(docs/providers-and-models.md): Remove deprecated Grok models from provider listings * New provider added (g4f/Provider/AllenAI.py) * feat(g4f/models.py): Add Ai2 models and update provider references * feat(docs/providers-and-models.md): update providers and models documentation * fix(g4f/models.py): update experimental model provider configuration * fix(g4f/Provider/PollinationsImage.py): Initialize image_models list and update label * fix(g4f/Provider/PollinationsAI.py): Resolve model initialization and alias conflicts * refactor(g4f/Provider/PollinationsAI.py): improve model initialization and error handling * refactor(g4f/Provider/PollinationsImage.py): Improve model synchronization and initialization * Update g4f/Provider/AllenAI.py --------- Co-authored-by: kqlio67 <>
2025-12-06 02:30:41 -08:00 · 2025-02-24 14:53:20 +00:00 · 2025-02-24 14:53:20 +00:00 · 07a8dfdff7
commit 07a8dfdff7
parent f23f66518b
15 changed files with 422 additions and 238 deletions
--- a/docs/providers-and-models.md
+++ b/docs/providers-and-models.md
@ -37,14 +37,14 @@ This document provides an overview of various AI providers and models, including
 ### Providers No auth required
 | Website | API Credentials | Provider | Text Models | Image Models | Vision (Image Upload) | Stream | Status |
 |----------|-------------|--------------|---------------|--------|--------|------|------|
-|[blackbox.ai](https://www.blackbox.ai)|No auth required|`g4f.Provider.Blackbox`|`blackboxai, gpt-4, gpt-4o, o3-mini, gemini-1.5-flash, gemini-1.5-pro, blackboxai-pro, llama-3.1-8b, llama-3.1-70b, llama-3-1-405b, llama-3.3-70b, mixtral-small-28b, deepseek-chat, dbrx-instruct, qwq-32b, hermes-2-dpo, deepseek-r1, gemini-2.0-flash` _**(+32)**_|`flux`|`blackboxai, gpt-4o, o3-mini, gemini-1.5-pro, gemini-1.5-flash, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b, gemini-2.0-flash`|✔|![](https://img.shields.io/badge/Active-brightgreen)|
-|[api.blackbox.ai](https://api.blackbox.ai)|No auth required|`g4f.Provider.BlackboxAPI`|`deepseek-v3, deepseek-r1, deepseek-chat, mixtral-small-28b, dbrx-instruct, qwq-32b, hermes-2-dpo`|❌|❌|✔|![](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)|
+|[blackbox.ai](https://www.blackbox.ai)|No auth required|`g4f.Provider.Blackbox`|`blackboxai, gemini-1.5-flash, blackboxai-pro, llama-3.1-8b, llama-3.1-70b, llama-3-1-405b, llama-3.3-70b, mixtral-small-28b, deepseek-chat, dbrx-instruct, qwq-32b, hermes-2-dpo, deepseek-v3, deepseek-r1, gemini-2.0-flash` _**(+35)**_|`flux`|`blackboxai, gpt-4o, o3-mini, gemini-1.5-pro, gemini-1.5-flash, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b, gemini-2.0-flash`|✔|![](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.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)|❌|
 |[copilot.microsoft.com](https://copilot.microsoft.com)|Optional API key|`g4f.Provider.Copilot`|`gpt-4, gpt-4o`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|
-|[duckduckgo.com/aichat](https://duckduckgo.com/aichat)|No auth required|`g4f.Provider.DDG`|`o3-mini, gpt-4, gpt-4o-mini, claude-3-haiku, llama-3.3-70b, mixtral-8x7b`|❌|❌|✔|![](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-28b, 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)|
 |[chat10.free2gpt.xyz](https://chat10.free2gpt.xyz)|No auth required|`g4f.Provider.Free2GPT`|`mistral-7b`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|
 |[freegptsnav.aifree.site](https://freegptsnav.aifree.site)|No auth required|`g4f.Provider.FreeGpt`|`gemini-1.5-pro`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|
@ -55,9 +55,9 @@ This document provides an overview of various AI providers and models, including
 |[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`|`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-haiku, 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)|
-|[liaobots.work](https://liaobots.work)|[Automatic cookies](https://liaobots.work)|`g4f.Provider.Liaobots`|`grok-2, gpt-4o-mini, gpt-4o, gpt-4, o1-preview, o1-mini, deepseek-r1, deepseek-v3, claude-3-opus, claude-3.5-sonnet, claude-3-sonnet, gemini-1.5-flash, gemini-1.5-pro, gemini-2.0-flash, gemini-2.0-flash-thinking`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|
+|[liaobots.work](https://liaobots.work)|[Automatic cookies](https://liaobots.work)|`g4f.Provider.Liaobots`|`gpt-4o-mini, gpt-4o, gpt-4, o1-preview, deepseek-r1, deepseek-v3, claude-3-opus, claude-3.5-sonnet, claude-3-sonnet, gemini-2.0-flash, gemini-2.0-flash-thinking, grok-3, grok-3-r1, o3-mini`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|
 |[mhystical.cc](https://mhystical.cc)|[Optional API key](https://mhystical.cc/dashboard)|`g4f.Provider.Mhystical`|`gpt-4`|❌|❌|✔|![Error](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`|❌|`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)|
 |[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)|
@ -92,7 +92,7 @@ This document provides an overview of various AI providers and models, including
 |[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)|
 |[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, gemini-1.5-flash, gemini-1.5-pro`|`gemini`|`gemini`|❌|![](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)|
 |[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)|
@ -120,13 +120,12 @@ This document provides an overview of various AI providers and models, including
 ### Text Models
 | Model | Base Provider | Providers | Website |
 |-------|---------------|-----------|---------|
-|gpt-4|OpenAI|9+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4)|
-|gpt-4o|OpenAI|7+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4o)|
+|gpt-4|OpenAI|8+ 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-mini|OpenAI|7+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4o-mini)|
 |o1|OpenAI|1+ Providers|[openai.com](https://openai.com/index/introducing-openai-o1-preview/)|
