gpt4free

公开

关注 0 Fork 0 Star 1

返回提交历史

XFEstudio/gpt4free

Updated some providers, added new providers and added new models

ec8caec5

kqlio67 <>

提交于 2025-02-03 14:17

父提交 50afc23

代码差异

6 个文件 +352 -92

Modified docs/providers-and-models.md +17 -15

@@ -39,8 +39,9 @@ This document provides an overview of various AI providers and models, including

39 39 |----------|-------------|--------------|---------------|--------|--------|------|------|

40 40

|[aichatfree.info](https://aichatfree.info)|No auth required|`g4f.Provider.AIChatFree`|`gemini-1.5-pro` _**(1+)**_|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|

41 41

|[autonomous.ai](https://www.autonomous.ai/anon/)|No auth required|`g4f.Provider.AutonomousAI`|`llama-3.3-70b, qwen-2.5-coder-32b, hermes-3, llama-3.2-90b, llama-3.3-70b, llama-3-2-70b`|✔|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|

|[blackbox.ai](https://www.blackbox.ai)|No auth required|`g4f.Provider.Blackbox`|`blackboxai, gpt-4, gpt-4o, gemini-1.5-flash, gemini-1.5-pro, claude-3.5-sonnet, blackboxai-pro, llama-3.1-8b, llama-3.1-70b, llama-3-1-405b, llama-3.3-70b, mixtral-7b, deepseek-chat, dbrx-instruct, qwq-32b, hermes-2-dpo, deepseek-r1` _**(+31)**_|`flux`|`blackboxai, gpt-4o, gemini-1.5-pro, gemini-1.5-flash, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b`|✔|![](https://img.shields.io/badge/Active-brightgreen)|

|[cablyai.com](https://cablyai.com)|No auth required|`g4f.Provider.CablyAI`|`cably-80b`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|

|[blackbox.ai](https://www.blackbox.ai)|No auth required|`g4f.Provider.Blackbox`|`blackboxai, gemini-1.5-flash, gemini-1.5-pro, blackboxai-pro, llama-3.1-8b, llama-3.1-70b, llama-3-1-405b, llama-3.3-70b, mixtral-small-28b, deepseek-chat, dbrx-instruct, qwq-32b, hermes-2-dpo, deepseek-r1` _**(+34)**_|`flux`|`blackboxai, gpt-4o, gemini-1.5-pro, gemini-1.5-flash, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b`|✔|![](https://img.shields.io/badge/Active-brightgreen)|

|[api.blackbox.ai](https://api.blackbox.ai)|No auth required|`g4f.Provider.BlackboxAPI`|`deepseek-v3, deepseek-r1, deepseek-chat, mixtral-small-28b, dbrx-instruct, qwq-32b, hermes-2-dpo`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|

|[cablyai.com](https://cablyai.com)|Optional API key|`g4f.Provider.CablyAI`|`gpt-4o-mini, llama-3.1-8b, deepseek-v3, deepseek-r1, o3-mini-low` _**(2+)**_|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|

44 45

|[chatglm.cn](https://chatglm.cn)|No auth required|`g4f.Provider.ChatGLM`|`glm-4`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|

45 46

|[chatgpt.com](https://chatgpt.com)|No auth required|`g4f.Provider.ChatGpt`|✔ _**(+7)**_|❌|❌|✔|![Error](https://img.shields.io/badge/HTTPError-f48d37)|

46 47

|[chatgpt.es](https://chatgpt.es)|No auth required|`g4f.Provider.ChatGptEs`|`gpt-4, gpt-4o, gpt-4o-mini`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|

@@ -126,18 +127,19 @@ This document provides an overview of various AI providers and models, including

126 127 |-------|---------------|-----------|---------|

127 128 |gpt-3|OpenAI|1+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-3-5-turbo)|

129 |gpt-4|OpenAI|11+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4)|

130 |gpt-4|OpenAI|10+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4)|

132 133 |o1|OpenAI|1+ Providers|[openai.com](https://openai.com/index/introducing-openai-o1-preview/)|

@@ -145,10 +147,10 @@ This document provides an overview of various AI providers and models, including

