返回提交历史
Modified
docs/providers-and-models.md
+102
-97
Added
etc/tool/commit.py
+105
-0
Modified
g4f/Provider/ARTA.py
+46
-6
Modified
g4f/Provider/AllenAI.py
+69
-16
Modified
g4f/Provider/Blackbox.py
+299
-238
Modified
g4f/Provider/DDG.py
+212
-35
Modified
g4f/Provider/PollinationsAI.py
+49
-21
Modified
g4f/Provider/PollinationsImage.py
+1
-0
Modified
g4f/gui/client/static/js/chat.v1.js
+4
-2
Modified
g4f/gui/server/api.py
+6
-0
Modified
g4f/gui/server/backend_api.py
+2
-0
Modified
g4f/models.py
+34
-14
XFEstudio/gpt4free
docs: update providers documentation and enhance support for Blackbox HAR auth
- Added "No auth / HAR file" authentication type in providers-and-models.md - Added "Video generation" column to provider tables for future capability - Updated model counts and provider capabilities throughout documentation - Fixed ARTA provider with improved error handling and response validation - Enhanced AllenAI provider with vision model support and proper image handling - Significantly improved Blackbox provider: - Added HAR file authentication support - Added subscription status checking - Added premium/demo model differentiation - Improved session handling and error recovery - Enhanced DDG provider with better error handling for challenges - Improved PollinationsAI and PollinationsImage providers' model handling - Added VideoModel class in g4f/models.py - Added audio/video generation indicators in GUI components - Added new Ai2 models: olmo-1-7b, olmo-2-32b, olmo-4-synthetic - Added new commit message generation tool in etc/tool/commit.py
54ef1a51
代码差异
12 个文件
+929
-429
@@ -26,6 +26,7 @@ This document provides an overview of various AI providers and models, including
26
26
- **Optional API key** - Works without authentication, but you can provide an API key for better rate limits or additional features. The service is usable without an API key.
27
27
- **API key / Cookies** - Supports both authentication methods. You can use either an API key or browser cookies for authentication.
28
28
- **No auth required** - No authentication needed. The service is publicly available without any credentials.
29
- **No auth / HAR file** - Supports both authentication methods. The service works without authentication, but you can also use HAR file authentication for potentially enhanced features or capabilities.
29
30
30
31
**Symbols:**
31
32
- ✔ - Feature is supported
@@ -34,108 +35,110 @@ This document provides an overview of various AI providers and models, including
34
35
35
36
---
36
37
### Providers No auth required
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, blackboxai-pro, 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`|✔|❌|❌||
38
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Video generation | Vision (Image Upload) | Status |
39
|----------|-------------|--------------|---------------|--------|--------|------|------|------|
40
|[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, olmo-2-32b`|❌|❌|❌|`olmo-4-synthetic`||
41
|[ai-arta.com](https://ai-arta.com)|No auth required|`g4f.Provider.ARTA`|❌|`flux` _**(16+)**_|❌|❌|❌||
42
|[blackbox.ai](https://www.blackbox.ai)|No auth / HAR file|`g4f.Provider.Blackbox`|`blackboxai, blackboxai-pro, gpt-4o-mini, deepseek-chat, deepseek-v3, deepseek-r1, gpt-4o, o1, o3-mini, claude-3.7-sonnet, llama-3.3-70b, mixtral-small-24b, qwq-32b` _**(40+)**_|`flux`|❌|❌|`blackboxai, gpt-4o, o1, o3-mini, deepseek-v3` _**(7+)**_||
43
|[chatglm.cn](https://chatglm.cn)|No auth required|`g4f.Provider.ChatGLM`|`glm-4`|❌|❌|❌|❌||
44
|[chatgpt.com](https://chatgpt.com)|No auth required|`g4f.Provider.ChatGpt`|✔ _**(7+)**_|❌|❌|❌|❌||
45
|[chatgpt.es](https://chatgpt.es)|No auth required|`g4f.Provider.ChatGptEs`|`gpt-4, gpt-4o, gpt-4o-mini`|❌|❌|❌|❌||
46
|[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`|❌|❌|❌|❌||
47
|[copilot.microsoft.com](https://copilot.microsoft.com)|Optional API key|`g4f.Provider.Copilot`|`gpt-4, o1`|❌|❌|❌|❌||
48
|[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`|❌|❌|❌|❌||
49
|[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`||
50
|[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`||
51
|[chat10.free2gpt.xyz](https://chat10.free2gpt.xyz)|No auth required|`g4f.Provider.Free2GPT`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌|❌||
52
|[freegptsnav.aifree.site](https://freegptsnav.aifree.site)|No auth required|`g4f.Provider.FreeGpt`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌|❌||
53
|[app.giz.ai/assistant](https://app.giz.ai/assistant)|No auth required|`g4f.Provider.GizAI`|`gemini-1.5-flash`|❌|❌|❌|❌||
54
|[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`|❌|❌|❌|❌||
55
|[goabror.uz](https://goabror.uz)|No auth required|`g4f.Provider.Goabror`|`gpt-4`|❌|❌|❌|❌||
56
|[hailuo.ai](https://www.hailuo.ai)|No auth required|`g4f.Provider.HailuoAI`|`MiniMax` _**(1+)**_|❌|❌|❌|❌||
57
|[editor.imagelabs.net](editor.imagelabs.net)|No auth required|`g4f.Provider.ImageLabs`|❌|`sdxl-turbo`|❌|❌|❌||
58
|[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`|❌|❌|❌||
59
|[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`|❌|❌|❌|❌||
60
|[lambda.chat](https://lambda.chat)|No auth required|`g4f.Provider.LambdaChat`|`deepseek-v3, deepseek-r1, hermes-3, nemotron-70b, llama-3.3-70b`|❌|❌|❌|❌||
61
|[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`|❌|❌|❌|❌||
62
|[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`||
63
|[labs.perplexity.ai](https://labs.perplexity.ai)|No auth required|`g4f.Provider.PerplexityLabs`|`sonar, sonar-pro, sonar-reasoning, sonar-reasoning-pro`|❌|❌|❌|❌||
64
|[pi.ai/talk](https://pi.ai/talk)|[Manual cookies](https://pi.ai/talk)|`g4f.Provider.Pi`|`pi`|❌|❌|❌|❌||
65
|[pizzagpt.it](https://www.pizzagpt.it)|No auth required|`g4f.Provider.Pizzagpt`|`gpt-4o-mini`|❌|❌|❌|❌||
66
|[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. qwq-32b, deepseek-v3, llama-3.2-11b` _**(9+)**_|`flux, flux-pro, flux-dev, flux-schnell, dall-e-3, sdxl-turbo`|`gpt-4o-audio` _**(3+)**_|❌|`gpt-4o, gpt-4o-mini, o1-mini, o3-mini`||
67
|[pollinations.ai](https://pollinations.ai)|No auth required|`g4f.Provider.PollinationsImage`|❌|`flux, flux-pro, flux-dev, flux-schnell, dall-e-3, sdxl-turbo`|❌|❌|❌||
68
|[teach-anything.com](https://www.teach-anything.com)|No auth required|`g4f.Provider.TeachAnything`|`gemini-1.5-pro, gemini-1.5-flash`|❌|❌|❌|❌||
69
|[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`||
70
|[you.com](https://you.com)|[Manual cookies](https://you.com)|`g4f.Provider.You`|✔|✔|❌|❌|✔||
71
|[websim.ai](https://websim.ai)|No auth required|`g4f.Provider.Websim`|`gemini-1.5-pro, gemini-1.5-flash`|`flux`|❌|❌|❌||
72
|[chat9.yqcloud.top](https://chat9.yqcloud.top)|No auth required|`g4f.Provider.Yqcloud`|`gpt-4`|✔|❌|❌|❌||
72
73
73
74
---
74
75
### Providers HuggingFace
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+)**_||
76
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Video generation | Vision (Image Upload) | Status |
77
|----------|-------------|--------------|---------------|--------|--------|------|------|------|
78
|[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`|❌|❌|❌||
79
|[huggingface.co/chat](https://huggingface.co/chat)|[API key / Cookies](https://huggingface.co/settings/tokens)|`g4f.Provider.HuggingFace`|✔ _**(47+)**_|✔ _**(9+)**_|❌|❌|❌||
80
|[api-inference.huggingface.co](https://api-inference.huggingface.co)|[Get API key](https://huggingface.co/settings/tokens)|`g4f.Provider.HuggingFaceAPI`|✔ _**(9+)**_|✔ _**(2+)**_|❌|❌|✔ _**(1+)**_||
80
81
81