 |o1-preview|OpenAI|1+ 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/)|
-|o3-mini|OpenAI|1+ Providers|[openai.com](https://openai.com/index/openai-o3-mini/)|
+|o3-mini|OpenAI|2+ Providers|[openai.com](https://openai.com/index/openai-o3-mini/)|
 |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/)|
 |llama-2-7b|Meta Llama|1+ Providers|[huggingface.co](https://huggingface.co/meta-llama/Llama-2-7b)|
@ -140,19 +139,20 @@ This document provides an overview of various AI providers and models, including
 |llama-3.2-11b|Meta Llama|3+ Providers|[ai.meta.com](https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/)|
 |llama-3.2-90b|Meta Llama|1+ Providers|[huggingface.co](https://huggingface.co/meta-llama/Llama-3.2-90B-Vision)|
 |llama-3.3-70b|Meta Llama|6+ Providers|[ai.meta.com](https://ai.meta.com/blog/llama-3-3/)|
-|mixtral-8x7b|Mistral|2+ Providers|[mistral.ai](https://mistral.ai/news/mixtral-of-experts/)|
+|mixtral-8x7b|Mistral|1+ Providers|[mistral.ai](https://mistral.ai/news/mixtral-of-experts/)|
 |mixtral-8x22b|Mistral|1+ Providers|[huggingface.co](https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1)|
 |mistral-nemo|Mistral|3+ Providers|[huggingface.co](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)|
+|mixtral-small-24b|Mistral|1+ Providers|[huggingface.co](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501)|
 |mixtral-small-28b|Mistral|3+ Providers|[mistral.ai](https://mistral.ai/news/mixtral-small-28b/)|
-|hermes-2-dpo|NousResearch|2+ Providers|[huggingface.co](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO)|
+|hermes-2-dpo|NousResearch|1+ Providers|[huggingface.co](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO)|
 |phi-3.5-mini|Microsoft|1+ Providers|[huggingface.co](https://huggingface.co/microsoft/Phi-3.5-mini-instruct)|
 |phi-4|Microsoft|1+ 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-2-8x22b|Microsoft|2+ Providers|[wizardlm.github.io](https://wizardlm.github.io/WizardLM2/)|
-|gemini|Google DeepMind|1+|[deepmind.google](http://deepmind.google/technologies/gemini/)|
+|gemini-2.0|Google DeepMind|1+|[deepmind.google](http://deepmind.google/technologies/gemini/)|
 |gemini-exp|Google DeepMind|1+ Providers|[blog.google](https://blog.google/feed/gemini-exp-1206/)|
-|gemini-1.5-flash|Google DeepMind|5+ Providers|[deepmind.google](https://deepmind.google/technologies/gemini/flash/)|
-|gemini-1.5-pro|Google DeepMind|5+ Providers|[deepmind.google](https://deepmind.google/technologies/gemini/pro/)|
+|gemini-1.5-flash|Google DeepMind|3+ Providers|[deepmind.google](https://deepmind.google/technologies/gemini/flash/)|
+|gemini-1.5-pro|Google DeepMind|2+ Providers|[deepmind.google](https://deepmind.google/technologies/gemini/pro/)|
 |gemini-2.0-flash|Google DeepMind|4+ Providers|[deepmind.google](https://deepmind.google/technologies/gemini/flash/)|
 |gemini-2.0-flash-thinking|Google DeepMind|1+ Providers|[ai.google.dev](https://ai.google.dev/gemini-api/docs/thinking-mode)|
 |claude-3-haiku|Anthropic|2+ Providers|[anthropic.com](https://www.anthropic.com/news/claude-3-haiku)|
@ -171,19 +171,21 @@ This document provides an overview of various AI providers and models, including
 |qwen-2.5-72b|Qwen|2+ 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-2.5-1m-demo|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2.5-1M-Demo)|
-|qwq-32b|Qwen|4+ Providers|[huggingface.co](https://huggingface.co/Qwen/QwQ-32B-Preview)|
+|qwq-32b|Qwen|3+ Providers|[huggingface.co](https://huggingface.co/Qwen/QwQ-32B-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)|
-|deepseek-chat|DeepSeek|4+ Providers|[huggingface.co](https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat)|
+|deepseek-chat|DeepSeek|3+ 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-r1|DeepSeek|9+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/news/news250120)|
-|grok-2|x.ai|1+|[x.ai](https://x.ai/blog/grok-2)|
+|deepseek-r1|DeepSeek|8+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/news/news250120)|
+|grok-3|x.ai|1+|[x.ai](https://x.ai/blog/grok-3)|
+|grok-3-r1|x.ai|1+|[x.ai](https://x.ai/blog/grok-3)|
 |sonar|Perplexity AI|1+ Providers|[sonar.perplexity.ai](https://sonar.perplexity.ai/)|
 |sonar-pro|Perplexity AI|1+ Providers|[sonar.perplexity.ai](https://sonar.perplexity.ai/)|
 |sonar-reasoning|Perplexity AI|1+ Providers|[sonar.perplexity.ai](https://sonar.perplexity.ai/)|
 |sonar-reasoning-pro|Perplexity AI|1+ Providers|[sonar.perplexity.ai](https://sonar.perplexity.ai/)|
+|r1-1776|Perplexity AI|1+ Providers|[perplexity.ai](https://www.perplexity.ai/hub/blog/open-sourcing-r1-1776)|
 |nemotron-70b|Nvidia|2+ Providers|[build.nvidia.com](https://build.nvidia.com/nvidia/llama-3_1-nemotron-70b-instruct)|
-|dbrx-instruct|Databricks|3+ Providers|[huggingface.co](https://huggingface.co/databricks/dbrx-instruct)|
+|dbrx-instruct|Databricks|2+ Providers|[huggingface.co](https://huggingface.co/databricks/dbrx-instruct)|
 |glm-4|THUDM|1+ Providers|[github.com/THUDM](https://github.com/THUDM/GLM-4)|
 |mini_max|MiniMax|1+ Providers|[hailuo.ai](https://www.hailuo.ai/)|
 |yi-34b|01-ai|1+ Providers|[huggingface.co](https://huggingface.co/01-ai/Yi-34B-Chat)|
@ -192,6 +194,11 @@ This document provides an overview of various AI providers and models, including
 |airoboros-70b|DeepInfra|1+ Providers|[huggingface.co](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-llama-3-70b)|
 |lzlv-70b|Lizpreciatior|1+ Providers|[huggingface.co](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-llama-3-70b)|
 |minicpm-2.5|OpenBMB|1+ Providers|[huggingface.co](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5)|
+|tulu-3-405b|Ai2|1+ Providers|[allenai.org](https://allenai.org/documentation)|
+|olmo-2-13b|Ai2|1+ Providers|[allenai.org](https://allenai.org/documentation)|
+|tulu-3-1-8b|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)|
 |evil|Evil Mode - Experimental|1+ Providers|[]( )|