145 147

|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/)|

148 |mixtral-7b|Mistral|1+|[mistral.ai](https://mistral.ai/news/mixtral-of-experts/)|

151

|hermes-2-dpo|NousResearch|1+ Providers|[huggingface.co](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO)|

153

|hermes-2-dpo|NousResearch|2+ Providers|[huggingface.co](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO)|

@@ -161,7 +163,7 @@ This document provides an overview of various AI providers and models, including

@@ -174,18 +176,18 @@ This document provides an overview of various AI providers and models, including

179 181 |pi|Inflection|1+ Providers|[inflection.ai](https://inflection.ai/blog/inflection-2-5)|

183 185 |grok-2|x.ai|1+|[x.ai](https://x.ai/blog/grok-2)|

189 191 |p1|PollinationsAI|1+ Providers|[pollinations.ai](https://pollinations.ai/)|

191 193 |glm-4|THUDM|1+ Providers|[github.com/THUDM](https://github.com/THUDM/GLM-4)|

@@ -193,7 +195,6 @@ This document provides an overview of various AI providers and models, including

193 195 |evil|Evil Mode - Experimental|1+ Providers||

194 196

195 197 ---

196

197 198 ### Image Models

199 200 |-------|---------------|-----------|---------|

@@ -207,6 +208,7 @@ This document provides an overview of various AI providers and models, including

208 209

209 210

211

210 212 ## Conclusion and Usage Tips

211 213

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:**

212 214 1. **Availability**: Check the status of the provider to ensure it's currently active and accessible.

Modified g4f/Provider/Blackbox.py +53 -36

@@ -38,16 +38,17 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):

38 38 default_model = "blackboxai"

39 39 default_vision_model = default_model

40 40 default_image_model = 'ImageGeneration'

41 image_models = [default_image_model, "ImageGeneration2"]

    vision_models = [default_vision_model, 'gpt-4o', 'gemini-pro', 'deepseek-v3', 'gemini-1.5-flash', 'llama-3.1-8b', 'llama-3.1-70b', 'llama-3.1-405b']

43 reasoning_models = ['deepseek-r1']

45 userSelectedModel = ['gpt-4o', 'gemini-pro', 'claude-sonnet-3.5', 'deepseek-r1', 'deepseek-v3', 'blackboxai-pro']

41 image_models = [default_image_model]

    vision_models = [default_vision_model, 'gpt-4o', 'o3-mini', 'gemini-pro', 'DeepSeek-V3', 'gemini-1.5-flash', 'llama-3.1-8b', 'llama-3.1-70b', 'llama-3.1-405b']

43 reasoning_models = ['DeepSeek-R1']

45 userSelectedModel = ['gpt-4o', 'o3-mini', 'claude-sonnet-3.5', 'gemini-pro', 'blackboxai-pro']

46 46

47 47 agentMode = {

48 'ImageGeneration': {'mode': True, 'id': "ImageGenerationLV45LJp", 'name': "Image Generation"},

48 'DeepSeek-V3': {'mode': True, 'id': "deepseek-chat", 'name': "DeepSeek-V3"},

49 'DeepSeek-R1': {'mode': True, 'id': "deepseek-reasoner", 'name': "DeepSeek-R1"},

49 50

        'Meta-Llama-3.3-70B-Instruct-Turbo': {'mode': True, 'id': "meta-llama/Llama-3.3-70B-Instruct-Turbo", 'name': "Meta-Llama-3.3-70B-Instruct-Turbo"},

        'Mistral-(7B)-Instruct-v0.2': {'mode': True, 'id': "mistralai/Mistral-7B-Instruct-v0.2", 'name': "Mistral-(7B)-Instruct-v0.2"},

        'Mistral-Small-24B-Instruct-2501': {'mode': True, 'id': "mistralai/Mistral-Small-24B-Instruct-2501", 'name': "Mistral-Small-24B-Instruct-2501"},

51 52

        'DeepSeek-LLM-Chat-(67B)': {'mode': True, 'id': "deepseek-ai/deepseek-llm-67b-chat", 'name': "DeepSeek-LLM-Chat-(67B)"},