82
---
82
83
### Providers HuggingSpace
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`|❌|❌||
84
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Video generation | Vision (Image Upload) | Status |
85
|----------|-------------|--------------|---------------|--------|--------|------|------|------|
86
|[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`|❌|❌|❌||
87
|[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`|❌|❌|❌||
88
|[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`|❌|❌|❌|❌||
89
|[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`|✔|✔|❌|❌|❌||
90
|[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+)**_||
91
|[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`||
92
|[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`|❌|❌|❌|❌||
93
|[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`|❌|❌|❌|❌||
94
|[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`|❌|❌|❌|❌||
95
|[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`|❌|❌|❌|❌||
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`|`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, flux-schnell`|❌|❌|❌||
98
99
99
100
### Providers Local
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`|✔|❌|❌|❌||
101
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Video generation | Vision (Image Upload) | Status |
102
|----------|-------------|--------------|---------------|--------|--------|------|------|------|
103
|[]( )|No auth required|`g4f.Provider.Local`|✔|❌|❌|❌|❌||
104
|[ollama.com](https://ollama.com)|No auth required|`g4f.Provider.Ollama`|✔|❌|❌|❌|❌||
104
105
105
106
---
106
107
### Providers MiniMax
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+)**_|❌|❌|❌||
108
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Video generation | Vision (Image Upload) | 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+)**_|❌|❌|❌|❌||
110
111
111
112
---
112
113
### Providers Needs Auth
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`|❌|❌||
117
|[cablyai.com/chat](https://cablyai.com/chat)|[Get API key](https://cablyai.com)|`g4f.Provider.CablyAI`|✔|✔|❌|✔||
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`|✔|❌|❌|❌||
114
| Website | API Credentials | Provider | Text generation | Image generation | Audio generation | Video generation | Vision (Image Upload) | Status |
115
|----------|-------------|--------------|---------------|--------|--------|------|------|------|
116
|[console.anthropic.com](https://console.anthropic.com)|[Get API key](https://console.anthropic.com/settings/keys)|`g4f.Provider.Anthropic`|✔ _**(8+)**_|❌|❌|❌|❌||
117
|[bing.com/images/create](https://www.bing.com/images/create)|[Manual cookies](https://www.bing.com)|`g4f.Provider.BingCreateImages`|❌|`dall-e-3`|❌|❌|❌||
118
|[cablyai.com/chat](https://cablyai.com/chat)|[Get API key](https://cablyai.com)|`g4f.Provider.CablyAI`|✔|✔|❌|❌|✔||
119
|[inference.cerebras.ai](https://inference.cerebras.ai/)|[Get API key](https://cloud.cerebras.ai)|`g4f.Provider.Cerebras`|✔ _**(3+)**_|❌|❌|❌|❌||
120
|[copilot.microsoft.com](https://copilot.microsoft.com)|[Manual cookies](https://copilot.microsoft.com)|`g4f.Provider.CopilotAccount`|✔ _**(1+)**_|✔ _**(1+)**_|❌|❌|✔ _**(1+)**_||
121
|[deepinfra.com](https://deepinfra.com)|[Get API key](https://deepinfra.com/dash/api_keys)|`g4f.Provider.DeepInfra`|✔ _**(17+)**_|✔ _**(6+)**_|❌|❌|❌||
122
|[platform.deepseek.com](https://platform.deepseek.com)|[Get API key](https://platform.deepseek.com/api_keys)|`g4f.Provider.DeepSeek`|✔ _**(1+)**_|❌|❌|❌|❌||
123
|[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`||
124
|[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`||
125
|[developers.sber.ru/gigachat](https://developers.sber.ru/gigachat)|[Manual cookies](https://developers.sber.ru/gigachat)|`g4f.Provider.GigaChat`|✔ _**(3+)**_|❌|❌|❌|❌||
126
|[github.com/copilot](https://github.com/copilot)|[Manual cookies](https://github.com/copilot)|`g4f.Provider.GithubCopilot`|✔ _**(4+)**_|❌|❌|❌|❌||
127
|[glhf.chat](https://glhf.chat)|[Get API key](https://glhf.chat/user-settings/api)|`g4f.Provider.GlhfChat`|✔ _**(22+)**_|❌|❌|❌|❌||
128
|[console.groq.com/playground](https://console.groq.com/playground)|[Get API key](https://console.groq.com/keys)|`g4f.Provider.Groq`|✔ _**(18+)**_|❌|❌|❌|✔||
129
|[meta.ai](https://www.meta.ai)|[Manual cookies](https://www.meta.ai)|`g4f.Provider.MetaAI`|`meta-ai`|❌|❌|❌|❌||
130
|[meta.ai](https://www.meta.ai)|[Manual cookies](https://www.meta.ai)|`g4f.Provider.MetaAIAccount`|❌|`meta-ai`|❌|❌|❌||
131
|[designer.microsoft.com](https://designer.microsoft.com)|[Manual cookies](https://designer.microsoft.com)|`g4f.Provider.MicrosoftDesigner`|❌|`dall-e-3`|❌|❌|❌||
132
|[platform.openai.com](https://platform.openai.com)|[Get API key](https://platform.openai.com/settings/organization/api-keys)|`g4f.Provider.OpenaiAPI`|✔|❌|❌|❌|❌||
133
|[chatgpt.com](https://chatgpt.com)|[Manual cookies](https://chatgpt.com)|`g4f.Provider.OpenaiChat`|`gpt-4o, gpt-4o-mini, gpt-4` _**(8+)**_|✔ _**(1)**_|❌|❌|✔ _**(8+)**_||
134
|[perplexity.ai](https://www.perplexity.ai)|[Get API key](https://www.perplexity.ai/settings/api)|`g4f.Provider.PerplexityApi`|✔ _**(6+)**_|❌|❌|❌|❌||
135
|[chatgpt.com](https://chatgpt.com)|[Manual cookies](https://chatgpt.com)|`g4f.Provider.OpenaiChat`|`gpt-4o, gpt-4o-mini, gpt-4` _**(8+)**_|✔ _**(1)**_|❌|❌|✔ _**(8+)**_||
136
|[perplexity.ai](https://www.perplexity.ai)|[Get API key](https://www.perplexity.ai/settings/api)|`g4f.Provider.PerplexityApi`|✔ _**(6+)**_|❌|❌|❌|❌||
137
|[chat.reka.ai](https://chat.reka.ai)|[Manual cookies](https://chat.reka.ai)|`g4f.Provider.Reka`|`reka-core`|✔|❌|❌|❌||
138
|[replicate.com](https://replicate.com)|[Get API key](https://replicate.com/account/api-tokens)|`g4f.Provider.Replicate`|✔ _**(1+)**_|❌|❌|❌|❌||
139
|[beta.theb.ai](https://beta.theb.ai)|[Get API key](https://beta.theb.ai)|`g4f.Provider.ThebApi`|✔ _**(21+)**_|❌|❌|❌|❌||
140
|[whiterabbitneo.com](https://www.whiterabbitneo.com)|[Manual cookies](https://www.whiterabbitneo.com)|`g4f.Provider.WhiteRabbitNeo`|✔|❌|❌|❌|❌||
141
|[console.x.ai](https://console.x.ai)|[Get API key](https://console.x.ai)|`g4f.Provider.xAI`|✔|❌|❌|❌|❌||
139
142
140
143
---
141
144
## Models
@@ -160,13 +163,13 @@ This document provides an overview of various AI providers and models, including
160
163
|llama-3.1-405b|Meta Llama|2+ Providers|[huggingface.co](https://huggingface.co/meta-llama/Llama-3.1-405B)|
161
164
|llama-3.2-1b|Meta Llama|1+ Providers|[huggingface.co](https://huggingface.co/meta-llama/Llama-3.2-1B)|
162
165
|llama-3.2-3b|Meta Llama|1+ Providers|[huggingface.co](https://huggingface.co/meta-llama/Llama-3.2-3B)|
163
|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/)|
166
|llama-3.2-11b|Meta Llama|4+ Providers|[ai.meta.com](https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/)|
164
167
|llama-3.2-90b|Meta Llama|2+ Providers|[huggingface.co](https://huggingface.co/meta-llama/Llama-3.2-90B-Vision)|
165
|llama-3.3-70b|Meta Llama|7+ Providers|[ai.meta.com](https://ai.meta.com/blog/llama-3-3/)|
168
|llama-3.3-70b|Meta Llama|8+ Providers|[ai.meta.com](https://ai.meta.com/blog/llama-3-3/)|
166
169
|mixtral-8x7b|Mistral|1+ Providers|[mistral.ai](https://mistral.ai/news/mixtral-of-experts/)|
167
170
|mixtral-8x22b|Mistral|1+ Providers|[huggingface.co](https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1)|
168
171
|mistral-nemo|Mistral|3+ Providers|[huggingface.co](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)|
169