 ---
--- a/g4f/Provider/AllenAI.py
+++ b/g4f/Provider/AllenAI.py
@ -0,0 +1,176 @@
+from __future__ import annotations
+import json
+from uuid import uuid4
+from aiohttp import ClientSession
+from ..typing import AsyncResult, Messages
+from .base_provider import AsyncGeneratorProvider, ProviderModelMixin
+from ..requests.raise_for_status import raise_for_status
+from ..providers.response import FinishReason, JsonConversation
+from .helper import format_prompt
+
+
+class Conversation(JsonConversation):
+    parent: str = None
+    x_anonymous_user_id: str = None
+
+    def __init__(self, model: str):
+        super().__init__()  # Ensure parent class is initialized
+        self.model = model
+        self.messages = []  # Instance-specific list
+        if not self.x_anonymous_user_id:
+            self.x_anonymous_user_id = str(uuid4())
+
+
+class AllenAI(AsyncGeneratorProvider, ProviderModelMixin):
+    label = "Ai2 Playground"
+    url = "https://playground.allenai.org"
+    login_url = None
+    api_endpoint = "https://olmo-api.allen.ai/v4/message/stream"
+    
+    working = True
+    needs_auth = False
+    use_nodriver = False
+    supports_stream = True
+    supports_system_message = False
+    supports_message_history = True
+
+    default_model = 'tulu3-405b'
+    models = [
+        default_model,
+        'OLMo-2-1124-13B-Instruct',
+        'tulu-3-1-8b',
+        'Llama-3-1-Tulu-3-70B',
+        'olmoe-0125'
+    ]
+    
+    model_aliases = {
+        "tulu-3-405b": default_model,
+        "olmo-2-13b": "OLMo-2-1124-13B-Instruct",
+        "tulu-3-1-8b": "tulu-3-1-8b",
+        "tulu-3-70b": "Llama-3-1-Tulu-3-70B",
+    }
+
+    @classmethod
+    async def create_async_generator(
+        cls,
+        model: str,
+        messages: Messages,
+        proxy: str = None,
+        host: str = "inferd",
+        private: bool = True,
+        parent: str = None,
+        top_p: float = None,
+        temperature: float = None,
+        conversation: Conversation = None,
+        return_conversation: bool = False,
+        **kwargs
+    ) -> AsyncResult:
+        # Initialize or update conversation
+        if conversation is None:
+            conversation = Conversation(model)
+        
+        # Generate new boundary for each request
+        boundary = f"----WebKitFormBoundary{uuid4().hex}"
+        
+        headers = {
+            "accept": "*/*",
+            "accept-language": "en-US,en;q=0.9",
+            "content-type": f"multipart/form-data; boundary={boundary}",
+            "origin": cls.url,
+            "referer": f"{cls.url}/",
+            "user-agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36",
+            "x-anonymous-user-id": conversation.x_anonymous_user_id,
+        }
+        
+        # Build multipart form data
+        form_data = [
+            f'--{boundary}\r\n'
+            f'Content-Disposition: form-data; name="model"\r\n\r\n{model}\r\n',
+            
+            f'--{boundary}\r\n'
+            f'Content-Disposition: form-data; name="host"\r\n\r\n{host}\r\n',
+            
+            f'--{boundary}\r\n'
+            f'Content-Disposition: form-data; name="content"\r\n\r\n{format_prompt(messages)}\r\n',
+            
+            f'--{boundary}\r\n'
+            f'Content-Disposition: form-data; name="private"\r\n\r\n{str(private).lower()}\r\n'
+        ]
+        
+        # Add parent if exists in conversation
+        if conversation.parent:
+            form_data.append(
+                f'--{boundary}\r\n'
+                f'Content-Disposition: form-data; name="parent"\r\n\r\n{conversation.parent}\r\n'
+            )
+        
+        # Add optional parameters
+        if temperature is not None:
+            form_data.append(
+                f'--{boundary}\r\n'
+                f'Content-Disposition: form-data; name="temperature"\r\n\r\n{temperature}\r\n'
+            )
+        
+        if top_p is not None:
+            form_data.append(
+                f'--{boundary}\r\n'
+                f'Content-Disposition: form-data; name="top_p"\r\n\r\n{top_p}\r\n'
+            )
+        
+        form_data.append(f'--{boundary}--\r\n')
+        data = "".join(form_data).encode()
+
+        async with ClientSession(headers=headers) as session:
+            async with session.post(
+                cls.api_endpoint,
+                data=data,
+                proxy=proxy,
+            ) as response:
+                await raise_for_status(response)
+                current_parent = None
+                
+                async for chunk in response.content:
+                    if not chunk:
+                        continue
+                    decoded = chunk.decode(errors="ignore")
+                    for line in decoded.splitlines():
+                        line = line.strip()
+                        if not line:
+                            continue
+                        
+                        try:
+                            data = json.loads(line)
+                        except json.JSONDecodeError:
+                            continue
+                        
+                        if isinstance(data, dict):
+                            # Update the parental ID
+                            if data.get("children"):
+                                for child in data["children"]:
+                                    if child.get("role") == "assistant":
+                                        current_parent = child.get("id")
+                                        break
+                            
+                            # We process content only from the assistant
+                            if "message" in data and data.get("content"):
+                                content = data["content"]
+                                # Skip empty content blocks
+                                if content.strip():
+                                    yield content
+                            
+                            # Processing the final response
+                            if data.get("final") or data.get("finish_reason") == "stop":
+                                if current_parent:
+                                    conversation.parent = current_parent
+                                
+                                # Add a message to the story
+                                conversation.messages.extend([
+                                    {"role": "user", "content": format_prompt(messages)},
+                                    {"role": "assistant", "content": "".join(conversation.messages[-1]["content"] + content if conversation.messages else content)}
+                                ])
+                                
+                                if return_conversation:
+                                    yield conversation
+                                
+                                yield FinishReason("stop")
+                                return
--- a/g4f/Provider/Blackbox.py
+++ b/g4f/Provider/Blackbox.py
@ -7,7 +7,6 @@ import random
 import string
 from pathlib import Path
 from typing import Optional
-from datetime import datetime, timezone

