返回提交历史
Modified
docs/providers-and-models.md
+104
-99
Modified
g4f/Provider/ARTA.py
+1
-1
Modified
g4f/Provider/DDG.py
+174
-92
Modified
g4f/Provider/DeepInfraChat.py
+2
-37
Modified
g4f/Provider/LambdaChat.py
+2
-1
Modified
g4f/Provider/TypeGPT.py
+7
-6
Modified
g4f/Provider/hf_space/BlackForestLabs_Flux1Dev.py
+2
-2
Modified
g4f/Provider/hf_space/BlackForestLabs_Flux1Schnell.py
+2
-2
Modified
g4f/Provider/hf_space/CohereForAI_C4AI_Command.py
+4
-10
Modified
g4f/Provider/hf_space/DeepseekAI_JanusPro7b.py
+2
-1
Modified
g4f/Provider/hf_space/Microsoft_Phi_4.py
+3
-1
Modified
g4f/Provider/hf_space/Qwen_QVQ_72B.py
+4
-3
Added
g4f/Provider/hf_space/Qwen_Qwen_2_5.py
+146
-0
Renamed
g4f/Provider/hf_space/Qwen_Qwen_2_5M.py
+4
-3
Added
g4f/Provider/hf_space/Qwen_Qwen_2_5_Max.py
+133
-0
Renamed
g4f/Provider/hf_space/Qwen_Qwen_2_72B.py
+3
-3
Modified
g4f/Provider/hf_space/StabilityAI_SD35Large.py
+2
-2
Modified
g4f/Provider/hf_space/Voodoohop_Flux1Schnell.py
+1
-1
Modified
g4f/Provider/hf_space/__init__.py
+9
-5
Modified
g4f/models.py
+58
-11
XFEstudio/gpt4free
Standardize model configurations and enhance error handling (#2818)
* 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 <>
97f1964b
代码差异
20 个文件
+663
-280
@@ -1,13 +1,9 @@
1
2
3
4
1
# G4F - Providers and Models
5
2
6
3
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.
7
4
8
5
> **Note**: See our [Authentication Guide](authentication.md) for authentication instructions for the provider.
9
6
10
11
7
## Table of Contents
12
8
- [Providers](#providers)
13
9
- [No auth required](#providers-not-needs-auth)
@@ -38,106 +34,108 @@ This document provides an overview of various AI providers and models, including
38
34
39
35
---
40
36
### Providers No auth required
41
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Streaming | Status |
42
|----------|-------------|--------------|---------------|--------|--------|------|------|------|
43
|[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`|❌|❌|❌|✔||
44
|[ai-arta.com](https://ai-arta.com)|No auth required|`g4f.Provider.ARTA`|❌|✔ _**(17+)**_|❌|❌|❌||
45
|[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+)**_|✔||
46
|[chatglm.cn](https://chatglm.cn)|No auth required|`g4f.Provider.ChatGLM`|`glm-4`|❌|❌|❌|✔||
47
|[chatgpt.com](https://chatgpt.com)|No auth required|`g4f.Provider.ChatGpt`|✔ _**(7+)**_|❌|❌|❌|✔||
48
|[chatgpt.es](https://chatgpt.es)|No auth required|`g4f.Provider.ChatGptEs`|`gpt-4, gpt-4o, gpt-4o-mini`|❌|❌|❌|✔||
49
|[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`|❌|❌|❌|✔||❌|
50
|[copilot.microsoft.com](https://copilot.microsoft.com)|Optional API key|`g4f.Provider.Copilot`|`gpt-4, o1`|❌|❌|❌|✔||
51
|[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`|❌|❌|❌|✔||
52
|[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`|✔||
53
|[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`|✔||
54
|[chat10.free2gpt.xyz](https://chat10.free2gpt.xyz)|No auth required|`g4f.Provider.Free2GPT`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌|✔||
55
|[freegptsnav.aifree.site](https://freegptsnav.aifree.site)|No auth required|`g4f.Provider.FreeGpt`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌|✔||
56
|[app.giz.ai/assistant](https://app.giz.ai/assistant)|No auth required|`g4f.Provider.GizAI`|`gemini-1.5-flash`|❌|❌|❌|✔||
57
|[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`|❌|❌|❌|✔||
58
|[goabror.uz](https://goabror.uz)|No auth required|`g4f.Provider.Goabror`|`gpt-4`|❌|❌|❌|✔||
59
|[hailuo.ai](https://www.hailuo.ai)|No auth required|`g4f.Provider.HailuoAI`|`MiniMax` _**(1+)**_|❌|❌|❌|✔||
60
|[editor.imagelabs.net](editor.imagelabs.net)|No auth required|`g4f.Provider.ImageLabs`|❌|`sdxl-turbo`|❌|❌|✔||
61
|[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`|❌|❌|✔||
62
|[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`|❌|❌|❌|✔||
63
|[lambda.chat](https://lambda.chat)|No auth required|`g4f.Provider.LambdaChat`|`deepseek-v3, deepseek-r1, hermes-3, nemotron-70b, llama-3.3-70b`|❌|❌|❌|✔||
64
|[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`|❌|❌|❌|✔||
65
|[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`|✔||
66
|[labs.perplexity.ai](https://labs.perplexity.ai)|No auth required|`g4f.Provider.PerplexityLabs`|`sonar, sonar-pro, sonar-reasoning, sonar-reasoning-pro`|❌|❌|❌|✔||
67
|[pi.ai/talk](https://pi.ai/talk)|[Manual cookies](https://pi.ai/talk)|`g4f.Provider.Pi`|`pi`|❌|❌|❌|✔||
68
|[pizzagpt.it](https://www.pizzagpt.it)|No auth required|`g4f.Provider.Pizzagpt`|`gpt-4o-mini`|❌|❌|❌|✔||
69
|[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`|❌|✔||
70
|[pollinations.ai](https://pollinations.ai)|No auth required|`g4f.Provider.PollinationsImage`|❌|`flux, flux-pro, flux-dev, flux-schnell, dall-e-3, sdxl-turbo`|❌|❌|✔||
71
|[teach-anything.com](https://www.teach-anything.com)|No auth required|`g4f.Provider.TeachAnything`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌|✔||
72
|[you.com](https://you.com)|[Manual cookies](https://you.com)|`g4f.Provider.You`|✔|✔|❌|✔|✔||
73
|[websim.ai](https://websim.ai)|No auth required|`g4f.Provider.Websim`|`gemini-1.5-pro, gemini-1.5-flash`|`flux`|❌|❌|✔||
74
|[chat9.yqcloud.top](https://chat9.yqcloud.top)|No auth required|`g4f.Provider.Yqcloud`|`gpt-4`|✔|❌|❌|✔||
37
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Status |
38
|----------|-------------|--------------|---------------|--------|--------|------|------|
39
|[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`|❌|❌|❌||