|mixtral-small-24b|Mistral|2+ Providers|[huggingface.co](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501)|
172
|mixtral-small-24b|Mistral|3+ Providers|[huggingface.co](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501)|
170
173
|hermes-3|NousResearch|1+ Providers|[huggingface.co](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B-FP8)|
171
174
|phi-3.5-mini|Microsoft|1+ Providers|[huggingface.co](https://huggingface.co/microsoft/Phi-3.5-mini-instruct)|
172
175
|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)|
@@ -199,11 +202,11 @@ This document provides an overview of various AI providers and models, including
199
202
|qwen-2.5-coder-32b|Qwen|3+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2.5-Coder-32B)|
200
203
|qwen-2.5-1m|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2.5-1M-Demo)|
201
204
|qwen-2-5-max|Qwen|1+ Providers|[qwen-ai.com](https://www.qwen-ai.com/2-5-max/)|
202
|qwq-32b|Qwen|2+ Providers|[huggingface.co](https://huggingface.co/Qwen/QwQ-32B-Preview)|
205
|qwq-32b|Qwen|4+ Providers|[huggingface.co](https://huggingface.co/Qwen/QwQ-32B-Preview)|
203
206
|qvq-72b|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/QVQ-72B-Preview)|
204
207
|pi|Inflection|1+ Providers|[inflection.ai](https://inflection.ai/blog/inflection-2-5)|
205
208
|deepseek-chat|DeepSeek|2+ Providers|[huggingface.co](https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat)|
206
|deepseek-v3|DeepSeek|5+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/news/news250120)|
209
|deepseek-v3|DeepSeek|6+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/news/news250120)|
207
210
|deepseek-r1|DeepSeek|10+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/news/news250120)|
208
211
|janus-pro-7b|DeepSeek|2+ Providers|[api-docs.deepseek.com](https://api-docs.deepseek.com/docs/janus-pro-7b)|
209
212
|grok-3|x.ai|1+ Providers|[x.ai](https://x.ai/blog/grok-3)|
@@ -223,11 +226,13 @@ This document provides an overview of various AI providers and models, including
223
226
|airoboros-70b|DeepInfra|1+ Providers|[huggingface.co](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-llama-3-70b)|
224
227
|lzlv-70b|Lizpreciatior|1+ Providers|[huggingface.co](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-llama-3-70b)|
225
228
|minicpm-2.5|OpenBMB|1+ Providers|[huggingface.co](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5)|
226
|tulu-3-405b|Ai2|1+ Providers|[allenai.org](https://allenai.org/documentation)|
227
|olmo-2-13b|Ai2|1+ Providers|[allenai.org](https://allenai.org/documentation)|
228
229
|tulu-3-1-8b|Ai2|1+ Providers|[allenai.org](https://allenai.org/documentation)|
229
230
|tulu-3-70b|Ai2|1+ Providers|[allenai.org](https://allenai.org/documentation)|
230
|olmoe-0125|Ai2|1+ Providers|[allenai.org](https://allenai.org/documentation)|
231
|tulu-3-405b|Ai2|1+ Providers|[allenai.org](https://allenai.org/documentation)|
232
|olmo-1-7b|Ai2|1+ Providers|[allenai.org](https://allenai.org/olmo)|
233
|olmo-2-13b|Ai2|1+ Providers|[allenai.org](https://allenai.org/olmo)|
234
|olmo-2-32b|Ai2|1+ Providers|[allenai.org](https://allenai.org/olmo)|
235
|olmo-4-synthetic|Ai2|1+ Providers|[allenai.org](https://allenai.org/olmo)|
231
236
|lfm-40b|Liquid AI|1+ Providers|[liquid.ai](https://www.liquid.ai/liquid-foundation-models)|
232
237
|evil|Evil Mode - Experimental|2+ Providers|[]( )|
233
238
@@ -237,7 +242,7 @@ This document provides an overview of various AI providers and models, including
237
242
|-------|---------------|-----------|---------|
238
243
|sdxl-turbo|Stability AI|2+ Providers|[huggingface.co](https://huggingface.co/stabilityai/sdxl-turbo)|
239
244
|sd-3.5|Stability AI|1+ Providers|[huggingface.co](https://huggingface.co/stabilityai/stable-diffusion-3.5-large)|
240
|flux|Black Forest Labs|4+ Providers|[github.com/black-forest-labs/flux](https://github.com/black-forest-labs/flux)|
245
|flux|Black Forest Labs|5+ Providers|[github.com/black-forest-labs/flux](https://github.com/black-forest-labs/flux)|
241
246
|flux-pro|Black Forest Labs|1+ Providers|[huggingface.co](https://huggingface.co/enhanceaiteam/FLUX.1-Pro)|
242
247
|flux-dev|Black Forest Labs|4+ Providers|[huggingface.co](https://huggingface.co/black-forest-labs/FLUX.1-dev)|
243
248
|flux-schnell|Black Forest Labs|4+ Providers|[huggingface.co](https://huggingface.co/black-forest-labs/FLUX.1-schnell)|
@@ -0,0 +1,105 @@
1
#!/usr/bin/env python3
2
"""
3
AI Commit Message Generator using gpt4free (g4f)
4
5
This tool uses AI to generate meaningful git commit messages based on
6
staged changes. It analyzes the git diff and suggests appropriate commit
7
messages following conventional commit format.
8
9
Usage:
10
python -m etc.tool.commit
11
"""
12
import subprocess
13
import sys
14
from g4f.client import Client
15
16
def get_git_diff():
17
"""Get the current git diff for staged changes"""
18
try:
19
diff_process = subprocess.run(
20
["git", "diff", "--staged"],
21
capture_output=True,
22
text=True
23
)
24
return diff_process.stdout
25
except Exception as e:
26
print(f"Error running git diff: {e}")
27
return None
28
29
def generate_commit_message(diff_text):
30
"""Generate a commit message based on the git diff"""
31
if not diff_text or diff_text.strip() == "":
32
return "No changes staged for commit"
33
34
client = Client()
35
36
prompt = f"""
37
{diff_text}
38
```
39
40
Analyze ONLY the exact changes in this git diff and create a precise commit message.
41
42
FORMAT:
43
1. First line: "<type>: <summary>" (max 70 chars)
44
- Type: feat, fix, docs, refactor, test, etc.
45
- Summary must describe ONLY actual changes shown in the diff
46
47
2. Leave one blank line
48
49
3. Add sufficient bullet points to:
50
- Describe ALL specific changes seen in the diff
51
- Reference exact functions/files/components that were modified
52
- Do NOT mention anything not explicitly shown in the code changes
53
- Avoid general statements or assumptions not directly visible in diff
54
- Include enough points to cover all significant changes (don't limit to a specific number)
55
56
IMPORTANT: Be 100% factual. Only mention code that was actually changed. Never invent or assume changes not shown in the diff. If unsure about a change's purpose, describe what changed rather than why. Output nothing except for the commit message, and don't surround it in quotes.
57
"""
58
59
try:
60
response = client.chat.completions.create(
61
model="claude-3.7-sonnet",
62
messages=[{"role": "user", "content": prompt}]
63
)
64
65
return response.choices[0].message.content.strip()
66
except Exception as e:
67
print(f"Error generating commit message: {e}")
68
return None
69
70
def main():
71
print("Fetching git diff...")
72
diff = get_git_diff()
73
74
if diff is None:
75
print("Failed to get git diff. Are you in a git repository?")
76
sys.exit(1)
77
78
if diff.strip() == "":
79
print("No changes staged for commit. Stage changes with 'git add' first.")
80
sys.exit(0)
81
82
print("Generating commit message...")
83
commit_message = generate_commit_message(diff)
84
85
if commit_message:
86
print("\nGenerated commit message:")
87
print("-" * 50)
88
print(commit_message)
89
print("-" * 50)
90
91
user_input = input("\nDo you want to use this commit message? (y/n): ")
92
if user_input.lower() == 'y':
93
try:
94
subprocess.run(
95
["git", "commit", "-m", commit_message],
96
check=True
97
)
98
print("Commit successful!")
99
except subprocess.CalledProcessError as e:
100
print(f"Error making commit: {e}")
101
else:
102
print("Failed to generate commit message.")