 from ..typing import AsyncResult, Messages, ImagesType
 from ..requests.raise_for_status import raise_for_status
@ -36,14 +35,16 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):
    supports_system_message = True
    supports_message_history = True
    
-    default_model = "blackboxai"
+    default_model = "BLACKBOXAI"
    default_vision_model = default_model
    default_image_model = 'ImageGeneration' 
    
    image_models = [default_image_model]   
    vision_models = [default_vision_model, 'GPT-4o', 'o3-mini', 'Gemini-PRO', 'gemini-1.5-flash', 'llama-3.1-8b', 'llama-3.1-70b', 'llama-3.1-405b', 'Gemini-Flash-2.0']
    
-    userSelectedModel = ['GPT-4o', 'o3-mini', 'Gemini-PRO', 'Claude-Sonnet-3.5', 'DeepSeek-V3', 'DeepSeek-R1', 'blackboxai-pro', 'Meta-Llama-3.3-70B-Instruct-Turbo', 'Mistral-Small-24B-Instruct-2501', 'DeepSeek-LLM-Chat-(67B)', 'DBRX-Instruct', 'Qwen-QwQ-32B-Preview', 'Nous-Hermes-2-Mixtral-8x7B-DPO', 'Gemini-Flash-2.0']
+    premium_models = ['GPT-4o', 'o1', 'o3-mini', 'Gemini-PRO', 'Claude-Sonnet-3.5']
+
+    userSelectedModel = ['DeepSeek-V3', 'DeepSeek-R1', 'BLACKBOXAI-PRO', 'Meta-Llama-3.3-70B-Instruct-Turbo', 'Mistral-Small-24B-Instruct-2501', 'DeepSeek-LLM-Chat-(67B)', 'DBRX-Instruct', 'Qwen-QwQ-32B-Preview', 'Nous-Hermes-2-Mixtral-8x7B-DPO', 'Gemini-Flash-2.0'] + premium_models

    agentMode = {
        'DeepSeek-V3': {'mode': True, 'id': "deepseek-chat", 'name': "DeepSeek-V3"},
@ -58,6 +59,7 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):
    }

    trendingAgentMode = {
+        "o1": {'mode': True, 'id': 'o1'},
        "o3-mini": {'mode': True, 'id': 'o3-mini'},
        "gemini-1.5-flash": {'mode': True, 'id': 'Gemini'},
        "llama-3.1-8b": {'mode': True, 'id': "llama-3.1-8b"},
@ -75,9 +77,7 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):
        'PyTorch Agent': {'mode': True, 'id': "PyTorch Agent"},
        'React Agent': {'mode': True, 'id': "React Agent"},
        'Xcode Agent': {'mode': True, 'id': "Xcode Agent"},
-        'AngularJS Agent': {'mode': True, 'id': "AngularJS Agent"},
-        'blackboxai-pro': {'mode': True, 'id': "BLACKBOXAI-PRO"},
-        'repomap': {'mode': True, 'id': "repomap"},
+        'BLACKBOXAI-PRO': {'mode': True, 'id': "BLACKBOXAI-PRO"},
        'Heroku Agent': {'mode': True, 'id': "Heroku Agent"},
        'Godot Agent': {'mode': True, 'id': "Godot Agent"},
        'Go Agent': {'mode': True, 'id': "Go Agent"},
@ -97,16 +97,11 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):
        'builder Agent': {'mode': True, 'id': "builder Agent"},
    }
    
-    premium_models = ['Claude-Sonnet-3.5']
-    
    models = list(dict.fromkeys([default_model, *userSelectedModel, *image_models, *list(agentMode.keys()), *list(trendingAgentMode.keys())]))

    model_aliases = {
-        "gpt-4": "GPT-4o",
-        "gpt-4o": "GPT-4o",
-        "claude-3.5-sonnet": "Claude-Sonnet-3.5", # Premium
+        "blackboxai": "BLACKBOXAI",
        "gemini-1.5-flash": "gemini-1.5-flash",
-        "gemini-1.5-pro": "Gemini-PRO",
        "deepseek-v3": "DeepSeek-V3",
        "deepseek-r1": "DeepSeek-R1",
        "llama-3.3-70b": "Meta-Llama-3.3-70B-Instruct-Turbo",
@ -116,6 +111,7 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):
        "qwq-32b": "Qwen-QwQ-32B-Preview",
        "hermes-2-dpo": "Nous-Hermes-2-Mixtral-8x7B-DPO",
        "gemini-2.0-flash": "Gemini-Flash-2.0",
+        "blackboxai-pro": "BLACKBOXAI-PRO",
        "flux": "ImageGeneration",
    }

@ -261,9 +257,6 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):
                    "content": msg["content"],
                    "role": msg["role"]
                }
-                if msg["role"] == "assistant" and i == len(messages)-1:
-                    current_time = datetime.now(timezone.utc).isoformat(timespec='milliseconds').replace('+00:00', 'Z')
-                    current_msg["createdAt"] = current_time
                current_messages.append(current_msg)
            
            if images is not None:
@ -279,14 +272,6 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):
                    "title": ""
                }

-            # Calculate the value for expires + lastChecked
-            expires_iso = datetime.now(timezone.utc).isoformat(timespec='milliseconds').replace('+00:00', 'Z')
-            last_checked_millis = int(datetime.now().timestamp() * 1000)
-            
-            # Fake data of a premium user (temporarily working)
-            fake_session = {"user":{"name":"John Doe","email":"john.doe@gmail.com","image":"https://lh3.googleusercontent.com/a/ACg8ocK9X7mNpQ2vR4jH3tY8wL5nB1xM6fDS9JW2kLpTn4Vy3hR2xN4m=s96-c"},"expires":expires_iso}
-            fake_subscriptionCache = {"status":"PREMIUM", "expiryTimestamp":None,"lastChecked":last_checked_millis}
-
            data = {
                "messages": current_messages,
                "agentMode": cls.agentMode.get(model, {}) if model in cls.agentMode else {},
@ -316,10 +301,17 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):
                "domains": None,
                "vscodeClient": False,
                "codeInterpreterMode": False,
-                "customProfile": {"name": "", "occupation": "", "traits": [], "additionalInfo": "", "enableNewChats": False},
-                "session": fake_session,
-                "isPremium": True, 
-                "subscriptionCache": fake_subscriptionCache,
+                "customProfile": {
+                    "name": "",
+                    "occupation": "",
+                    "traits": [],
+                    "additionalInfo": "",
+                    "enableNewChats": False
+                },
+                "session": None,
+                "isPremium": False, 
+                "subscriptionCache": None,
+                "beastMode": False,
                "webSearchMode": False
            }
            