40
|[ai-arta.com](https://ai-arta.com)|No auth required|`g4f.Provider.ARTA`|❌|✔ _**(17+)**_|❌|❌||
41
|[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+)**_||
42
|[chatglm.cn](https://chatglm.cn)|No auth required|`g4f.Provider.ChatGLM`|`glm-4`|❌|❌|❌||
43
|[chatgpt.com](https://chatgpt.com)|No auth required|`g4f.Provider.ChatGpt`|✔ _**(7+)**_|❌|❌|❌||
44
|[chatgpt.es](https://chatgpt.es)|No auth required|`g4f.Provider.ChatGptEs`|`gpt-4, gpt-4o, gpt-4o-mini`|❌|❌|❌||
45
|[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`|❌|❌|❌||
46
|[copilot.microsoft.com](https://copilot.microsoft.com)|Optional API key|`g4f.Provider.Copilot`|`gpt-4, o1`|❌|❌|❌||
47
|[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`|❌|❌|❌||
48
|[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`||
49
|[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`||
50
|[chat10.free2gpt.xyz](https://chat10.free2gpt.xyz)|No auth required|`g4f.Provider.Free2GPT`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌||
51
|[freegptsnav.aifree.site](https://freegptsnav.aifree.site)|No auth required|`g4f.Provider.FreeGpt`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌||
52
|[app.giz.ai/assistant](https://app.giz.ai/assistant)|No auth required|`g4f.Provider.GizAI`|`gemini-1.5-flash`|❌|❌|❌||
53
|[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`|❌|❌|❌||
54
|[goabror.uz](https://goabror.uz)|No auth required|`g4f.Provider.Goabror`|`gpt-4`|❌|❌|❌||
55
|[hailuo.ai](https://www.hailuo.ai)|No auth required|`g4f.Provider.HailuoAI`|`MiniMax` _**(1+)**_|❌|❌|❌||
56
|[editor.imagelabs.net](editor.imagelabs.net)|No auth required|`g4f.Provider.ImageLabs`|❌|`sdxl-turbo`|❌|❌||
57
|[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`|❌|❌||
58
|[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`|❌|❌|❌||
59
|[lambda.chat](https://lambda.chat)|No auth required|`g4f.Provider.LambdaChat`|`deepseek-v3, deepseek-r1, hermes-3, nemotron-70b, llama-3.3-70b`|❌|❌|❌||
60
|[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`|❌|❌|❌||
61
|[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`||
62
|[labs.perplexity.ai](https://labs.perplexity.ai)|No auth required|`g4f.Provider.PerplexityLabs`|`sonar, sonar-pro, sonar-reasoning, sonar-reasoning-pro`|❌|❌|❌||
63
|[pi.ai/talk](https://pi.ai/talk)|[Manual cookies](https://pi.ai/talk)|`g4f.Provider.Pi`|`pi`|❌|❌|❌||
64
|[pizzagpt.it](https://www.pizzagpt.it)|No auth required|`g4f.Provider.Pizzagpt`|`gpt-4o-mini`|❌|❌|❌||
65
|[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`||
66
|[pollinations.ai](https://pollinations.ai)|No auth required|`g4f.Provider.PollinationsImage`|❌|`flux, flux-pro, flux-dev, flux-schnell, dall-e-3, sdxl-turbo`|❌|❌||
67
|[teach-anything.com](https://www.teach-anything.com)|No auth required|`g4f.Provider.TeachAnything`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌||
68
|[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`||
69
|[you.com](https://you.com)|[Manual cookies](https://you.com)|`g4f.Provider.You`|✔|✔|❌|✔||
70
|[websim.ai](https://websim.ai)|No auth required|`g4f.Provider.Websim`|`gemini-1.5-pro, gemini-1.5-flash`|`flux`|❌|❌||
71
|[chat9.yqcloud.top](https://chat9.yqcloud.top)|No auth required|`g4f.Provider.Yqcloud`|`gpt-4`|✔|❌|❌||
75
72
76
73
---
77
74
### Providers HuggingFace
78
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Streaming | Status |
79
|----------|-------------|--------------|---------------|--------|--------|------|------|------|
80
|[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`|❌|❌|✔||
81
|[huggingface.co/chat](https://huggingface.co/chat)|[API key / Cookies](https://huggingface.co/settings/tokens)|`g4f.Provider.HuggingFace`|✔ _**(47+)**_|✔ _**(9+)**_|❌|❌|✔||
82
|[api-inference.huggingface.co](https://api-inference.huggingface.co)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.HuggingFaceAPI`|✔ _**(9+)**_|✔ _**(2+)**_|❌|✔ _**(1+)**_|❌||✔|
75
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Status |
76
|----------|-------------|--------------|---------------|--------|--------|------|------|
77
|[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`|❌|❌||
78
|[huggingface.co/chat](https://huggingface.co/chat)|[API key / Cookies](https://huggingface.co/settings/tokens)|`g4f.Provider.HuggingFace`|✔ _**(47+)**_|✔ _**(9+)**_|❌|❌||
79
|[api-inference.huggingface.co](https://api-inference.huggingface.co)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.HuggingFaceAPI`|✔ _**(9+)**_|✔ _**(2+)**_|❌|✔ _**(1+)**_||
83
80
84
81
---
85
82
### Providers HuggingSpace
86
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Streaming | Status |
87
|----------|-------------|--------------|---------------|--------|--------|------|------|------|
88
|[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`|❌|❌|✔||
89
|[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`|❌|❌|✔||
90
|[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`|❌|❌|❌|✔||
91
|[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`|✔|✔|❌|❌|✔||
92
|[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+)**_|✔||
93
|[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+)**_|✔||
94
|[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`|❌|❌|❌|✔||
95
|[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`|❌|❌|❌|✔||
96
|[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`|❌|❌|❌|✔||
97
|[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`|❌|❌|✔||
98