103
104
if __name__ == "__main__":
105
main()
@@ -27,7 +27,8 @@ class ARTA(AsyncGeneratorProvider, ProviderModelMixin):
27
27
default_model = "Flux"
28
28
default_image_model = default_model
29
29
model_aliases = {
30
"flux": "Flux",
30
default_image_model: default_image_model,
31
"flux": default_image_model,
31
32
"medieval": "Medieval",
32
33
"vincent_van_gogh": "Vincent Van Gogh",
33
34
"f_dev": "F Dev",
@@ -91,7 +92,17 @@ class ARTA(AsyncGeneratorProvider, ProviderModelMixin):
91
92
# Step 1: Generate Authentication Token
92
93
auth_payload = {"clientType": "CLIENT_TYPE_ANDROID"}
93
94
async with session.post(cls.auth_url, json=auth_payload, proxy=proxy) as auth_response:
94
auth_data = await auth_response.json()
95
if auth_response.status >= 400:
96
error_text = await auth_response.text()
97
raise ResponseError(f"Failed to obtain authentication token. Status: {auth_response.status}, Response: {error_text}")
98
99
try:
100
auth_data = await auth_response.json()
101
except Exception as e:
102
error_text = await auth_response.text()
103
content_type = auth_response.headers.get('Content-Type', 'unknown')
104
raise ResponseError(f"Failed to parse auth response as JSON. Content-Type: {content_type}, Error: {str(e)}, Response: {error_text}")
105
95
106
auth_token = auth_data.get("idToken")
96
107
#refresh_token = auth_data.get("refreshToken")
97
108
if not auth_token:
@@ -107,7 +118,17 @@ class ARTA(AsyncGeneratorProvider, ProviderModelMixin):
107
118
"refresh_token": refresh_token,
108
119
}
109
120
async with session.post(cls.token_refresh_url, data=payload, proxy=proxy) as response:
110
response_data = await response.json()
121
if response.status >= 400:
122
error_text = await response.text()
123
raise ResponseError(f"Failed to refresh token. Status: {response.status}, Response: {error_text}")
124
125
try:
126
response_data = await response.json()
127
except Exception as e:
128
error_text = await response.text()
129
content_type = response.headers.get('Content-Type', 'unknown')
130
raise ResponseError(f"Failed to parse token refresh response as JSON. Content-Type: {content_type}, Error: {str(e)}, Response: {error_text}")
131
111
132
return response_data.get("id_token"), response_data.get("refresh_token")
112
133
113
134
@classmethod
@@ -167,9 +188,18 @@ class ARTA(AsyncGeneratorProvider, ProviderModelMixin):
167
188
}
168
189
169
190
async with session.post(cls.image_generation_url, data=image_payload, headers=headers, proxy=proxy) as image_response:
170
image_data = await image_response.json()
191
if image_response.status >= 400:
192
error_text = await image_response.text()
193
raise ResponseError(f"Failed to initiate image generation. Status: {image_response.status}, Response: {error_text}")
194
195
try:
196
image_data = await image_response.json()
197
except Exception as e:
198
error_text = await image_response.text()
199
content_type = image_response.headers.get('Content-Type', 'unknown')
200
raise ResponseError(f"Failed to parse response as JSON. Content-Type: {content_type}, Error: {str(e)}, Response: {error_text}")
201
171
202
record_id = image_data.get("record_id")
172
173
203
if not record_id:
174
204
raise ResponseError(f"Failed to initiate image generation: {image_data}")
175
205
@@ -180,7 +210,17 @@ class ARTA(AsyncGeneratorProvider, ProviderModelMixin):
180
210
last_status = None
181
211
while True:
182
212
async with session.get(status_url, headers=headers, proxy=proxy) as status_response:
183
status_data = await status_response.json()
213
if status_response.status >= 400:
214
error_text = await status_response.text()
215
raise ResponseError(f"Failed to check image generation status. Status: {status_response.status}, Response: {error_text}")
216
217
try:
218
status_data = await status_response.json()
219
except Exception as e:
220
error_text = await status_response.text()
221
content_type = status_response.headers.get('Content-Type', 'unknown')
222
raise ResponseError(f"Failed to parse status response as JSON. Content-Type: {content_type}, Error: {str(e)}, Response: {error_text}")
223
184
224
status = status_data.get("status")
185
225
186
226
if status == "DONE":
@@ -2,21 +2,23 @@ from __future__ import annotations
2
2
import json
3
3
from uuid import uuid4
4
4
from aiohttp import ClientSession
5
from ..typing import AsyncResult, Messages
5
from ..typing import AsyncResult, Messages, MediaListType
6
from ..image import to_bytes, is_accepted_format, to_data_uri
6
7
from .base_provider import AsyncGeneratorProvider, ProviderModelMixin
7
8
from ..requests.raise_for_status import raise_for_status
8
9
from ..providers.response import FinishReason, JsonConversation
9
from .helper import format_prompt, get_last_user_message
10
from .helper import format_prompt, get_last_user_message, format_image_prompt
11
from ..tools.media import merge_media
10
12
11
13
12
14
class Conversation(JsonConversation):
13
parent: str = None
14
15
x_anonymous_user_id: str = None
15
16
16
17
def __init__(self, model: str):
17
18
super().__init__() # Ensure parent class is initialized
18
19
self.model = model
19
20
self.messages = [] # Instance-specific list
21
self.parent = None # Initialize parent as instance attribute
20
22
if not self.x_anonymous_user_id:
21
23
self.x_anonymous_user_id = str(uuid4())
22
24
@@ -35,42 +37,73 @@ class AllenAI(AsyncGeneratorProvider, ProviderModelMixin):
35
37
supports_message_history = True
36
38
37
39
default_model = 'tulu3-405b'
38
models = [
39
default_model,
40
'OLMo-2-1124-13B-Instruct',
41
'tulu-3-1-8b',
42
'Llama-3-1-Tulu-3-70B',
43
'olmoe-0125'
44
]
40
default_vision_model = 'mm-olmo-uber-model-v4-synthetic'
41
vision_models = [default_vision_model]
42
# Map models to their required hosts
43
model_hosts = {
44
default_model: "inferd",
45
"OLMo-2-1124-13B-Instruct": "modal",
46
"tulu-3-1-8b": "modal",
47
"Llama-3-1-Tulu-3-70B": "modal",
48
"olmoe-0125": "modal",
49
"olmo-2-0325-32b-instruct": "modal",
50
"mm-olmo-uber-model-v4-synthetic": "modal",
51
}
52
53
models = list(model_hosts.keys())
45
54
46
55
model_aliases = {
47
56
"tulu-3-405b": default_model,
57
"olmo-1-7b": "olmoe-0125",
48
58
"olmo-2-13b": "OLMo-2-1124-13B-Instruct",
59
"olmo-2-32b": "olmo-2-0325-32b-instruct",
49
60
"tulu-3-1-8b": "tulu-3-1-8b",
50
61
"tulu-3-70b": "Llama-3-1-Tulu-3-70B",
51
62
"llama-3.1-405b": "tulu3-405b",
52
63
"llama-3.1-8b": "tulu-3-1-8b",
53
64
"llama-3.1-70b": "Llama-3-1-Tulu-3-70B",
65
"olmo-4-synthetic": "mm-olmo-uber-model-v4-synthetic",
54
66
}
55
67
68
56
69
@classmethod
57
70
async def create_async_generator(
58
71
cls,
59
72
model: str,
60
73
messages: Messages,
61
74
proxy: str = None,
62
host: str = "inferd",
75
host: str = None,
63
76
private: bool = True,
64
77
top_p: float = None,
65
78
temperature: float = None,
66
79
conversation: Conversation = None,
67
80
return_conversation: bool = False,
81
media: MediaListType = None,
68
82
**kwargs
69
83
) -> AsyncResult:
70
prompt = format_prompt(messages) if conversation is None else get_last_user_message(messages)
84
actual_model = cls.get_model(model)
85
86
# Use format_image_prompt for vision models when media is provided
87
if media is not None and len(media) > 0:
88
# For vision models, use format_image_prompt
89
if actual_model in cls.vision_models:
90
prompt = format_image_prompt(messages)
91
else:
92
# For non-vision models with images, still use the last user message
93
prompt = get_last_user_message(messages)
94
else:
95
# For text-only messages, use the standard format
96
prompt = format_prompt(messages) if conversation is None else get_last_user_message(messages)
97
98
# Determine the correct host for the model
99
if host is None:
100
# Use model-specific host from model_hosts dictionary
101
host = cls.model_hosts[actual_model]
102
71
103
# Initialize or update conversation
72
if conversation is None:
73
conversation = Conversation(model)
104
# For mm-olmo-uber-model-v4-synthetic, always create a new conversation
105
if conversation is None or actual_model == 'mm-olmo-uber-model-v4-synthetic':
106
conversation = Conversation(actual_model)
74
107
75
108
# Generate new boundary for each request
76
109
boundary = f"----WebKitFormBoundary{uuid4().hex}"
@@ -101,7 +134,7 @@ class AllenAI(AsyncGeneratorProvider, ProviderModelMixin):
101
134
]
102
135
103
136
# Add parent if exists in conversation
104
if conversation.parent:
137
if hasattr(conversation, 'parent') and conversation.parent:
105
138
form_data.append(
106
139
f'--{boundary}\r\n'
107
140
f'Content-Disposition: form-data; name="parent"\r\n\r\n{conversation.parent}\r\n'
@@ -120,8 +153,25 @@ class AllenAI(AsyncGeneratorProvider, ProviderModelMixin):
120
153
f'Content-Disposition: form-data; name="top_p"\r\n\r\n{top_p}\r\n'
121
154
)
122
155
156
# Always create a new conversation when an image is attached to avoid 403 errors
157
if media is not None and len(media) > 0:
158