--- a/g4f/Provider/BlackboxAPI.py
+++ b/g4f/Provider/BlackboxAPI.py
@ -1,75 +0,0 @@
-from __future__ import annotations
-from aiohttp import ClientSession
-
-from ..typing import AsyncResult, Messages
-from .base_provider import AsyncGeneratorProvider, ProviderModelMixin
-from ..requests.raise_for_status import raise_for_status
-
-class BlackboxAPI(AsyncGeneratorProvider, ProviderModelMixin):
-    label = "Blackbox AI API"
-    url = "https://api.blackbox.ai"
-    api_endpoint = "https://api.blackbox.ai/api/chat"
-    
-    working = True
-    needs_auth = False
-    supports_stream = False
-    supports_system_message = True
-    supports_message_history = True
-    
-    default_model = 'deepseek-ai/DeepSeek-V3'
-    models = [
-        default_model,
-        'deepseek-ai/DeepSeek-R1',
-        'mistralai/Mistral-Small-24B-Instruct-2501',
-        'deepseek-ai/deepseek-llm-67b-chat',
-        'databricks/dbrx-instruct',
-        'Qwen/QwQ-32B-Preview',
-        'NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO'
-    ]
-    
-    model_aliases = {       
-        "deepseek-v3": "deepseek-ai/DeepSeek-V3",
-        "deepseek-r1": "deepseek-ai/DeepSeek-R1",
-        "deepseek-chat": "deepseek-ai/deepseek-llm-67b-chat",
-        "mixtral-small-28b": "mistralai/Mistral-Small-24B-Instruct-2501",
-        "dbrx-instruct": "databricks/dbrx-instruct",
-        "qwq-32b": "Qwen/QwQ-32B-Preview",
-        "hermes-2-dpo": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
-    }
-
-    @classmethod
-    async def create_async_generator(
-        cls,
-        model: str,
-        messages: Messages,
-        proxy: str = None,
-        max_tokens: str = None,
-        **kwargs
-    ) -> AsyncResult:
-        model = cls.get_model(model)
-        
-        headers = {
-            "Content-Type": "application/json",
-        }
-        
-        async with ClientSession(headers=headers) as session:
-            data = {
-                "messages": messages,
-                "model": model,
-                "max_tokens": max_tokens
-            }
-            
-            async with session.post(cls.api_endpoint, json=data, proxy=proxy) as response:
-                await raise_for_status(response)
-                
-                async for chunk in response.content:
-                    if not chunk:
-                        continue
-                    
-                    text = chunk.decode(errors='ignore')
-                    
-                    try:
-                        if text:
-                            yield text
-                    except Exception as e:
-                        return
--- a/g4f/Provider/ChatGLM.py
+++ b/g4f/Provider/ChatGLM.py
@ -8,6 +8,7 @@ from aiohttp import ClientSession
 from ..typing import AsyncResult, Messages
 from ..requests.raise_for_status import raise_for_status
 from .base_provider import AsyncGeneratorProvider, ProviderModelMixin
+from ..providers.response import FinishReason

 class ChatGLM(AsyncGeneratorProvider, ProviderModelMixin):
    url = "https://chatglm.cn"
@ -18,9 +19,8 @@ class ChatGLM(AsyncGeneratorProvider, ProviderModelMixin):
    supports_system_message = False
    supports_message_history = False
    
-    default_model = "all-tools-230b"
+    default_model = "glm-4"
    models = [default_model]
-    model_aliases = {"glm-4": default_model}

    @classmethod
    async def create_async_generator(
@ -85,9 +85,13 @@ class ChatGLM(AsyncGeneratorProvider, ProviderModelMixin):
                                if parts:
                                    content = parts[0].get('content', [])
                                    if content:
-                                        text = content[0].get('text', '')[yield_text:]
+                                        text_content = content[0].get('text', '')
+                                        text = text_content[yield_text:]
                                        if text:
                                            yield text
                                            yield_text += len(text)
+                                # Yield FinishReason when status is 'finish'
+                                if json_data.get('status') == 'finish':
+                                    yield FinishReason("stop")
                            except json.JSONDecodeError:
                                pass
--- a/g4f/Provider/DDG.py
+++ b/g4f/Provider/DDG.py
@ -36,12 +36,12 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
    supports_message_history = True
    
    default_model = "gpt-4o-mini"
-    models = [default_model, "o3-mini", "claude-3-haiku-20240307", "meta-llama/Llama-3.3-70B-Instruct-Turbo", "mistralai/Mistral-Small-24B-Instruct-2501"]
+    models = [default_model, "meta-llama/Llama-3.3-70B-Instruct-Turbo", "claude-3-haiku-20240307", "o3-mini", "mistralai/Mistral-Small-24B-Instruct-2501"]

    model_aliases = {
        "gpt-4": "gpt-4o-mini",
-        "claude-3-haiku": "claude-3-haiku-20240307",
        "llama-3.3-70b": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
+        "claude-3-haiku": "claude-3-haiku-20240307",
        "mixtral-small-24b": "mistralai/Mistral-Small-24B-Instruct-2501",
    }

--- a/g4f/Provider/ImageLabs.py
+++ b/g4f/Provider/ImageLabs.py
@ -18,11 +18,10 @@ class ImageLabs(AsyncGeneratorProvider, ProviderModelMixin):
    supports_system_message = False
    supports_message_history = False
    
-    default_model = 'general'
+    default_model = 'sdxl-turbo'
    default_image_model = default_model
    image_models = [default_image_model]
    models = image_models
-    model_aliases = {"sdxl-turbo": default_model}