|[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`|❌|❌|✔||
83
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Status |
84
|----------|-------------|--------------|---------------|--------|--------|------|------|
85
|[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`|❌|❌||
86
|[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`|❌|❌||
87
|[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`|❌|❌|❌||
88
|[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`|✔|✔|❌|❌||
89
|[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+)**_||
90
|[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`||
91
|[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`|❌|❌|❌||
92
|[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`|❌|❌|❌||
93
|[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`|❌|❌|❌||
94
|[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`|❌|❌|❌||
95
|[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`|❌|❌|❌||
96
|[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`|❌|❌||
97
|[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`|❌|❌||
99
98
100
99
### Providers Local
101
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Streaming | Status |
102
|----------|-------------|--------------|---------------|--------|--------|------|------|------|
103
|[]( )|No auth required|`g4f.Provider.Local`|✔|❌|❌|❌|✔||
104
|[ollama.com](https://ollama.com)|No auth required|`g4f.Provider.Ollama`|✔|❌|❌|❌|✔||
100
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Status |
101
|----------|-------------|--------------|---------------|--------|--------|------|------|
102
|[]( )|No auth required|`g4f.Provider.Local`|✔|❌|❌|❌||
103
|[ollama.com](https://ollama.com)|No auth required|`g4f.Provider.Ollama`|✔|❌|❌|❌||
105
104
106
105
---
107
106
### Providers MiniMax
108
| Website | API Credentials | Provider | Text generation | Image generation| Audio generation | Vision (Image Upload) | Stream | Status |
109
|----------|-------------|--------------|---------------|--------|--------|------|------|------|
110
|[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)**_|❌|❌|❌|✔||
111
107
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Status |
108
|----------|-------------|--------------|---------------|--------|--------|------|------|
109
|[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+)**_|❌|❌|❌||
112
110
113
111
---
114
112
### Providers Needs Auth
115
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Streaming | Status |
116
|----------|-------------|--------------|---------------|--------|--------|------|------|------|
117
|[console.anthropic.com](https://console.anthropic.com)|[Get API key](https://console.anthropic.com/settings/keys)|`g4f.Provider.Anthropic`|✔ _**(8+)**_|❌|❌|❌|✔||
118
|[bing.com/images/create](https://www.bing.com/images/create)|[Manual cookies](https://www.bing.com)|`g4f.Provider.BingCreateImages`|❌|`dall-e-3`|❌|❌|❌||
113
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Vision (Image Upload) | Status |
114
|----------|-------------|--------------|---------------|--------|--------|------|------|
115
|[console.anthropic.com](https://console.anthropic.com)|[Get API key](https://console.anthropic.com/settings/keys)|`g4f.Provider.Anthropic`|✔ _**(8+)**_|❌|❌|❌||
116
|[bing.com/images/create](https://www.bing.com/images/create)|[Manual cookies](https://www.bing.com)|`g4f.Provider.BingCreateImages`|❌|`dall-e-3`|❌|❌||
119
117
|[cablyai.com/chat](https://cablyai.com/chat)|[Get API key](https://cablyai.com)|`g4f.Provider.CablyAI`|✔|✔|❌|✔||
120
|[inference.cerebras.ai](https://inference.cerebras.ai/)|[Get API key](https://cloud.cerebras.ai)|`g4f.Provider.Cerebras`|✔ _**(3+)**_|❌|❌|❌|✔||
121
|[copilot.microsoft.com](https://copilot.microsoft.com)|[Manual cookies](https://copilot.microsoft.com)|`g4f.Provider.CopilotAccount`|✔ _**(1+)**_|✔ _**(1+)**_|❌|✔ _**(1+)**_|✔||
122
|[deepinfra.com](https://deepinfra.com)|[Get API key](https://deepinfra.com/dash/api_keys)|`g4f.Provider.DeepInfra`|✔ _**(17+)**_|✔ _**(6+)**_|❌|❌|✔||
123
|[platform.deepseek.com](https://platform.deepseek.com)|[Get API key](https://platform.deepseek.com/api_keys)|`g4f.Provider.DeepSeek`|✔ _**(1+)**_|❌|❌|❌|❌||
124
|[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`|❌||
125
|[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`|❌||
126
|[developers.sber.ru/gigachat](https://developers.sber.ru/gigachat)|[Manual cookies](https://developers.sber.ru/gigachat)|`g4f.Provider.GigaChat`|✔ _**(3+)**_|❌|❌|❌|❌||
127
|[github.com/copilot](https://github.com/copilot)|[Manual cookies](https://github.com/copilot)|`g4f.Provider.GithubCopilot`|✔ _**(4+)**_|❌|❌|❌|❌||
128
|[glhf.chat](https://glhf.chat)|[Get API key](https://glhf.chat/user-settings/api)|`g4f.Provider.GlhfChat`|✔ _**(22+)**_|❌|❌|❌|❌||
129
|[console.groq.com/playground](https://console.groq.com/playground)|[Get API key](https://console.groq.com/keys)|`g4f.Provider.Groq`|✔ _**(18+)**_|❌|❌|✔|❌||
130
|[meta.ai](https://www.meta.ai)|[Manual cookies](https://www.meta.ai)|`g4f.Provider.MetaAI`|`meta-ai`|❌|❌|❌|✔||✔|
131
|[meta.ai](https://www.meta.ai)|[Manual cookies](https://www.meta.ai)|`g4f.Provider.MetaAIAccount`|❌|`meta-ai`|❌|❌|✔||
132
|[designer.microsoft.com](https://designer.microsoft.com)|[Manual cookies](https://designer.microsoft.com)|`g4f.Provider.MicrosoftDesigner`|❌|`dall-e-3`|❌|❌|❌||
133