conversation = Conversation(actual_model)
159
160
# Add image if provided
161
if media is not None and len(media) > 0:
162
# For each image in the media list (using merge_media to handle different formats)
163
for image, image_name in merge_media(media, messages):
164
image_bytes = to_bytes(image)
165
form_data.extend([
166
f'--{boundary}\r\n'
167
f'Content-Disposition: form-data; name="files"; filename="{image_name}"\r\n'
168
f'Content-Type: {is_accepted_format(image_bytes)}\r\n\r\n'
169
])
170
form_data.append(image_bytes.decode('latin1'))
171
form_data.append('\r\n')
172
123
173
form_data.append(f'--{boundary}--\r\n')
124
data = "".join(form_data).encode()
174
data = "".join(form_data).encode('latin1')
125
175
126
176
async with ClientSession(headers=headers) as session:
127
177
async with session.post(
@@ -164,6 +214,9 @@ class AllenAI(AsyncGeneratorProvider, ProviderModelMixin):
164
214
# Processing the final response
165
215
if data.get("final") or data.get("finish_reason") == "stop":
166
216
if current_parent:
217
# Ensure the parent attribute exists before setting it
218
if not hasattr(conversation, 'parent'):
219
setattr(conversation, 'parent', None)
167
220
conversation.parent = current_parent
168
221
169
222
# Add a message to the story
@@ -26,6 +26,9 @@ except ImportError:
26
26
class DuckDuckGoSearchException(Exception):
27
27
"""Base exception class for duckduckgo_search."""
28
28
29
class DuckDuckGoChallengeError(ResponseStatusError):
30
"""Raised when DuckDuckGo presents a challenge that needs to be solved."""
31
29
32
class Conversation(JsonConversation):
30
33
vqd: str = None
31
34
vqd_hash_1: str = None
@@ -48,14 +51,19 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
48
51
supports_message_history = True
49
52
50
53
default_model = "gpt-4o-mini"
51
models = [default_model, "meta-llama/Llama-3.3-70B-Instruct-Turbo", "claude-3-haiku-20240307", "o3-mini", "mistralai/Mistral-Small-24B-Instruct-2501"]
52
53
model_aliases = {
54
"gpt-4": "gpt-4o-mini",
54
55
# Model mapping from user-friendly names to API model names
56
_chat_models = {
57
"gpt-4": default_model,
58
"gpt-4o-mini": default_model,
55
59
"llama-3.3-70b": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
56
60
"claude-3-haiku": "claude-3-haiku-20240307",
61
"o3-mini": "o3-mini",
57
62
"mixtral-small-24b": "mistralai/Mistral-Small-24B-Instruct-2501",
58
63
}
64
65
# Available models (user-friendly names)
66
models = list(_chat_models.keys())
59
67
60
68
last_request_time = 0
61
69
max_retries = 3
@@ -100,19 +108,52 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
100
108
def build_x_vqd_hash_1(cls, vqd_hash_1: str, headers: dict) -> str:
101
109
"""Build the x-vqd-hash-1 header value."""
102
110
try:
103
decoded = base64.b64decode(vqd_hash_1).decode()
104
server_hashes = cls.parse_server_hashes(decoded)
105
dom_fingerprint = cls.parse_dom_fingerprint(decoded)
106
111
# If we received a valid base64 string, try to decode it
112
if vqd_hash_1 and len(vqd_hash_1) > 20:
113
try:
114
# Try to decode and parse as JSON first
115
decoded_json = json.loads(base64.b64decode(vqd_hash_1).decode())
116
# If it's already a complete structure with meta, return it as is
117
if isinstance(decoded_json, dict) and "meta" in decoded_json:
118
return vqd_hash_1
119
120
# Otherwise, extract what we can from it
121
if isinstance(decoded_json, dict) and "server_hashes" in decoded_json:
122
server_hashes = decoded_json.get("server_hashes", ["1", "2"])
123
else:
124
# Fall back to parsing from string
125
decoded = base64.b64decode(vqd_hash_1).decode()
126
server_hashes = cls.parse_server_hashes(decoded)
127
except (json.JSONDecodeError, UnicodeDecodeError):
128
# If it's not valid JSON, try to parse it as a string
129
decoded = base64.b64decode(vqd_hash_1).decode()
130
server_hashes = cls.parse_server_hashes(decoded)
131
else:
132
# Default server hashes if we can't extract them
133
server_hashes = ["1", "2"]
134
135
# Generate fingerprints
136
dom_fingerprint = "1000" # Default value
107
137
ua_fingerprint = headers.get("User-Agent", "") + headers.get("sec-ch-ua", "")
108
138
ua_hash = cls.sha256_base64(ua_fingerprint)
109
139
dom_hash = cls.sha256_base64(dom_fingerprint)
110
140
141
# Create a challenge ID (random hex string)
142
challenge_id = ''.join(random.choice('0123456789abcdef') for _ in range(40)) + 'h8jbt'
143
144
# Build the complete structure including meta
111
145
final_result = {
112
146
"server_hashes": server_hashes,
113
147
"client_hashes": [ua_hash, dom_hash],
114
148
"signals": {},
149
"meta": {
150
"v": "1",
151
"challenge_id": challenge_id,
152
"origin": "https://duckduckgo.com",
153
"stack": "Error\nat ke (https://duckduckgo.com/dist/wpm.chat.js:1:29526)\nat async dispatchServiceInitialVQD (https://duckduckgo.com/dist/wpm.chat.js:1:45076)"
154
}
115
155
}
156
116
157
base64_final_result = base64.b64encode(json.dumps(final_result).encode()).decode()
117
158
return base64_final_result
118
159
except Exception as e:
@@ -121,13 +162,18 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
121
162
122
163
@classmethod
123
164
def validate_model(cls, model: str) -> str:
124
"""Validates and returns the correct model name"""
165
"""Validates and returns the correct model name for the API"""
125
166
if not model:
126
167
return cls.default_model
168
169
# Check aliases first
127
170
if model in cls.model_aliases:
128
171
model = cls.model_aliases[model]
172
173
# Check if it's a valid model name
129
174
if model not in cls.models:
130
175
raise ModelNotSupportedError(f"Model {model} not supported. Available models: {cls.models}")
176
131
177
return model
132
178
133
179
@classmethod
@@ -147,18 +193,45 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
147
193
await cls.sleep()
148
194
# Make initial request to get cookies
149
195
async with session.get(cls.url) as response:
150
# We also manually set required cookies
196
# Set the required cookies
151
197
cookies = {}
152
198
cookies_dict = {'dcs': '1', 'dcm': '3'}
153
199
200
# Add any cookies from the response
201
for cookie in response.cookies.values():
202
cookies[cookie.key] = cookie.value
203
204
# Ensure our required cookies are set
154
205
for name, value in cookies_dict.items():
155
206
cookies[name] = value
156
207
url_obj = URL(cls.url)
157
208
session.cookie_jar.update_cookies({name: value}, url_obj)
158
209
210
# Make a second request to the status endpoint to get any additional cookies
211
headers = {
212
"accept": "text/event-stream",
213
"accept-language": "en",
214
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.0.0.0 Safari/537.36",
215
"origin": "https://duckduckgo.com",
216
"referer": "https://duckduckgo.com/",
217
}
218
219
await cls.sleep()
220
async with session.get(cls.status_url, headers=headers) as status_response:
221
# Add any cookies from the status response
222
for cookie in status_response.cookies.values():
223
cookies[cookie.key] = cookie.value
224
url_obj = URL(cls.url)
225
session.cookie_jar.update_cookies({cookie.key: cookie.value}, url_obj)
226
159
227
return cookies
160
228
except Exception as e:
161
return {}
229
# Return at least the required cookies on error
230
cookies = {'dcs': '1', 'dcm': '3'}
231
url_obj = URL(cls.url)
232
for name, value in cookies.items():
233
session.cookie_jar.update_cookies({name: value}, url_obj)
234
return cookies
162
235
163
236
@classmethod
164
237
async def fetch_fe_version(cls, session: ClientSession) -> str:
@@ -175,26 +248,38 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
175
248
176
249
# Extract x-fe-version components
177
250
try:
251
# Try to extract the version components
178
252
xfe1 = content.split('__DDG_BE_VERSION__="', 1)[1].split('"', 1)[0]
179
253
xfe2 = content.split('__DDG_FE_CHAT_HASH__="', 1)[1].split('"', 1)[0]
180
cls._chat_xfe = f"{xfe1}-{xfe2}"
254
255
# Format it like "serp_YYYYMMDD_HHMMSS_ET-hash"
256
from datetime import datetime
257
current_date = datetime.now().strftime("%Y%m%d_%H%M%S")
258
cls._chat_xfe = f"serp_{current_date}_ET-{xfe2}"
259
181
260
return cls._chat_xfe
182
261
except Exception:
183
# If extraction fails, return an empty string
184
return ""
262
# Fallback to a default format if extraction fails
263
from datetime import datetime
264
current_date = datetime.now().strftime("%Y%m%d_%H%M%S")
265
cls._chat_xfe = f"serp_{current_date}_ET-78c2e87e3d286691cc21"
266
return cls._chat_xfe
185
267
except Exception:
186
return ""
268
# Fallback to a default format if request fails
269
from datetime import datetime
270
current_date = datetime.now().strftime("%Y%m%d_%H%M%S")
271
cls._chat_xfe = f"serp_{current_date}_ET-78c2e87e3d286691cc21"
272
return cls._chat_xfe
187
273
188
274
@classmethod
189
275
async def fetch_vqd_and_hash(cls, session: ClientSession, retry_count: int = 0) -> tuple[str, str]:
190
276
"""Fetches the required VQD token and hash for the chat session with retries."""