52 53 'DBRX-Instruct': {'mode': True, 'id': "databricks/dbrx-instruct", 'name': "DBRX-Instruct"},

53 54 'Qwen-QwQ-32B-Preview': {'mode': True, 'id': "Qwen/QwQ-32B-Preview", 'name': "Qwen-QwQ-32B-Preview"},

@@ -96,12 +97,12 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):

96 97

    models = list(dict.fromkeys([default_model, *userSelectedModel, *reasoning_models, *image_models, *list(agentMode.keys()), *list(trendingAgentMode.keys())]))

97 98

98 99 model_aliases = {

99 "gpt-4": "gpt-4o",

100 100 "gemini-1.5-flash": "gemini-1.5-flash",

101 101 "gemini-1.5-pro": "gemini-pro",

102 "claude-3.5-sonnet": "claude-sonnet-3.5",

102 "deepseek-v3": "DeepSeek-V3",

103 "deepseek-r1": "DeepSeek-R1",

103 104 "llama-3.3-70b": "Meta-Llama-3.3-70B-Instruct-Turbo",

104 "mixtral-7b": "Mistral-(7B)-Instruct-v0.2",

105 "mixtral-small-28b": "Mistral-Small-24B-Instruct-2501",

105 106 "deepseek-chat": "DeepSeek-LLM-Chat-(67B)",

106 107 "dbrx-instruct": "DBRX-Instruct",

107 108 "qwq-32b": "Qwen-QwQ-32B-Preview",

@@ -196,7 +197,7 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):

196 197 }

197 198

198 199 async with ClientSession(headers=headers) as session:

199 if model == "ImageGeneration2":

200 if model in "ImageGeneration":

200 201 prompt = format_image_prompt(messages, prompt)

201 202 data = {

202 203 "query": format_image_prompt(messages, prompt),

@@ -294,32 +295,48 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):

294 295 if not text_to_yield or text_to_yield.isspace():

295 296 return

296 297

297 if model in cls.image_models:

298 image_url_match = re.search(r'!\[.*?\]$(.*?)$', text_to_yield)

299 if image_url_match:

300 image_url = image_url_match.group(1)

301 prompt = format_image_prompt(messages, prompt)

302 yield ImageResponse(images=[image_url], alt=prompt)

303 else:

304 if "Generated by BLACKBOX.AI" in text_to_yield:

305 conversation.validated_value = await cls.fetch_validated(force_refresh=True)

306 if conversation.validated_value:

307 data["validated"] = conversation.validated_value

308 async with session.post(cls.api_endpoint, json=data, proxy=proxy) as new_response:

309 await raise_for_status(new_response)

310 new_response_text = await new_response.text()

311 new_parts = new_response_text.split('$~~~$')

312 new_text = new_parts[2] if len(new_parts) >= 3 else new_response_text

313

314 if new_text and not new_text.isspace():

315 yield new_text

316 else:

317 if text_to_yield and not text_to_yield.isspace():

318 yield text_to_yield

298 if model in cls.reasoning_models and "\n\n\n" in text_to_yield:

299 think_split = text_to_yield.split("\n\n\n", 1)

300 if len(think_split) > 1:

301 think_content, answer = think_split[0].strip(), think_split[1].strip()

302 yield Reasoning(status=think_content)

303 yield answer

304 else:

305 yield text_to_yield

306 elif "<think>" in text_to_yield:

307 pre_think, rest = text_to_yield.split('<think>', 1)

308 think_content, post_think = rest.split('</think>', 1)

309

310 pre_think = pre_think.strip()

311 think_content = think_content.strip()

312 post_think = post_think.strip()

313

314 if pre_think:

315 yield pre_think

316 if think_content:

317 yield Reasoning(status=think_content)

318 if post_think:

319 yield post_think

320

321 elif "Generated by BLACKBOX.AI" in text_to_yield:

322 conversation.validated_value = await cls.fetch_validated(force_refresh=True)

323 if conversation.validated_value:

324 data["validated"] = conversation.validated_value

325 async with session.post(cls.api_endpoint, json=data, proxy=proxy) as new_response:

326 await raise_for_status(new_response)

327 new_response_text = await new_response.text()

328 new_parts = new_response_text.split('$~~~$')

329 new_text = new_parts[2] if len(new_parts) >= 3 else new_response_text

330

331 if new_text and not new_text.isspace():

332 yield new_text

319 333 else:

320 334 if text_to_yield and not text_to_yield.isspace():

321 335 yield text_to_yield

336 else:

337 if text_to_yield and not text_to_yield.isspace():

338 yield text_to_yield

322 339

323 if return_conversation:

324 conversation.message_history.append({"role": "assistant", "content": text_to_yield})

325 yield conversation

340 if return_conversation:

341 conversation.message_history.append({"role": "assistant", "content": text_to_yield})

342 yield conversation

Added g4f/Provider/BlackboxAPI.py +103 -0

@@ -0,0 +1,103 @@

1 from __future__ import annotations

2 import json

3 from aiohttp import ClientSession

5 from ..typing import AsyncResult, Messages

6 from .base_provider import AsyncGeneratorProvider, ProviderModelMixin

7 from ..requests.raise_for_status import raise_for_status

8 from ..providers.response import Reasoning

9 from .helper import format_prompt

11 class BlackboxAPI(AsyncGeneratorProvider, ProviderModelMixin):

12 label = "Blackbox AI API"

13 url = "https://api.blackbox.ai"

14 api_endpoint = "https://api.blackbox.ai/api/chat"

16 working = True

17 needs_auth = False

18 supports_stream = False

19 supports_system_message = True

20 supports_message_history = True

22 default_model = 'deepseek-ai/DeepSeek-V3'

23 reasoning_models = ['deepseek-ai/DeepSeek-R1']

24 models = [

25 default_model,

26 'mistralai/Mistral-Small-24B-Instruct-2501',

27 'deepseek-ai/deepseek-llm-67b-chat',

28 'databricks/dbrx-instruct',

29 'Qwen/QwQ-32B-Preview',

30 'NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO'

31 ] + reasoning_models

33 model_aliases = {

34 "deepseek-v3": "deepseek-ai/DeepSeek-V3",

35 "deepseek-r1": "deepseek-ai/DeepSeek-R1",

36 "deepseek-chat": "deepseek-ai/deepseek-llm-67b-chat",

37 "mixtral-small-28b": "mistralai/Mistral-Small-24B-Instruct-2501",

38 "dbrx-instruct": "databricks/dbrx-instruct",

39 "qwq-32b": "Qwen/QwQ-32B-Preview",

40 "hermes-2-dpo": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",

41 }

43 @classmethod

44 async def create_async_generator(

45 cls,

46 model: str,

47 messages: Messages,

48 proxy: str = None,

49 max_tokens: str = None,

50 **kwargs

51 ) -> AsyncResult:

52 model = cls.get_model(model)

54 headers = {

55 "Content-Type": "application/json",

56 }

58 async with ClientSession(headers=headers) as session:

59 data = {

60 "messages": messages,

61 "model": model,

62 "max_tokens": max_tokens

63 }

65 async with session.post(cls.api_endpoint, json=data, proxy=proxy) as response:

66 await raise_for_status(response)

68 is_reasoning = False

69 current_reasoning = ""

71 async for chunk in response.content:

72 if not chunk:

73 continue

75 text = chunk.decode(errors='ignore')

77 if model in cls.reasoning_models:

78 if "<think>" in text:

79 text = text.replace("<think>", "")

80 is_reasoning = True

81 current_reasoning = text

82 continue

84 if "</think>" in text:

85 text = text.replace("</think>", "")

86 is_reasoning = False

87 current_reasoning += text

88 yield Reasoning(status=current_reasoning.strip())

89 current_reasoning = ""

90 continue

92 if is_reasoning:

93 current_reasoning += text

94 continue

96 try:

97 if text:

98 yield text

99 except Exception as e:

100 return

101

102 if is_reasoning and current_reasoning:

103 yield Reasoning(status=current_reasoning.strip())