|[platform.openai.com](https://platform.openai.com)|[Get API key](https://platform.openai.com/settings/organization/api-keys)|`g4f.Provider.OpenaiAPI`|✔|❌|❌|❌|✔||
134
|[chatgpt.com](https://chatgpt.com)|[Manual cookies](https://chatgpt.com)|`g4f.Provider.OpenaiChat`|`gpt-4o, gpt-4o-mini, gpt-4` _**(8+)**_|✔ _**(1)**_|❌|✔ _**(8+)**_|✔||
135
|[perplexity.ai](https://www.perplexity.ai)|[Get API key](https://www.perplexity.ai/settings/api)|`g4f.Provider.PerplexityApi`|✔ _**(6+)**_|❌|❌|❌|✔||
136
|[chat.reka.ai](https://chat.reka.ai)|[Manual cookies](https://chat.reka.ai)|`g4f.Provider.Reka`|`reka-core`|✔|❌|❌|✔||
137
|[replicate.com](https://replicate.com)|[Get API key](https://replicate.com/account/api-tokens)|`g4f.Provider.Replicate`|✔ _**(1+)**_|❌|❌|❌|✔||
138
|[beta.theb.ai](https://beta.theb.ai)|[Get API key](https://beta.theb.ai)|`g4f.Provider.ThebApi`|✔ _**(21+)**_|❌|❌|❌|✔||
139
|[whiterabbitneo.com](https://www.whiterabbitneo.com)|[Manual cookies](https://www.whiterabbitneo.com)|`g4f.Provider.WhiteRabbitNeo`|✔|❌|❌|❌|✔||
140
|[console.x.ai](https://console.x.ai)|[Get API key](https://console.x.ai)|`g4f.Provider.xAI`|✔|❌|❌|❌|✔||
118
|[inference.cerebras.ai](https://inference.cerebras.ai/)|[Get API key](https://cloud.cerebras.ai)|`g4f.Provider.Cerebras`|✔ _**(3+)**_|❌|❌|❌||
119
|[copilot.microsoft.com](https://copilot.microsoft.com)|[Manual cookies](https://copilot.microsoft.com)|`g4f.Provider.CopilotAccount`|✔ _**(1+)**_|✔ _**(1+)**_|❌|✔ _**(1+)**_||
120
|[deepinfra.com](https://deepinfra.com)|[Get API key](https://deepinfra.com/dash/api_keys)|`g4f.Provider.DeepInfra`|✔ _**(17+)**_|✔ _**(6+)**_|❌|❌||
121
|[platform.deepseek.com](https://platform.deepseek.com)|[Get API key](https://platform.deepseek.com/api_keys)|`g4f.Provider.DeepSeek`|✔ _**(1+)**_|❌|❌|❌||
122
|[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`||
123
|[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`||
124
|[developers.sber.ru/gigachat](https://developers.sber.ru/gigachat)|[Manual cookies](https://developers.sber.ru/gigachat)|`g4f.Provider.GigaChat`|✔ _**(3+)**_|❌|❌|❌||
125
|[github.com/copilot](https://github.com/copilot)|[Manual cookies](https://github.com/copilot)|`g4f.Provider.GithubCopilot`|✔ _**(4+)**_|❌|❌|❌||
126
|[glhf.chat](https://glhf.chat)|[Get API key](https://glhf.chat/user-settings/api)|`g4f.Provider.GlhfChat`|✔ _**(22+)**_|❌|❌|❌||
127
|[console.groq.com/playground](https://console.groq.com/playground)|[Get API key](https://console.groq.com/keys)|`g4f.Provider.Groq`|✔ _**(18+)**_|❌|❌|✔||
128
|[meta.ai](https://www.meta.ai)|[Manual cookies](https://www.meta.ai)|`g4f.Provider.MetaAI`|`meta-ai`|❌|❌|❌||
129
|[meta.ai](https://www.meta.ai)|[Manual cookies](https://www.meta.ai)|`g4f.Provider.MetaAIAccount`|❌|`meta-ai`|❌|❌||
130
|[designer.microsoft.com](https://designer.microsoft.com)|[Manual cookies](https://designer.microsoft.com)|`g4f.Provider.MicrosoftDesigner`|❌|`dall-e-3`|❌|❌||
131
|[platform.openai.com](https://platform.openai.com)|[Get API key](https://platform.openai.com/settings/organization/api-keys)|`g4f.Provider.OpenaiAPI`|✔|❌|❌|❌||
132
|[chatgpt.com](https://chatgpt.com)|[Manual cookies](https://chatgpt.com)|`g4f.Provider.OpenaiChat`|`gpt-4o, gpt-4o-mini, gpt-4` _**(8+)**_|✔ _**(1)**_|❌|✔ _**(8+)**_||
133
|[perplexity.ai](https://www.perplexity.ai)|[Get API key](https://www.perplexity.ai/settings/api)|`g4f.Provider.PerplexityApi`|✔ _**(6+)**_|❌|❌|❌||
134
|[chat.reka.ai](https://chat.reka.ai)|[Manual cookies](https://chat.reka.ai)|`g4f.Provider.Reka`|`reka-core`|✔|❌|❌||
135
|[replicate.com](https://replicate.com)|[Get API key](https://replicate.com/account/api-tokens)|`g4f.Provider.Replicate`|✔ _**(1+)**_|❌|❌|❌||
136
|[beta.theb.ai](https://beta.theb.ai)|[Get API key](https://beta.theb.ai)|`g4f.Provider.ThebApi`|✔ _**(21+)**_|❌|❌|❌||
137
|[whiterabbitneo.com](https://www.whiterabbitneo.com)|[Manual cookies](https://www.whiterabbitneo.com)|`g4f.Provider.WhiteRabbitNeo`|✔|❌|❌|❌||
138
|[console.x.ai](https://console.x.ai)|[Get API key](https://console.x.ai)|`g4f.Provider.xAI`|✔|❌|❌|❌||
141
139
142
140
---
143
141
## Models
@@ -145,12 +143,13 @@ This document provides an overview of various AI providers and models, including
145
143
### Text generation models
146
144
| Model | Base Provider | Providers | Website |
147
145
|-------|---------------|-----------|---------|
146
|gpt-3.5-turbo|OpenAI|1+ Providers|[platform.openai.com](https://platform.openai.com/docs/engines/gpt-3.5-turbo)|
148
147
|gpt-4|OpenAI|9+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4)|
149
148
|gpt-4o|OpenAI|6+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4o)|
150
|gpt-4o-mini|OpenAI|8+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4o-mini)|
151
|o1|OpenAI|3+ Providers|[openai.com](https://openai.com/index/introducing-openai-o1-preview/)|
149
|gpt-4o-mini|OpenAI|9+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4o-mini)|
150
|o1|OpenAI|4+ Providers|[openai.com](https://openai.com/index/introducing-openai-o1-preview/)|
152
151
|o1-mini|OpenAI|1+ Providers|[openai.com](https://openai.com/index/openai-o1-mini-advancing-cost-efficient-reasoning/)|
153
|o3-mini|OpenAI|3+ Providers|[openai.com](https://openai.com/index/openai-o3-mini/)|
152
|o3-mini|OpenAI|4+ Providers|[openai.com](https://openai.com/index/openai-o3-mini/)|
154
153
|gigachat|GigaChat|1+ Providers|[developers.sber.ru/gigachat](https://developers.sber.ru/gigachat)|
155
154
|meta-ai|Meta|1+ Providers|[ai.meta.com](https://ai.meta.com/)|
156
155