191
277
headers = {
192
278
"accept": "text/event-stream",
193
"accept-language": "en-US,en;q=0.9",
279
"accept-language": "en",
194
280
"cache-control": "no-cache",
195
"content-type": "application/json",
196
281
"pragma": "no-cache",
197
"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",
282
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.0.0.0 Safari/537.36",
198
283
"origin": "https://duckduckgo.com",
199
284
"referer": "https://duckduckgo.com/",
200
285
"x-vqd-accept": "1",
@@ -270,30 +355,44 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
270
355
last_message = get_last_user_message(messages.copy())
271
356
conversation.message_history.append({"role": "user", "content": last_message})
272
357
273
# Step 4: Prepare headers - IMPORTANT: send empty x-vqd-hash-1 for the first request
358
# Step 4: Prepare headers with proper x-vqd-hash-1
274
359
headers = {
275
360
"accept": "text/event-stream",
276
"accept-language": "en-US,en;q=0.9",
361
"accept-language": "en",
362
"cache-control": "no-cache",
277
363
"content-type": "application/json",
278
"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",
364
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.0.0.0 Safari/537.36",
279
365
"origin": "https://duckduckgo.com",
280
366
"referer": "https://duckduckgo.com/",
281
"sec-ch-ua": '"Chromium";v="133", "Not_A Brand";v="8"',
367
"pragma": "no-cache",
368
"priority": "u=1, i",
369
"sec-ch-ua": '"Not:A-Brand";v="24", "Chromium";v="134"',
370
"sec-ch-ua-mobile": "?0",
371
"sec-ch-ua-platform": '"Linux"',
372
"sec-fetch-dest": "empty",
373
"sec-fetch-mode": "cors",
374
"sec-fetch-site": "same-origin",
282
375
"x-fe-version": conversation.fe_version or cls._chat_xfe,
283
376
"x-vqd-4": conversation.vqd,
284
"x-vqd-hash-1": "", # Send empty string initially
285
377
}
378
379
# For the first request, send an empty x-vqd-hash-1 header
380
# This matches the behavior in the duckduckgo_search module
381
headers["x-vqd-hash-1"] = ""
286
382
287
383
# Step 5: Prepare the request data
384
# Convert the user-friendly model name to the API model name
385
api_model = cls._chat_models.get(model, model)
386
288
387
data = {
289
"model": model,
388
"model": api_model,
290
389
"messages": conversation.message_history,
291
390
}
292
391
293
392
# Step 6: Send the request
294
393
await cls.sleep(multiplier=1.0 + retry_count * 0.5)
295
394
async with session.post(cls.api_endpoint, json=data, headers=headers, proxy=proxy) as response:
296
# Handle 429 errors specifically
395
# Handle 429 and 418 errors specifically
297
396
if response.status == 429:
298
397
response_text = await response.text()
299
398
@@ -307,7 +406,69 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
307
406
continue
308
407
else:
309
408
raise RateLimitError(f"Rate limited after {cls.max_retries} retries")
409
elif response.status == 418:
410
# Check if it's a challenge error
411
try:
412
response_text = await response.text()
413
try:
414
response_json = json.loads(response_text)
415
416
# Extract challenge data if available
417
challenge_data = None
418
if response_json.get("type") == "ERR_CHALLENGE" and "cd" in response_json:
419
challenge_data = response_json["cd"]
420
421
if retry_count < cls.max_retries:
422
retry_count += 1
423
wait_time = cls.base_delay * (2 ** retry_count) * (1 + random.random())
424
await asyncio.sleep(wait_time)
425
426
# Reset tokens and try again with fresh session
427
conversation = None
428
cls._chat_xfe = ""
429
430
# Get fresh cookies
431
cookies = await cls.get_default_cookies(session)
432
433
# If we have challenge data, try to use it
434
if challenge_data and isinstance(challenge_data, dict):
435
# Extract any useful information from challenge data
436
# This could be used to build a better response in the future
437
pass
438
439
continue
440
else:
441
raise DuckDuckGoChallengeError(f"Challenge error after {cls.max_retries} retries")
442
except json.JSONDecodeError:
443
# If we can't parse the JSON, assume it's a challenge error anyway
444
if retry_count < cls.max_retries:
445
retry_count += 1
446
wait_time = cls.base_delay * (2 ** retry_count) * (1 + random.random())
447
await asyncio.sleep(wait_time)
448
449
# Reset tokens and try again with fresh session
450
conversation = None
451
cls._chat_xfe = ""
452
cookies = await cls.get_default_cookies(session)
453
continue
454
else:
455
raise DuckDuckGoChallengeError(f"Challenge error after {cls.max_retries} retries")
456
except Exception as e:
457
# If any other error occurs during handling, still try to recover
458
if retry_count < cls.max_retries:
459
retry_count += 1
460
wait_time = cls.base_delay * (2 ** retry_count) * (1 + random.random())
461
await asyncio.sleep(wait_time)
462
463
# Reset tokens and try again with fresh session
464
conversation = None
465
cls._chat_xfe = ""
466
cookies = await cls.get_default_cookies(session)
467
continue
468
else:
469
raise DuckDuckGoChallengeError(f"Challenge error after {cls.max_retries} retries: {str(e)}")
310
470
471
# For other status codes, use the standard error handler
311
472
await raise_for_status(response)
312
473
reason = None
313
474
full_message = ""
@@ -328,6 +489,11 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
328
489
if error_type == "ERR_CONVERSATION_LIMIT":
329
490
raise ConversationLimitError(error_type)
330
491
raise RateLimitError(error_type)
492
elif message.get("status") == 418 and error_type == "ERR_CHALLENGE":
493
# Handle challenge error by refreshing tokens and retrying
494
if retry_count < cls.max_retries:
495
# Don't raise here, let the outer exception handler retry
496
raise DuckDuckGoChallengeError(f"Challenge detected: {error_type}")
331
497
raise DuckDuckGoSearchException(error_type)
332
498
333
499
if "message" in message:
@@ -339,15 +505,19 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
339
505
reason = "stop"
340
506
341
507
# Step 8: Update conversation with response information
508
# Always update the VQD tokens from the response headers
509
conversation.vqd = response.headers.get("x-vqd-4", conversation.vqd)
510
conversation.vqd_hash_1 = response.headers.get("x-vqd-hash-1", conversation.vqd_hash_1)
511
512
# Update cookies
513
conversation.cookies = {
514
n: c.value
515
for n, c in session.cookie_jar.filter_cookies(URL(cls.url)).items()
516
}
517
518
# If requested, return the updated conversation
342
519
if return_conversation:
343
520
conversation.message_history.append({"role": "assistant", "content": full_message})
344
# Update tokens from response headers
345
conversation.vqd = response.headers.get("x-vqd-4", conversation.vqd)
346
conversation.vqd_hash_1 = response.headers.get("x-vqd-hash-1", conversation.vqd_hash_1)
347
conversation.cookies = {
348
n: c.value
349
for n, c in session.cookie_jar.filter_cookies(URL(cls.url)).items()
350
}
351
521
yield conversation
352
522
353
523
if reason is not None:
@@ -356,11 +526,18 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
356
526
# If we got here, the request was successful
357
527
break
358
528
359
except (RateLimitError, ResponseStatusError) as e:
360
if "429" in str(e) and retry_count < cls.max_retries:
529
except (RateLimitError, ResponseStatusError, DuckDuckGoChallengeError) as e:
530
if ("429" in str(e) or isinstance(e, DuckDuckGoChallengeError)) and retry_count < cls.max_retries:
361
531
retry_count += 1
362
532
wait_time = cls.base_delay * (2 ** retry_count) * (1 + random.random())
363
533
await asyncio.sleep(wait_time)
534
535
# For challenge errors, refresh tokens and cookies
536
if isinstance(e, DuckDuckGoChallengeError):
537
# Reset conversation to force new token acquisition
538
conversation = None
539
# Clear class cache to force refresh
540
cls._chat_xfe = ""
364
541
else:
365
542
raise
366
543
except asyncio.TimeoutError as e:
@@ -46,11 +46,13 @@ class PollinationsAI(AsyncGeneratorProvider, ProviderModelMixin):
46
46
default_model = "openai"
47
47
default_image_model = "flux"
48
48
default_vision_model = default_model
49
default_audio_model = "openai-audio"
49
50
text_models = [default_model]
50
51
image_models = [default_image_model]
52
audio_models = [default_audio_model]
51
53
extra_image_models = ["flux-pro", "flux-dev", "flux-schnell", "midjourney", "dall-e-3", "turbo"]
52
vision_models = [default_vision_model, "gpt-4o-mini", "o3-mini", "openai", "openai-large"]
53
extra_text_models = vision_models
54
vision_models = ["gpt-4o-mini", "o3-mini", "openai-large"] # Removed duplicates with default_model
55
extra_text_models = [] # Will be populated with unique vision models
54
56
_models_loaded = False
55
57
model_aliases = {
56
58
### Text Models ###
@@ -68,7 +70,12 @@ class PollinationsAI(AsyncGeneratorProvider, ProviderModelMixin):
68
70
"gemini-2.0": "gemini",
69
71
"gemini-2.0-flash": "gemini",
70
72
"gemini-2.0-flash-thinking": "gemini-thinking",
71
"deepseek-r1": "deepseek-r1-llama",
73
"gemini-2.0-flash-thinking": "gemini-reasoning",
74
"deepseek-r1": "deepseek-reasoning-large",
75
"deepseek-r1": "deepseek-reasoning",
76
"deepseek-v3": "deepseek",
77
"qwq-32b": "qwen-reasoning",
78
"llama-3.2-11b": "llama-vision",
72
79
"gpt-4o-audio": "openai-audio",
73
80
74
81
### Image Models ###
@@ -86,37 +93,52 @@ class PollinationsAI(AsyncGeneratorProvider, ProviderModelMixin):
86
93
else:
87
94
new_image_models = []
88
95
89
# Combine models without duplicates
90
all_image_models = (
91
cls.image_models + # Already contains the default
92
cls.extra_image_models +
93
new_image_models
94
)
95
cls.image_models = list(dict.fromkeys(all_image_models))
96
# Combine image models without duplicates
97
all_image_models = [cls.default_image_model] # Start with default model
98
99
# Add extra image models if not already in the list
100
for model in cls.extra_image_models + new_image_models:
101
if model not in all_image_models:
102
all_image_models.append(model)
103
104
cls.image_models = all_image_models
96
105
97
106
# Update of text models
98
107
text_response = requests.get("https://text.pollinations.ai/models")
99
108
text_response.raise_for_status()
100
109
models = text_response.json()
101
original_text_models = [
110
111
# Purpose of text models
112
cls.text_models = [
102
113
model.get("name")
103
114
for model in models
104
if model.get("type") == "chat"
115
if "input_modalities" in model and "text" in model["input_modalities"]
105
116
]
117
118
# Purpose of audio models
106
119
cls.audio_models = {
107
120
model.get("name"): model.get("voices")
108
121
for model in models
109
122
if model.get("audio")
110
123
}
124
125
# Create a set of unique text models starting with default model
126
unique_text_models = {cls.default_model}
111
127
112
# Combining text models
113
combined_text = (
114
cls.text_models + # Already contains the default
115
cls.extra_text_models +
116
original_text_models +
117
cls.vision_models
118
)
119
cls.text_models = list(dict.fromkeys(combined_text))
128
# Add models from vision_models
129
unique_text_models.update(cls.vision_models)
130
131
# Add models from the API response
132
for model in models:
133
model_name = model.get("name")
134
if model_name and "input_modalities" in model and "text" in model["input_modalities"]:
135
unique_text_models.add(model_name)
136
137
# Convert to list and update text_models
138
cls.text_models = list(unique_text_models)
139
140
# Update extra_text_models with unique vision models
141
cls.extra_text_models = [model for model in cls.vision_models if model != cls.default_model]
120
142
121
143
cls._models_loaded = True
122
144
@@ -128,7 +150,13 @@ class PollinationsAI(AsyncGeneratorProvider, ProviderModelMixin):
128
150
cls.image_models = [cls.default_image_model]
129
151
debug.error(f"Failed to fetch models: {e}")
130
152
131
return cls.text_models + cls.image_models
153
# Return unique models across all categories
154
all_models = set(cls.text_models)
155
all_models.update(cls.image_models)
156
all_models.update(cls.audio_models.keys())
157
result = list(all_models)
158
return result
159
132
160
133
161
@classmethod
134
162
async def create_async_generator(
@@ -11,6 +11,7 @@ class PollinationsImage(PollinationsAI):
11
11
default_model = "flux"
12
12
default_vision_model = None
13
13
default_image_model = default_model
14
audio_models = None
14
15
image_models = [default_image_model] # Default models
15
16
_models_loaded = False # Add a checkbox for synchronization
16
17
@@ -2306,7 +2306,7 @@ async function on_api() {
2306
2306
models.forEach((model) => {
2307
2307
let option = document.createElement("option");
2308
2308
option.value = model.name;
2309
option.text = model.name + (model.image ? " (Image Generation)" : "") + (model.vision ? " (Image Upload)" : "");
2309
option.text = model.name + (model.image ? " (Image Generation)" : "") + (model.vision ? " (Image Upload)" : "") + (model.audio ? " (Audio Generation)" : "") + (model.video ? " (Video Generation)" : "");
2310
2310
option.dataset.providers = model.providers.join(" ");
2311
2311
modelSelect.appendChild(option);
2312
2312
is_demo = model.demo;
@@ -2355,6 +2355,8 @@ async function on_api() {
2355
2355
option.text = provider.label
2356
2356
+ (provider.vision ? " (Image Upload)" : "")
2357
2357
+ (provider.image ? " (Image Generation)" : "")
2358
+ (provider.audio ? " (Audio Generation)" : "")
2359
+ (provider.video ? " (Video Generation)" : "")
2358
2360
+ (provider.nodriver ? " (Browser)" : "")
2359
2361
+ (provider.hf_space ? " (HuggingSpace)" : "")
2360
2362
+ (!provider.nodriver && provider.auth ? " (Auth)" : "");
@@ -2942,7 +2944,7 @@ async function load_provider_models(provider=null) {
2942
2944
let option = document.createElement('option');
2943
2945
option.value = model.model;
2944
2946
option.dataset.label = model.model;
2945