    @classmethod
    async def create_async_generator(
--- a/g4f/Provider/Liaobots.py
+++ b/g4f/Provider/Liaobots.py
@ -18,6 +18,51 @@ models = {
        "tokenLimit": 7800,
        "context": "8K",
    },
+    "grok-3": {
+        "id": "grok-3",
+        "name": "Grok-3",
+        "model": "Grok",
+        "provider": "x.ai",
+        "maxLength": 800000,
+        "tokenLimit": 200000,
+        "context": "200K",
+    },
+    "grok-3-r1": {
+        "id": "grok-3-r1",
+        "name": "Grok-3-Thinking",
+        "model": "Grok",
+        "provider": "x.ai",
+        "maxLength": 800000,
+        "tokenLimit": 200000,
+        "context": "200K",
+    },
+    "deepseek-r1": {
+        "id": "deepseek-r1",
+        "name": "DeepSeek-R1",
+        "model": "DeepSeek-R1",
+        "provider": "DeepSeek",
+        "maxLength": 400000,
+        "tokenLimit": 100000,
+        "context": "128K",
+    },
+    "deepseek-r1-distill-llama-70b": {
+        "id": "deepseek-r1-distill-llama-70b",
+        "name": "DeepSeek-R1-70B",
+        "model": "DeepSeek-R1-70B",
+        "provider": "DeepSeek",
+        "maxLength": 400000,
+        "tokenLimit": 100000,
+        "context": "128K",
+    },
+    "deepseek-v3": {
+        "id": "deepseek-v3",
+        "name": "DeepSeek-V3",
+        "model": "DeepSeek-V3",
+        "provider": "DeepSeek",
+        "maxLength": 400000,
+        "tokenLimit": 100000,
+        "context": "128K",
+    },
    "gpt-4o-2024-11-20": {
        "id": "gpt-4o-2024-11-20",
        "name": "GPT-4o",
@ -36,6 +81,15 @@ models = {
        "tokenLimit": 126000,
        "context": "128K",
    },
+    "o3-mini": {
+        "id": "o3-mini",
+        "name": "o3-mini",
+        "model": "o3",
+        "provider": "OpenAI",
+        "maxLength": 400000,
+        "tokenLimit": 100000,
+        "context": "128K",
+    },
    "o1-preview-2024-09-12": {
        "id": "o1-preview-2024-09-12",
        "name": "o1-preview",
@ -45,51 +99,6 @@ models = {
        "tokenLimit": 100000,
        "context": "128K",
    },
-    "o1-mini-2024-09-12": {
-        "id": "o1-mini-2024-09-12",
-        "name": "o1-mini",
-        "model": "o1",
-        "provider": "OpenAI",
-        "maxLength": 400000,
-        "tokenLimit": 100000,
-        "context": "128K",
-    },
-    "DeepSeek-R1-Distill-Llama-70b": {
-        "id": "DeepSeek-R1-Distill-Llama-70b",
-        "name": "DeepSeek-R1-70B",
-        "model": "DeepSeek-R1-70B",
-        "provider": "DeepSeek",
-        "maxLength": 400000,
-        "tokenLimit": 100000,
-        "context": "128K",
-    },
-    "DeepSeek-R1": {
-        "id": "DeepSeek-R1",
-        "name": "DeepSeek-R1",
-        "model": "DeepSeek-R1",
-        "provider": "DeepSeek",
-        "maxLength": 400000,
-        "tokenLimit": 100000,
-        "context": "128K",
-    },
-    "DeepSeek-V3": {
-        "id": "DeepSeek-V3",
-        "name": "DeepSeek-V3",
-        "model": "DeepSeek-V3",
-        "provider": "DeepSeek",
-        "maxLength": 400000,
-        "tokenLimit": 100000,
-        "context": "128K",
-    },
-    "grok-2": {
-        "id": "grok-2",
-        "name": "Grok-2",
-        "model": "Grok",
-        "provider": "x.ai",
-        "maxLength": 400000,
-        "tokenLimit": 100000,
-        "context": "100K",
-    },
    "claude-3-opus-20240229": {
        "id": "claude-3-opus-20240229",
        "name": "Claude-3-Opus",
@ -144,9 +153,9 @@ models = {
        "tokenLimit": 200000,
        "context": "200K",
    },
-    "gemini-2.0-flash-exp": {
-        "id": "gemini-2.0-flash-exp",
-        "name": "Gemini-2.0-Flash-Exp",
+    "gemini-2.0-flash": {
+        "id": "gemini-2.0-flash",
+        "name": "Gemini-2.0-Flash",
        "model": "Gemini",
        "provider": "Google",
        "maxLength": 4000000,
@ -162,18 +171,9 @@ models = {
        "tokenLimit": 1000000,
        "context": "1024K",
    },
-    "gemini-1.5-flash-002": {
-        "id": "gemini-1.5-flash-002",
-        "name": "Gemini-1.5-Flash-1M",
-        "model": "Gemini",
-        "provider": "Google",
-        "maxLength": 4000000,
-        "tokenLimit": 1000000,
-        "context": "1024K",
-    },
-    "gemini-1.5-pro-002": {
-        "id": "gemini-1.5-pro-002",
-        "name": "Gemini-1.5-Pro-1M",
+    "gemini-2.0-pro-exp": {
+        "id": "gemini-2.0-pro-exp",
+        "name": "Gemini-2.0-Pro-Exp",
        "model": "Gemini",
        "provider": "Google",
        "maxLength": 4000000,
@ -197,11 +197,8 @@ class Liaobots(AsyncGeneratorProvider, ProviderModelMixin):
        "gpt-4": default_model,
        
        "o1-preview": "o1-preview-2024-09-12",
-        "o1-mini": "o1-mini-2024-09-12",
        
-        "deepseek-r1": "DeepSeek-R1-Distill-Llama-70b",
-        "deepseek-r1": "DeepSeek-R1",
-        "deepseek-v3": "DeepSeek-V3",
+        "deepseek-r1": "deepseek-r1-distill-llama-70b",
        
        "claude-3-opus": "claude-3-opus-20240229",
        "claude-3.5-sonnet": "claude-3-5-sonnet-20240620",
@ -210,10 +207,7 @@ class Liaobots(AsyncGeneratorProvider, ProviderModelMixin):
        "claude-3-opus": "claude-3-opus-20240229-t",
        "claude-3.5-sonnet": "claude-3-5-sonnet-20241022-t",
        
-        "gemini-2.0-flash": "gemini-2.0-flash-exp",
        "gemini-2.0-flash-thinking": "gemini-2.0-flash-thinking-exp",
-        "gemini-1.5-flash": "gemini-1.5-flash-002",
-        "gemini-1.5-pro": "gemini-1.5-pro-002"
    }
    
    _auth_code = ""
--- a/g4f/Provider/OIVSCode.py
+++ b/g4f/Provider/OIVSCode.py
@ -5,7 +5,7 @@ from .template import OpenaiTemplate
 class OIVSCode(OpenaiTemplate):
    label = "OI VSCode Server"
    url = "https://oi-vscode-server.onrender.com"
-    api_base = "https://oi-vscode-server.onrender.com/v1"
+    api_base = "https://oi-vscode-server-2.onrender.com/v1"
    
    working = True
    needs_auth = False
@ -16,6 +16,9 @@ class OIVSCode(OpenaiTemplate):
    default_model = "gpt-4o-mini-2024-07-18"
    default_vision_model = default_model
    vision_models = [default_model, "gpt-4o-mini"]
-    models = vision_models
+    models = vision_models + ["deepseek-ai/DeepSeek-V3"]
    
-    model_aliases = {"gpt-4o-mini": "gpt-4o-mini-2024-07-18"}
+    model_aliases = {
+        "gpt-4o-mini": "gpt-4o-mini-2024-07-18",
+        "deepseek-v3": "deepseek-ai/DeepSeek-V3"
+    }
--- a/g4f/Provider/PollinationsAI.py
+++ b/g4f/Provider/PollinationsAI.py
@ -39,9 +39,12 @@ class PollinationsAI(AsyncGeneratorProvider, ProviderModelMixin):
    default_model = "openai"
    default_image_model = "flux"
    default_vision_model = "gpt-4o"
-    image_models = ["flux-pro", "flux-dev", "flux-schnell", "midjourney", "dall-e-3", "turbo"]
+    text_models = [default_model]
+    image_models = [default_image_model]
+    extra_image_models = ["flux-pro", "flux-dev", "flux-schnell", "midjourney", "dall-e-3"]
    vision_models = [default_vision_model, "gpt-4o-mini"]
    extra_text_models = ["claude", "claude-email", "deepseek-reasoner", "deepseek-r1"] + vision_models
+    _models_loaded = False
    model_aliases = {
        ### Text Models ###
        "gpt-4o-mini": "openai",
@ -66,27 +69,51 @@ class PollinationsAI(AsyncGeneratorProvider, ProviderModelMixin):
        ### Image Models ###
        "sdxl-turbo": "turbo",
    }
-    text_models = []