|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
170
169
|mixtral-small-24b|Mistral|2+ Providers|[huggingface.co](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501)|
171
170
|hermes-3|NousResearch|1+ Providers|[huggingface.co](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B-FP8)|
172
171
|phi-3.5-mini|Microsoft|1+ Providers|[huggingface.co](https://huggingface.co/microsoft/Phi-3.5-mini-instruct)|
173
|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)|
172
|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)|
174
173
|wizardlm-2-7b|Microsoft|1+ Providers|[wizardlm.github.io](https://wizardlm.github.io/WizardLM2/)|
175
174
|wizardlm-2-8x22b|Microsoft|2+ Providers|[wizardlm.github.io](https://wizardlm.github.io/WizardLM2/)|
176
175
|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
197
196
|qwen-2-vl-7b|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2-VL-7B)|
198
197
|qwen-2.5-72b|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)|
199
198
|qwen-2.5-coder-32b|Qwen|3+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2.5-Coder-32B)|
200
|qwen-2.5-1m-demo|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2.5-1M-Demo)|
199
|qwen-2.5-1m|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2.5-1M-Demo)|
200
|qwen-2-5-max|Qwen|1+ Providers|[qwen-ai.com](https://www.qwen-ai.com/2-5-max/)|
201
201
|qwq-32b|Qwen|2+ Providers|[huggingface.co](https://huggingface.co/Qwen/QwQ-32B-Preview)|
202
202
|qvq-72b|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/QVQ-72B-Preview)|
203
203
|pi|Inflection|1+ Providers|[inflection.ai](https://inflection.ai/blog/inflection-2-5)|
204
204
|deepseek-chat|DeepSeek|2+ Providers|[huggingface.co](https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat)|
205
|deepseek-v3|DeepSeek|4+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/news/news250120)|
206
|deepseek-r1|DeepSeek|9+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/news/news250120)|
205
|deepseek-v3|DeepSeek|5+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/news/news250120)|
206
|deepseek-r1|DeepSeek|10+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/news/news250120)|
207
207
|janus-pro-7b|DeepSeek|2+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/docs/janus-pro-7b)|
208
208
|grok-3|x.ai|1+ Providers|[x.ai](https://x.ai/blog/grok-3)|
209
209
|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
228
228
|tulu-3-70b|Ai2|1+ Providers|[allenai.org](https://allenai.org/documentation)|
229
229
|olmoe-0125|Ai2|1+ Providers|[allenai.org](https://allenai.org/documentation)|
230
230
|lfm-40b|Liquid AI|1+ Providers|[liquid.ai](https://www.liquid.ai/liquid-foundation-models)|
231
|evil|Evil Mode - Experimental|1+ Providers|[]( )|
231
|evil|Evil Mode - Experimental|2+ Providers|[]( )|
232
232
233
233
---
234
234
### Image generation models
@@ -243,14 +243,19 @@ This document provides an overview of various AI providers and models, including
243
243
|dall-e-3|OpenAI|5+ Providers|[openai.com](https://openai.com/index/dall-e/)|
244
244
|midjourney|Midjourney|1+ Providers|[docs.midjourney.com](https://docs.midjourney.com/docs/model-versions)|
245
245
246
---
247
### Audio generation models
248
| Model | Base Provider | Providers | Website |
249
|-------|---------------|-----------|---------|
250
|gpt-4o-audio|Stability AI|1+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4o-audio)|
251
246
252
247
253
## Conclusion and Usage Tips
248
254
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:**
249
255
1. **Availability**: Check the status of the provider to ensure it's currently active and accessible.
250
256
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.
251
257
3. **Authentication**: Some providers require authentication, while others don't. Consider this when selecting a provider for your project.
252
4. **Streaming Support**: If real-time responses are important for your application, prioritize providers that offer streaming capabilities.
253
5. **Vision Models**: For tasks requiring image understanding or multimodal interactions, look for providers offering vision models.
258
4. **Vision Models**: For tasks requiring image understanding or multimodal interactions, look for providers offering vision models.
254
259
255
260
Remember to stay updated with the latest developments in the AI field, as new models and providers are constantly emerging and evolving.
256
261
@@ -75,7 +75,7 @@ class ARTA(AsyncGeneratorProvider, ProviderModelMixin):
75
75
"professional": "Professional",
76
76
"black_ink": "Black Ink"
77
77
}
78
image_models = [*model_aliases.keys()]
78
image_models = list(model_aliases.keys())
79
79
models = image_models
80
80
81
81
@classmethod
@@ -5,19 +5,22 @@ from aiohttp import ClientSession, ClientTimeout
5
5
import json
6
6
import asyncio
7
7
import random
8
from yarl import URL
8
9
9
10
from ..typing import AsyncResult, Messages, Cookies
10
11
from ..requests.raise_for_status import raise_for_status
11
12
from .base_provider import AsyncGeneratorProvider, ProviderModelMixin
12
from .helper import format_prompt
13
from .helper import format_prompt, get_last_user_message
13
14
from ..providers.response import FinishReason, JsonConversation
14
15
from ..errors import ModelNotSupportedError, ResponseStatusError, RateLimitError, TimeoutError, ConversationLimitError
15
16
17
16
18
class DuckDuckGoSearchException(Exception):
17
19
"""Base exception class for duckduckgo_search."""