Modified g4f/Provider/CablyAI.py +152 -23

@@ -1,37 +1,166 @@

1 1 from __future__ import annotations

2 2

3 import json

4 from typing import AsyncGenerator

5 from aiohttp import ClientSession

3 7 from ..typing import AsyncResult, Messages

4 from .template import OpenaiTemplate

8 from .base_provider import AsyncGeneratorProvider, ProviderModelMixin

9 from ..requests.raise_for_status import raise_for_status

10 from ..providers.response import FinishReason, Reasoning

5 12

6 class CablyAI(OpenaiTemplate):

13 class CablyAI(AsyncGeneratorProvider, ProviderModelMixin):

14 label = "CablyAI"

7 15 url = "https://cablyai.com"

8 login_url = None

9 needs_auth = False

10 api_base = "https://cablyai.com/v1"

16 api_endpoint = "https://cablyai.com/v1/chat/completions"

17 api_key = "sk-your-openai-api-key"

11 19 working = True

13 default_model = "Cably-80B"

14 models = [default_model]

15 model_aliases = {"cably-80b": default_model}

20 needs_auth = False

21 supports_stream = True

22 supports_system_message = True

23 supports_message_history = True

25 default_model = 'gpt-4o-mini'

26 reasoning_models = ['deepseek-r1-uncensored']

27 models = [

28 default_model,

29 'searchgpt',

30 'llama-3.1-8b-instruct',

31 'deepseek-v3',

32 'tinyswallow1.5b',

33 'andy-3.5',

34 'o3-mini-low',

35 ] + reasoning_models

37 model_aliases = {

38 "gpt-4o-mini": "searchgpt",

39 "llama-3.1-8b": "llama-3.1-8b-instruct",

40 "deepseek-r1": "deepseek-r1-uncensored",

41 }

16 42

17 43 @classmethod

18 def create_async_generator(

44 async def create_async_generator(

19 45 cls,

20 46 model: str,

21 47 messages: Messages,

48 api_key: str = None,

49 stream: bool = True,

50 proxy: str = None,

22 51 **kwargs

23 ) -> AsyncResult:

52 ) -> AsyncResult:

53 model = cls.get_model(model)

54 api_key = api_key or cls.api_key

24 56 headers = {

25 'Accept': '*/*',

26 'Accept-Language': 'en-US,en;q=0.9',

27 'Content-Type': 'application/json',

28 'Origin': 'https://cablyai.com',

29 'Referer': 'https://cablyai.com/chat',

            'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36'

57 "Accept": "*/*",

58 "Accept-Language": "en-US,en;q=0.9",

59 "Authorization": f"Bearer {api_key}",

60 "Content-Type": "application/json",

61 "Origin": cls.url,

62 "Referer": f"{cls.url}/chat",

            "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"

31 64 }

32 return super().create_async_generator(

33 model=model,

34 messages=messages,

35 headers=headers,

36 **kwargs

37 )

66 async with ClientSession(headers=headers) as session:

67 data = {

68 "model": model,

69 "messages": messages,

70 "stream": stream

71 }

73 async with session.post(

74 cls.api_endpoint,

75 json=data,

76 proxy=proxy

77 ) as response:

78 await raise_for_status(response)

80 if stream:

81 reasoning_buffer = []

82 in_reasoning = False

84 async for line in response.content:

85 if not line:

86 continue

88 line = line.decode('utf-8').strip()

89 print(line)

91 if not line.startswith("data: "):

92 continue

94 if line == "data: [DONE]":

95 if in_reasoning and reasoning_buffer:

96 yield Reasoning(status="".join(reasoning_buffer).strip())

97 yield FinishReason("stop")

98 return

100 try:

101 json_data = json.loads(line[6:])

102 delta = json_data["choices"][0].get("delta", {})

103 content = delta.get("content", "")

104 finish_reason = json_data["choices"][0].get("finish_reason")

105

106 if finish_reason:

107 if in_reasoning and reasoning_buffer:

108 yield Reasoning(status="".join(reasoning_buffer).strip())

109 yield FinishReason(finish_reason)