    @classmethod
    def get_models(cls, **kwargs):
-        if not cls.text_models or not cls.image_models:
+        if not cls._models_loaded:
            try:
+                # Update of image models
                image_response = requests.get("https://image.pollinations.ai/models")
                image_response.raise_for_status()
                new_image_models = image_response.json()
-                cls.image_models = list(dict.fromkeys([*cls.image_models, *new_image_models]))
                
+                # Combine models without duplicates
+                all_image_models = (
+                    cls.image_models +  # Already contains the default
+                    cls.extra_image_models + 
+                    new_image_models
+                )
+                cls.image_models = list(dict.fromkeys(all_image_models))
+
+                # Update of text models
                text_response = requests.get("https://text.pollinations.ai/models")
                text_response.raise_for_status()
-                original_text_models = [model.get("name") for model in text_response.json()]
+                original_text_models = [
+                    model.get("name") 
+                    for model in text_response.json()
+                ]
                
-                combined_text = cls.extra_text_models + [
+                # Combining text models
+                combined_text = (
+                    cls.text_models +  # Already contains the default
+                    cls.extra_text_models + 
+                    [
                        model for model in original_text_models
                        if model not in cls.extra_text_models
                    ]
+                )
                cls.text_models = list(dict.fromkeys(combined_text))
+                
+                cls._models_loaded = True
+
            except Exception as e:
+                # Save default models in case of an error
+                if not cls.text_models:
+                    cls.text_models = [cls.default_model]
+                if not cls.image_models:
+                    cls.image_models = [cls.default_image_model]
                raise RuntimeError(f"Failed to fetch models: {e}") from e
            
        return cls.text_models + cls.image_models
@ -114,6 +141,7 @@ class PollinationsAI(AsyncGeneratorProvider, ProviderModelMixin):
        cache: bool = False,
        **kwargs
    ) -> AsyncResult:
+        cls.get_models()
        if images is not None and not model:
            model = cls.default_vision_model
        try:
--- a/g4f/Provider/PollinationsImage.py
+++ b/g4f/Provider/PollinationsImage.py
@ -10,13 +10,23 @@ class PollinationsImage(PollinationsAI):
    default_model = "flux"
    default_vision_model = None
    default_image_model = default_model
+    image_models = [default_image_model]  # Default models
+    _models_loaded = False  # Add a checkbox for synchronization

    @classmethod
    def get_models(cls, **kwargs):
-        if not cls.models:
-            super().get_models(**kwargs)
-            cls.models = cls.image_models
-        return cls.models
+        if not cls._models_loaded:
+            # Calling the parent method to load models
+            super().get_models()
+            # Combine models from the parent class and additional ones
+            all_image_models = list(dict.fromkeys(
+                cls.image_models +
+                PollinationsAI.image_models +
+                cls.extra_image_models
+            ))
+            cls.image_models = all_image_models
+            cls._models_loaded = True
+        return cls.image_models

    @classmethod
    async def create_async_generator(
@ -35,6 +45,8 @@ class PollinationsImage(PollinationsAI):
        safe: bool = False,
        **kwargs
    ) -> AsyncResult:
+        # Calling model updates before creating a generator
+        cls.get_models()
        async for chunk in cls._generate_image(
            model=model,
            prompt=format_image_prompt(messages, prompt),
--- a/g4f/Provider/init.py
+++ b/g4f/Provider/init.py
@ -14,8 +14,8 @@ from .hf_space         import *
 from .mini_max         import HailuoAI, MiniMax
 from .template         import OpenaiTemplate, BackendApi

+from .AllenAI              import AllenAI
 from .Blackbox             import Blackbox
-from .BlackboxAPI          import BlackboxAPI
 from .ChatGLM              import ChatGLM
 from .ChatGpt              import ChatGpt
 from .ChatGptEs            import ChatGptEs
--- a/g4f/Provider/needs_auth/CablyAI.py
+++ b/g4f/Provider/needs_auth/CablyAI.py
@ -9,7 +9,7 @@ class CablyAI(OpenaiTemplate):
    api_base = "https://cablyai.com/v1"

    working = True
-    needs_auth = False
+    needs_auth = True
    supports_stream = True
    supports_system_message = True
    supports_message_history = True
--- a/g4f/models.py
+++ b/g4f/models.py
@ -5,8 +5,8 @@ from dataclasses import dataclass
 from .Provider import IterListProvider, ProviderType
 from .Provider import (
    ### no auth required ###
+    AllenAI,
    Blackbox,
-    BlackboxAPI,
    ChatGLM,
    ChatGptEs,
    Cloudflare,
@ -115,14 +115,14 @@ default_vision = Model(
 gpt_4 = Model(
    name          = 'gpt-4',
    base_provider = 'OpenAI',
-    best_provider = IterListProvider([Blackbox, DDG, Jmuz, ChatGptEs, PollinationsAI, Yqcloud, Copilot, OpenaiChat, Liaobots, Mhystical])
+    best_provider = IterListProvider([DDG, Jmuz, ChatGptEs, PollinationsAI, Yqcloud, Copilot, OpenaiChat, Liaobots, Mhystical])
 )

 # gpt-4o
 gpt_4o = VisionModel(
    name          = 'gpt-4o',
    base_provider = 'OpenAI',
-    best_provider = IterListProvider([Blackbox, Jmuz, ChatGptEs, PollinationsAI, Copilot, Liaobots, OpenaiChat])
+    best_provider = IterListProvider([Jmuz, ChatGptEs, PollinationsAI, Copilot, Liaobots, OpenaiChat])
 )

 gpt_4o_mini = Model(
@ -144,17 +144,11 @@ o1_preview = Model(
    best_provider = Liaobots
 )

-o1_mini = Model(
-    name          = 'o1-mini',
-    base_provider = 'OpenAI',
-    best_provider = Liaobots
-)
-
 # o3
 o3_mini = Model(
    name          = 'o3-mini',
    base_provider = 'OpenAI',
-    best_provider = IterListProvider([DDG, Blackbox])
+    best_provider = IterListProvider([DDG, Liaobots])
 )