18
20
19
21
class Conversation(JsonConversation):
20
22
vqd: str = None
23
vqd_hash_1: str = None
21
24
message_history: Messages = []
22
25
cookies: dict = {}
23
26
@@ -30,7 +33,7 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
30
33
api_endpoint = "https://duckduckgo.com/duckchat/v1/chat"
31
34
status_url = "https://duckduckgo.com/duckchat/v1/status"
32
35
33
working = False
36
working = True
34
37
supports_stream = True
35
38
supports_system_message = True
36
39
supports_message_history = True
@@ -46,6 +49,8 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
46
49
}
47
50
48
51
last_request_time = 0
52
max_retries = 3
53
base_delay = 2
49
54
50
55
@classmethod
51
56
def validate_model(cls, model: str) -> str:
@@ -59,43 +64,78 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
59
64
return model
60
65
61
66
@classmethod
62
async def sleep(cls):
67
async def sleep(cls, multiplier=1.0):
63
68
"""Implements rate limiting between requests"""
64
69
now = time.time()
65
70
if cls.last_request_time > 0:
66
delay = max(0.0, 0.75 - (now - cls.last_request_time))
71
delay = max(0.0, 1.5 - (now - cls.last_request_time)) * multiplier
67
72
if delay > 0:
68
73
await asyncio.sleep(delay)
69
cls.last_request_time = now
74
cls.last_request_time = time.time()
75
76
@classmethod
77
async def get_default_cookies(cls, session: ClientSession) -> dict:
78
"""Obtains default cookies needed for API requests"""
79
try:
80
await cls.sleep()
81
# Make initial request to get cookies
82
async with session.get(cls.url) as response:
83
# We also manually set required cookies
84
cookies = {}
85
cookies_dict = {'dcs': '1', 'dcm': '3'}
86
87
for name, value in cookies_dict.items():
88
cookies[name] = value
89
url_obj = URL(cls.url)
90
session.cookie_jar.update_cookies({name: value}, url_obj)
91
92
return cookies
93
except Exception as e:
94
return {}
70
95
71
96
@classmethod
72
async def fetch_vqd(cls, session: ClientSession, max_retries: int = 3) -> str:
73
"""Fetches the required VQD token for the chat session with retries."""
97
async def fetch_vqd_and_hash(cls, session: ClientSession, retry_count: int = 0) -> tuple[str, str]:
98
"""Fetches the required VQD token and hash for the chat session with retries."""
74
99
headers = {
75
100
"accept": "text/event-stream",
101
"accept-language": "en-US,en;q=0.9",
102
"cache-control": "no-cache",
76
103
"content-type": "application/json",
104
"pragma": "no-cache",
105
"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",
106
"origin": "https://duckduckgo.com",
107
"referer": "https://duckduckgo.com/",
77
108
"x-vqd-accept": "1",
78
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
79
109
}
80
110
81
for attempt in range(max_retries):
82
try:
83
await cls.sleep()
84
async with session.get(cls.status_url, headers=headers) as response:
85
await raise_for_status(response)
86
vqd = response.headers.get("x-vqd-4", "")
87
if vqd:
88
return vqd
89
response_text = await response.text()
90
raise RuntimeError(f"Failed to fetch VQD token: {response.status} {response_text}")
91
except ResponseStatusError as e:
92
if attempt < max_retries - 1:
93
wait_time = random.uniform(1, 3) * (attempt + 1)
94
await asyncio.sleep(wait_time)
95
else:
96
raise RuntimeError(f"Failed to fetch VQD token after {max_retries} attempts: {str(e)}")
111
# Make sure we have cookies first
112
if len(session.cookie_jar) == 0:
113
await cls.get_default_cookies(session)
97
114
98
raise RuntimeError("Failed to fetch VQD token: Maximum retries exceeded")
115
try:
116
await cls.sleep(multiplier=1.0 + retry_count * 0.5)
117
async with session.get(cls.status_url, headers=headers) as response:
118
await raise_for_status(response)
119
120
vqd = response.headers.get("x-vqd-4", "")
121
vqd_hash_1 = response.headers.get("x-vqd-hash-1", "")
122
123
if vqd and vqd_hash_1:
124
return vqd, vqd_hash_1
125
126
if vqd and not vqd_hash_1:
127
return vqd, ""
128
129
response_text = await response.text()
130
raise RuntimeError(f"Failed to fetch VQD token and hash: {response.status} {response_text}")
131
132
except Exception as e:
133
if retry_count < cls.max_retries:
134
wait_time = cls.base_delay * (2 ** retry_count) * (1 + random.random())
135
await asyncio.sleep(wait_time)
136
return await cls.fetch_vqd_and_hash(session, retry_count + 1)
137
else:
138
raise RuntimeError(f"Failed to fetch VQD token and hash after {cls.max_retries} attempts: {str(e)}")
99
139
100
140
@classmethod
101
141
async def create_async_generator(
@@ -103,80 +143,122 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
103
143
model: str,
104
144
messages: Messages,
105
145
proxy: str = None,
106
timeout: int = 30,
146
timeout: int = 60,
107
147
cookies: Cookies = None,
108
148
conversation: Conversation = None,
109
149
return_conversation: bool = False,
110
150
**kwargs
111
151
) -> AsyncResult:
112
152
model = cls.validate_model(model)
153
retry_count = 0
113
154
114
if cookies is None and conversation is not None:
115
cookies = conversation.cookies
155
while retry_count <= cls.max_retries:
156
try:
157
session_timeout = ClientTimeout(total=timeout)
158
async with ClientSession(timeout=session_timeout, cookies=cookies) as session:
159
if conversation is None:
160
# Get initial cookies if not provided
161
if not cookies:
162
await cls.get_default_cookies(session)
163
164
conversation = Conversation(model)
165
vqd, vqd_hash_1 = await cls.fetch_vqd_and_hash(session)
166
conversation.vqd = vqd
167
conversation.vqd_hash_1 = vqd_hash_1
168
conversation.message_history = [{"role": "user", "content": format_prompt(messages)}]
169
else:
170
last_message = get_last_user_message(messages.copy())
171
conversation.message_history.append({"role": "user", "content": last_message})