option.text = `${model.model}${model.image ? " (Image Generation)" : ""}${model.vision ? " (Image Upload)" : ""}`;
2947
option.text = `${model.model}${model.image ? " (Image Generation)" : ""}${model.audio ? " (Audio Generation)" : ""}${model.video ? " (Video Generation)" : ""}${model.vision ? " (Image Upload)" : ""}`;
2946
2948
if (model.task) {
2947
2949
option.text += ` (${model.task})`;
2948
2950
}
@@ -30,6 +30,8 @@ class Api:
30
30
"name": model.name,
31
31
"image": isinstance(model, models.ImageModel),
32
32
"vision": isinstance(model, models.VisionModel),
33
"audio": isinstance(model, models.AudioModel),
34
"video": isinstance(model, models.VideoModel),
33
35
"providers": [
34
36
getattr(provider, "parent", provider.__name__)
35
37
for provider in providers
@@ -52,6 +54,8 @@ class Api:
52
54
"model": model,
53
55
"default": model == provider.default_model,
54
56
"vision": getattr(provider, "default_vision_model", None) == model or model in getattr(provider, "vision_models", []),
57
"audio": getattr(provider, "default_audio_model", None) == model or model in getattr(provider, "audio_models", []),
58
"video": getattr(provider, "default_video_model", None) == model or model in getattr(provider, "video_models", []),
55
59
"image": False if provider.image_models is None else model in provider.image_models,
56
60
"task": None if not hasattr(provider, "task_mapping") else provider.task_mapping[model] if model in provider.task_mapping else None
57
61
}
@@ -66,6 +70,8 @@ class Api:
66
70
"label": provider.label if hasattr(provider, "label") else provider.__name__,
67
71
"parent": getattr(provider, "parent", None),
68
72
"image": bool(getattr(provider, "image_models", False)),
73
"audio": getattr(provider, "audio_models", None) is not None,
74
"video": getattr(provider, "video_models", None) is not None,
69
75
"vision": getattr(provider, "default_vision_model", None) is not None,
70
76
"nodriver": getattr(provider, "use_nodriver", False),
71
77
"hf_space": getattr(provider, "hf_space", False),
@@ -99,6 +99,8 @@ class Backend_Api(Api):
99
99
"name": model.name,
100
100
"image": isinstance(model, models.ImageModel),
101
101
"vision": isinstance(model, models.VisionModel),
102
"audio": isinstance(model, models.AudioModel),
103
"video": isinstance(model, models.VideoModel),
102
104
"providers": [
103
105
getattr(provider, "parent", provider.__name__)
104
106
for provider in providers
@@ -6,6 +6,7 @@ from .Provider import IterListProvider, ProviderType
6
6
from .Provider import (
7
7
### No Auth Required ###
8
8
AllenAI,
9
ARTA,
9
10
Blackbox,
10
11
ChatGLM,
11
12
ChatGptEs,
@@ -77,7 +78,10 @@ class ImageModel(Model):
77
78
78
79
class AudioModel(Model):
79
80
pass
80
81
82
class VideoModel(Model):
83
pass
84
81
85
class VisionModel(Model):
82
86
pass
83
87
@@ -105,7 +109,7 @@ default = Model(
105
109
])
106
110
)
107
111
108
default_vision = Model(
112
default_vision = VisionModel(
109
113
name = "",
110
114
base_provider = "",
111
115
best_provider = IterListProvider([
@@ -115,6 +119,7 @@ default_vision = Model(
115
119
DeepInfraChat,
116
120
PollinationsAI,
117
121
Dynaspark,
122
AllenAI,
118
123
HuggingSpace,
119
124
GeminiPro,
120
125
HuggingFaceAPI,
@@ -263,7 +268,7 @@ llama_3_2_90b = Model(
263
268
llama_3_3_70b = Model(
264
269
name = "llama-3.3-70b",
265
270
base_provider = "Meta Llama",
266
best_provider = IterListProvider([DDG, DeepInfraChat, LambdaChat, PollinationsAI, Jmuz, HuggingChat, HuggingFace])
271
best_provider = IterListProvider([Blackbox, DDG, DeepInfraChat, LambdaChat, PollinationsAI, Jmuz, HuggingChat, HuggingFace])
267
272
)
268
273
269
274
### Mistral ###
@@ -287,7 +292,7 @@ mistral_nemo = Model(
287
292
mixtral_small_24b = Model(
288
293
name = "mixtral-small-24b",
289
294
base_provider = "Mistral",
290
best_provider = IterListProvider([DDG, DeepInfraChat])
295
best_provider = IterListProvider([Blackbox, DDG, DeepInfraChat])
291
296
)
292
297
293
298
### NousResearch ###
@@ -383,7 +388,7 @@ claude_3_haiku = Model(
383
388
claude_3_5_sonnet = Model(
384
389
name = 'claude-3.5-sonnet',
385
390
base_provider = 'Anthropic',
386
best_provider = IterListProvider([Jmuz, Liaobots])
391
best_provider = IterListProvider([Blackbox, Jmuz, Liaobots])
387
392
)
388
393
389
394
# claude 3.7
@@ -491,7 +496,7 @@ qwen_2_5_max = Model(
491
496
qwq_32b = Model(
492
497
name = 'qwq-32b',
493
498
base_provider = 'Qwen',
494
best_provider = IterListProvider([Jmuz, HuggingChat])
499
best_provider = IterListProvider([Blackbox, PollinationsAI, Jmuz, HuggingChat])
495
500
)
496
501
qvq_72b = VisionModel(
497
502
name = 'qvq-72b',
@@ -516,7 +521,7 @@ deepseek_chat = Model(
516
521
deepseek_v3 = Model(
517
522
name = 'deepseek-v3',
518
523
base_provider = 'DeepSeek',
519
best_provider = IterListProvider([Blackbox, DeepInfraChat, LambdaChat, OIVSCode, TypeGPT, Liaobots])
524
best_provider = IterListProvider([Blackbox, DeepInfraChat, LambdaChat, PollinationsAI, OIVSCode, TypeGPT, Liaobots])
520
525
)
521
526
522
527
deepseek_r1 = Model(
@@ -645,8 +650,8 @@ minicpm_2_5 = Model(
645
650
)
646
651
647
652
### Ai2 ###
648
tulu_3_405b = Model(
649
name = "tulu-3-405b",
653
olmo_1_7b = Model(
654
name = "olmo-1-7b",
650
655
base_provider = "Ai2",
651
656
best_provider = AllenAI
652
657
)
@@ -657,6 +662,18 @@ olmo_2_13b = Model(
657
662
best_provider = AllenAI
658
663
)
659
664
665
olmo_2_32b = Model(
666
name = "olmo-2-32b",
667
base_provider = "Ai2",
668
best_provider = AllenAI
669
)
670
671
olmo_4_synthetic = VisionModel(
672
name = "olmo-4-synthetic",
673
base_provider = "Ai2",
674
best_provider = AllenAI
675
)
676
660
677
tulu_3_1_8b = Model(
661
678
name = "tulu-3-1-8b",
662
679
base_provider = "Ai2",
@@ -669,12 +686,13 @@ tulu_3_70b = Model(
669
686
best_provider = AllenAI
670
687
)
671
688
672
olmoe_0125 = Model(
673
name = "olmoe-0125",
689
tulu_3_405b = Model(
690
name = "tulu-3-405b",
674
691
base_provider = "Ai2",
675
692
best_provider = AllenAI
676
693
)
677
694
695
### Liquid AI ###
678
696
lfm_40b = Model(
679
697
name = "lfm-40b",
680
698
base_provider = "Liquid AI",
@@ -710,7 +728,7 @@ sd_3_5 = ImageModel(
710
728
flux = ImageModel(
711
729
name = 'flux',
712
730
base_provider = 'Black Forest Labs',
713
best_provider = IterListProvider([Blackbox, PollinationsImage, Websim, HuggingSpace])
731
best_provider = IterListProvider([Blackbox, PollinationsImage, Websim, HuggingSpace, ARTA])
714
732
)
715
733
716
734
flux_pro = ImageModel(
@@ -922,11 +940,13 @@ class ModelUtils:
922
940
minicpm_2_5.name: minicpm_2_5,
923
941
924
942
### Ai2 ###
925
tulu_3_405b.name: tulu_3_405b,
943
olmo_1_7b.name: olmo_1_7b,
926
944
olmo_2_13b.name: olmo_2_13b,
945
olmo_2_32b.name: olmo_2_32b,
946
olmo_4_synthetic.name: olmo_4_synthetic,
927
947
tulu_3_1_8b.name: tulu_3_1_8b,
928
948
tulu_3_70b.name: tulu_3_70b,
929
olmoe_0125.name: olmoe_0125,
949
tulu_3_405b.name: tulu_3_405b,
930
950
931
951
### Liquid AI ###
932
952
lfm_40b.name: lfm_40b,