 ### GigaChat ###
@ -268,14 +262,14 @@ mixtral_small_24b = Model(
 mixtral_small_28b = Model(
    name          = "mixtral-small-28b",
    base_provider = "Mistral",
-    best_provider = IterListProvider([Blackbox, BlackboxAPI, DeepInfraChat])
+    best_provider = IterListProvider([Blackbox, DeepInfraChat])
 )

 ### NousResearch ###
 hermes_2_dpo = Model(
    name          = "hermes-2-dpo",
    base_provider = "NousResearch",
-    best_provider = IterListProvider([Blackbox, BlackboxAPI])
+    best_provider = Blackbox
 )

 ### Microsoft ###
@ -324,13 +318,13 @@ gemini_exp = Model(
 gemini_1_5_flash = Model(
    name          = 'gemini-1.5-flash',
    base_provider = 'Google DeepMind',
-    best_provider = IterListProvider([Blackbox, Jmuz, GeminiPro, Liaobots])
+    best_provider = IterListProvider([Blackbox, Jmuz, GeminiPro])
 )

 gemini_1_5_pro = Model(
    name          = 'gemini-1.5-pro',
    base_provider = 'Google DeepMind',
-    best_provider = IterListProvider([Blackbox, Jmuz, GeminiPro, Liaobots])
+    best_provider = IterListProvider([Jmuz, GeminiPro])
 )

 # gemini-2.0
@ -449,7 +443,7 @@ qwen_2_5_1m = Model(
 qwq_32b = Model(
    name = 'qwq-32b',
    base_provider = 'Qwen',
-    best_provider = IterListProvider([Blackbox, BlackboxAPI, Jmuz, HuggingChat])
+    best_provider = IterListProvider([Blackbox, Jmuz, HuggingChat])
 )
 qvq_72b = VisionModel(
    name = 'qvq-72b',
@ -468,19 +462,19 @@ pi = Model(
 deepseek_chat = Model(
    name = 'deepseek-chat',
    base_provider = 'DeepSeek',
-    best_provider = IterListProvider([Blackbox, BlackboxAPI, Jmuz, PollinationsAI])
+    best_provider = IterListProvider([Blackbox, Jmuz, PollinationsAI])
 )

 deepseek_v3 = Model(
    name = 'deepseek-v3',
    base_provider = 'DeepSeek',
-    best_provider = IterListProvider([Blackbox, BlackboxAPI, DeepInfraChat, Liaobots])
+    best_provider = IterListProvider([Blackbox, DeepInfraChat, OIVSCode, Liaobots])
 )

 deepseek_r1 = Model(
    name = 'deepseek-r1',
    base_provider = 'DeepSeek',
-    best_provider = IterListProvider([Blackbox, BlackboxAPI, DeepInfraChat, Glider, PollinationsAI, Jmuz, Liaobots, HuggingChat, HuggingFace])
+    best_provider = IterListProvider([Blackbox, DeepInfraChat, Glider, PollinationsAI, Jmuz, Liaobots, HuggingChat, HuggingFace])
 )

 janus_pro_7b = VisionModel(
@ -490,8 +484,14 @@ janus_pro_7b = VisionModel(
 )

 ### x.ai ###
-grok_2 = Model(
-    name = 'grok-2',
+grok_3 = Model(
+    name = 'grok-3',
+    base_provider = 'x.ai',
+    best_provider = Liaobots
+)
+
+grok_3_r1 = Model(
+    name = 'grok-3-r1',
    base_provider = 'x.ai',
    best_provider = Liaobots
 )
@ -521,6 +521,12 @@ sonar_reasoning_pro = Model(
    best_provider = PerplexityLabs
 )

+r1_1776 = Model(
+    name = 'r1-1776',
+    base_provider = 'Perplexity AI',
+    best_provider = PerplexityLabs
+)
+
 ### Nvidia ### 
 nemotron_70b = Model(
    name = 'nemotron-70b',
@ -532,7 +538,7 @@ nemotron_70b = Model(
 dbrx_instruct = Model(
    name = 'dbrx-instruct',
    base_provider = 'Databricks',
-    best_provider = IterListProvider([Blackbox, BlackboxAPI, DeepInfraChat])
+    best_provider = IterListProvider([Blackbox, DeepInfraChat])
 )

 ### THUDM ### 
@ -590,6 +596,37 @@ minicpm_2_5 = Model(
    best_provider = DeepInfraChat
 )

+### Ai2 ###
+tulu_3_405b = Model(
+    name = "tulu-3-405b",
+    base_provider = "Ai2",
+    best_provider = AllenAI
+)
+
+olmo_2_13b = Model(
+    name = "olmo-2-13b",
+    base_provider = "Ai2",
+    best_provider = AllenAI
+)
+
+tulu_3_1_8b = Model(
+    name = "tulu-3-1-8b",
+    base_provider = "Ai2",
+    best_provider = AllenAI
+)
+
+tulu_3_70b = Model(
+    name = "tulu-3-70b",
+    base_provider = "Ai2",
+    best_provider = AllenAI
+)
+
+olmoe_0125 = Model(
+    name = "olmoe-0125",
+    base_provider = "Ai2",
+    best_provider = AllenAI
+)
+
 ### Uncensored AI ### 
 evil = Model(
    name = 'evil',
@ -678,7 +715,6 @@ class ModelUtils:
        # o1
        o1.name: o1,
        o1_preview.name: o1_preview,
-        o1_mini.name: o1_mini,
        
        # o3
        o3_mini.name: o3_mini,
@ -776,13 +812,14 @@ class ModelUtils:
        pi.name: pi,

        ### x.ai ###
-        grok_2.name: grok_2,
+        grok_3.name: grok_3,

        ### Perplexity AI ###
        sonar.name: sonar,
        sonar_pro.name: sonar_pro,
        sonar_reasoning.name: sonar_reasoning,
        sonar_reasoning_pro.name: sonar_reasoning_pro,
+        r1_1776.name: r1_1776,
        
        ### DeepSeek ###
        deepseek_chat.name: deepseek_chat,
@ -803,6 +840,13 @@ class ModelUtils:
        lzlv_70b.name: lzlv_70b, ### Lizpreciatior ###
        minicpm_2_5.name: minicpm_2_5, ### OpenBMB ###
        
+        ### Ai2 ###
+        tulu_3_405b.name: tulu_3_405b,
+        olmo_2_13b.name: olmo_2_13b,
+        tulu_3_1_8b.name: tulu_3_1_8b,
+        tulu_3_70b.name: tulu_3_70b,
+        olmoe_0125.name: olmoe_0125,
+        
        evil.name: evil, ### Uncensored AI ###
        
        #############