116
172
117
try:
118
async with ClientSession(timeout=ClientTimeout(total=timeout), cookies=cookies) as session:
119
if conversation is None:
120
conversation = Conversation(model)
121
conversation.vqd = await cls.fetch_vqd(session)
122
conversation.message_history = [{"role": "user", "content": format_prompt(messages)}]
123
else:
124
conversation.message_history.append(messages[-1])
125
126
headers = {
127
"accept": "text/event-stream",
128
"content-type": "application/json",
129
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
130
"x-vqd-4": conversation.vqd,
131
}
132
133
data = {
134
"model": model,
135
"messages": conversation.message_history,
136
}
137
138
await cls.sleep()
139
async with session.post(cls.api_endpoint, json=data, headers=headers, proxy=proxy) as response:
140
await raise_for_status(response)
141
reason = None
142
full_message = ""
143
144
async for line in response.content:
145
line = line.decode("utf-8").strip()
146
147
if line.startswith("data:"):
148
try:
149
message = json.loads(line[5:].strip())
150
except json.JSONDecodeError:
173
headers = {
174
"accept": "text/event-stream",
175
"accept-language": "en-US,en;q=0.9",
176
"content-type": "application/json",
177
"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",
178
"origin": "https://duckduckgo.com",
179
"referer": "https://duckduckgo.com/",
180
"x-vqd-4": conversation.vqd,
181
}
182
183
# Add the x-vqd-hash-1 header if available
184
if conversation.vqd_hash_1:
185
headers["x-vqd-hash-1"] = conversation.vqd_hash_1
186
187
data = {
188
"model": model,
189
"messages": conversation.message_history,
190
}
191
192
await cls.sleep(multiplier=1.0 + retry_count * 0.5)
193
async with session.post(cls.api_endpoint, json=data, headers=headers, proxy=proxy) as response:
194
# Handle 429 errors specifically
195
if response.status == 429:
196
response_text = await response.text()
197
198
if retry_count < cls.max_retries:
199
retry_count += 1
200
wait_time = cls.base_delay * (2 ** retry_count) * (1 + random.random())
201
await asyncio.sleep(wait_time)
202
203
# Get fresh tokens and cookies
204
cookies = await cls.get_default_cookies(session)
151
205
continue
206
else:
207
raise RateLimitError(f"Rate limited after {cls.max_retries} retries")
208
209
await raise_for_status(response)
210
reason = None
211
full_message = ""
212
213
async for line in response.content:
214
line = line.decode("utf-8").strip()
215
216
if line.startswith("data:"):
217
try:
218
message = json.loads(line[5:].strip())
219
except json.JSONDecodeError:
220
continue
221
222
if "action" in message and message["action"] == "error":
223
error_type = message.get("type", "")
224
if message.get("status") == 429:
225
if error_type == "ERR_CONVERSATION_LIMIT":
226
raise ConversationLimitError(error_type)
227
raise RateLimitError(error_type)
228
raise DuckDuckGoSearchException(error_type)
152
229
153
if "action" in message and message["action"] == "error":
154
error_type = message.get("type", "")
155
if message.get("status") == 429:
156
if error_type == "ERR_CONVERSATION_LIMIT":
157
raise ConversationLimitError(error_type)
158
raise RateLimitError(error_type)
159
raise DuckDuckGoSearchException(error_type)
160
161
if "message" in message:
162
if message["message"]:
163
yield message["message"]
164
full_message += message["message"]
165
reason = "length"
166
else:
167
reason = "stop"
168
169
if return_conversation:
170
conversation.message_history.append({"role": "assistant", "content": full_message})
171
conversation.vqd = response.headers.get("x-vqd-4", conversation.vqd)
172
conversation.cookies = {
173
n: c.value
174
for n, c in session.cookie_jar.filter_cookies(cls.url).items()
175
}
176
yield conversation
177
178
if reason is not None:
179
yield FinishReason(reason)
180
181
except asyncio.TimeoutError as e:
182
raise TimeoutError(f"Request timed out: {str(e)}")
230
if "message" in message:
231
if message["message"]:
232
yield message["message"]
233
full_message += message["message"]
234
reason = "length"
235
else:
236
reason = "stop"
237
238
if return_conversation:
239
conversation.message_history.append({"role": "assistant", "content": full_message})
240
conversation.vqd = response.headers.get("x-vqd-4", conversation.vqd)
241
conversation.vqd_hash_1 = response.headers.get("x-vqd-hash-1", conversation.vqd_hash_1)
242
conversation.cookies = {
243
n: c.value
244
for n, c in session.cookie_jar.filter_cookies(URL(cls.url)).items()
245
}
246
yield conversation
247
248
if reason is not None:
249
yield FinishReason(reason)
250
251
# If we got here, the request was successful
252
break
253
254
except (RateLimitError, ResponseStatusError) as e:
255
if "429" in str(e) and retry_count < cls.max_retries:
256
retry_count += 1
257
wait_time = cls.base_delay * (2 ** retry_count) * (1 + random.random())
258
await asyncio.sleep(wait_time)
259
else:
260
raise
261
except asyncio.TimeoutError as e:
262
raise TimeoutError(f"Request timed out: {str(e)}")
263
except Exception as e:
264
raise
@@ -1,8 +1,6 @@
1
1
from __future__ import annotations
2
2
3
from ..typing import AsyncResult, Messages, MediaListType
4
3
from .template import OpenaiTemplate
5
from ..image import to_data_uri
6
4
7
5
class DeepInfraChat(OpenaiTemplate):
8
6
url = "https://deepinfra.com/chat"
@@ -10,8 +8,8 @@ class DeepInfraChat(OpenaiTemplate):
10
8
working = True
11
9
12
10
default_model = 'deepseek-ai/DeepSeek-V3'
13
default_vision_model = 'meta-llama/Llama-3.2-90B-Vision-Instruct'
14
vision_models = [default_vision_model, 'openbmb/MiniCPM-Llama3-V-2_5']
11
default_vision_model = 'openbmb/MiniCPM-Llama3-V-2_5'
12
vision_models = [default_vision_model, 'meta-llama/Llama-3.2-90B-Vision-Instruct']
15
13
models = [
16
14
'meta-llama/Meta-Llama-3.1-8B-Instruct',
17
15
'meta-llama/Llama-3.3-70B-Instruct-Turbo',
@@ -59,36 +57,3 @@ class DeepInfraChat(OpenaiTemplate):
59
57
"mixtral-8x22b": "mistralai/Mixtral-8x22B-Instruct-v0.1",
60
58
"minicpm-2.5": "openbmb/MiniCPM-Llama3-V-2_5",
61
59
}
62
63
@classmethod
64
async def create_async_generator(
65
cls,
66
model: str,
67
messages: Messages,
68
stream: bool = True,
69
top_p: float = 0.9,
70
temperature: float = 0.7,
71
max_tokens: int = None,
72
headers: dict = {},
73
**kwargs
74
) -> AsyncResult:
75
headers = {
76
'Accept-Language': 'en-US,en;q=0.9',
77
'Origin': 'https://deepinfra.com',
78
'Referer': 'https://deepinfra.com/',
79
'X-Deepinfra-Source': 'web-page',
80
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
81
**headers
82
}
83
84
async for chunk in super().create_async_generator(
85
model,
86
messages,
87
headers=headers,
88
stream=stream,
89
top_p=top_p,
90
temperature=temperature,
91
max_tokens=max_tokens,
92
**kwargs
93
):
94
yield chunk
@@ -14,7 +14,6 @@ class LambdaChat(HuggingChat):
14
14
default_model = "deepseek-llama3.3-70b"
15
15
reasoning_model = "deepseek-r1"
16
16
image_models = []
17
models = []
18
17
fallback_models = [
19
18
default_model,
20
19
reasoning_model,
@@ -23,6 +22,8 @@ class LambdaChat(HuggingChat):
23
22
"lfm-40b",
24
23
"llama3.3-70b-instruct-fp8"
25
24
]
25
models = fallback_models.copy()
26
26
27
model_aliases = {
27
28
"deepseek-v3": default_model,
28
29
"hermes-3": "hermes-3-llama-3.1-405b-fp8",
@@ -5,13 +5,14 @@ from .template import OpenaiTemplate
5
5
class TypeGPT(OpenaiTemplate):
6
6
label = "TypeGpt"
7
7
url = "https://chat.typegpt.net"
8
api_endpoint = "https://chat.typegpt.net/api/openai/typegpt/v1/chat/completions"
8
api_base = "https://chat.typegpt.net/api/openai/typegpt/v1"
9
9
working = True
10
10
11
default_model = "gpt-4o-mini-2024-07-18"
12
models = [
13
default_model, "o1", "o3-mini", "gemini-1.5-flash", "deepseek-r1", "deepseek-v3", "gemini-pro", "evil"
14
]
11
default_model = 'gpt-4o-mini-2024-07-18'
12
default_vision_model = default_model
13
vision_models = ['gpt-3.5-turbo', 'gpt-3.5-turbo-202201', default_vision_model, "o3-mini"]
14
models = vision_models + ["deepseek-r1", "deepseek-v3", "evil", "o1"]
15
15
model_aliases = {
16
"gpt-3.5-turbo": "gpt-3.5-turbo-202201",
16
17
"gpt-4o-mini": "gpt-4o-mini-2024-07-18",
17
}
18
}
@@ -22,8 +22,8 @@ class BlackForestLabs_Flux1Dev(AsyncGeneratorProvider, ProviderModelMixin):
22
22
23
23
default_model = 'black-forest-labs-flux-1-dev'
24
24
default_image_model = default_model
25
model_aliases = {"flux-dev": default_model, "flux": default_model}
26
image_models = [default_image_model, *model_aliases.keys()]
25
model_aliases = {"flux-dev": default_image_model, "flux": default_image_model}
26
image_models = list(model_aliases.keys())
27
27
models = image_models
28
28
29
29
@classmethod
@@ -19,8 +19,8 @@ class BlackForestLabs_Flux1Schnell(AsyncGeneratorProvider, ProviderModelMixin):
19
19
20
20
default_model = "black-forest-labs-flux-1-schnell"
21
21
default_image_model = default_model
22
model_aliases = {"flux-schnell": default_model, "flux": default_model}
23
image_models = [default_image_model, *model_aliases.keys()]
22
model_aliases = {"flux-schnell": default_image_model, "flux": default_image_model}
23
image_models = list(model_aliases.keys())
24
24
models = image_models
25
25
26
26
@classmethod
@@ -17,21 +17,15 @@ class CohereForAI_C4AI_Command(AsyncGeneratorProvider, ProviderModelMixin):
17
17
working = True
18
18
19
19
default_model = "command-a-03-2025"
20
models = [
21
default_model,
22
"command-r-plus-08-2024",
23
"command-r-08-2024",
24
"command-r-plus",
25
"command-r",
26
"command-r7b-12-2024",
27
"command-r7b-arabic-02-2025",
28
]
29
20
model_aliases = {
30
"command-a": "command-a-03-2025",
21
"command-a": default_model,
31
22
"command-r-plus": "command-r-plus-08-2024",
32
23
"command-r": "command-r-08-2024",
24
"command-r": "command-r",
33
25
"command-r7b": "command-r7b-12-2024",
34
26
}
27
28
models = list(model_aliases.keys())
35
29
36
30
@classmethod
37
31
async def create_async_generator(
@@ -34,8 +34,9 @@ class DeepseekAI_JanusPro7b(AsyncGeneratorProvider, ProviderModelMixin):
34
34
default_model = "janus-pro-7b"
35
35
default_image_model = "janus-pro-7b-image"
36
36
default_vision_model = default_model
37
models = [default_model, default_image_model]
38
37
image_models = [default_image_model]
38
vision_models = [default_vision_model]
39
models = vision_models + image_models
39
40
40
41
@classmethod
41
42
def run(cls, method: str, session: StreamSession, prompt: str, conversation: JsonConversation, image: dict = None, seed: int = 0):
@@ -29,7 +29,9 @@ class Microsoft_Phi_4(AsyncGeneratorProvider, ProviderModelMixin):
29
29
30
30
default_model = "phi-4-multimodal"
31
31
default_vision_model = default_model
32
models = [default_model]
32
model_aliases = {"phi-4": default_vision_model}
33
vision_models = list(model_aliases.keys())
34
models = vision_models
33
35
34
36
@classmethod
35
37
def run(cls, method: str, session: StreamSession, prompt: str, conversation: JsonConversation, media: list = None):
@@ -18,9 +18,10 @@ class Qwen_QVQ_72B(AsyncGeneratorProvider, ProviderModelMixin):
18
18
working = True
19
19
20
20
default_model = "qwen-qvq-72b-preview"
21
models = [default_model]
22
model_aliases = {"qvq-72b": default_model}
23
vision_models = models
21
default_vision_model = default_model
22
model_aliases = {"qvq-72b": default_vision_model}
23
vision_models = list(model_aliases.keys())
24
models = vision_models
24
25
25
26
@classmethod
26
27
async def create_async_generator(