110 return

111

112 if model in cls.reasoning_models:

113 # Processing the beginning of a tag

114 if "<think>" in content:

115 pre, _, post = content.partition("<think>")

116 if pre:

117 yield pre

118 in_reasoning = True

119 content = post

120

121 # Tag end processing

122 if "</think>" in content:

123 in_reasoning = False

124 thought, _, post = content.partition("</think>")

125 if thought:

126 reasoning_buffer.append(thought)

127 if reasoning_buffer:

128 yield Reasoning(status="".join(reasoning_buffer).strip())

129 reasoning_buffer.clear()

130 if post:

131 yield post

132 continue

133

134 # Buffering content inside tags

135 if in_reasoning:

136 reasoning_buffer.append(content)

137 else:

138 if content:

139 yield content

140 else:

141 if content:

142 yield content

143

144 except json.JSONDecodeError:

145 continue

146 except Exception:

147 yield FinishReason("error")

148 return

149 else:

150 try:

151 response_data = await response.json()

152 message = response_data["choices"][0]["message"]

153 content = message["content"]

154

155 if model in cls.reasoning_models and "<think>" in content:

156 think_start = content.find("<think>") + 7

157 think_end = content.find("</think>")

158 if think_start > 6 and think_end > 0:

159 reasoning = content[think_start:think_end].strip()

160 yield Reasoning(status=reasoning)

161 content = content[think_end + 8:].strip()

162

163 yield content

164 yield FinishReason("stop")

165 except Exception:

166 yield FinishReason("error")

Modified g4f/Provider/__init__.py +1 -0

@@ -15,6 +15,7 @@ from .mini_max import HailuoAI, MiniMax

15 15 from .template import OpenaiTemplate, BackendApi

16 16

17 17 from .Blackbox import Blackbox

18 from .BlackboxAPI import BlackboxAPI

18 19 from .CablyAI import CablyAI

19 20 from .ChatGLM import ChatGLM

20 21 from .ChatGpt import ChatGpt

Modified g4f/models.py +26 -18

@@ -6,6 +6,7 @@ from .Provider import IterListProvider, ProviderType

6 6 from .Provider import (

7 7 ### no auth required ###

8 8 Blackbox,

9 BlackboxAPI,

9 10 CablyAI,

10 11 ChatGLM,

11 12 ChatGptEs,

@@ -123,20 +124,20 @@ gpt_35_turbo = Model(

123 124 gpt_4 = Model(

124 125 name = 'gpt-4',

125 126 base_provider = 'OpenAI',

126

    best_provider = IterListProvider([DDG, Blackbox, Jmuz, ChatGptEs, ChatGptt, PollinationsAI, Yqcloud, Copilot, OpenaiChat, Liaobots, Mhystical])

127

    best_provider = IterListProvider([DDG, Jmuz, ChatGptEs, ChatGptt, PollinationsAI, Yqcloud, Copilot, OpenaiChat, Liaobots, Mhystical])

127 128 )

128 129

129 130 # gpt-4o

130 131 gpt_4o = VisionModel(

131 132 name = 'gpt-4o',

132 133 base_provider = 'OpenAI',

133

    best_provider = IterListProvider([Blackbox, ChatGptt, Jmuz, ChatGptEs, PollinationsAI, DarkAI, Copilot, Liaobots, OpenaiChat])

134 best_provider = IterListProvider([ChatGptt, Jmuz, ChatGptEs, PollinationsAI, DarkAI, Copilot, Liaobots, OpenaiChat])

134 135 )

135 136

136 137 gpt_4o_mini = Model(

137 138 name = 'gpt-4o-mini',

138 139 base_provider = 'OpenAI',

139 best_provider = IterListProvider([DDG, ChatGptEs, ChatGptt, Jmuz, PollinationsAI, OIVSCode, Liaobots, OpenaiChat])

140

    best_provider = IterListProvider([DDG, ChatGptEs, ChatGptt, Jmuz, PollinationsAI, OIVSCode, CablyAI, Liaobots, OpenaiChat])

140 141 )

141 142

142 143 # o1

@@ -158,6 +159,13 @@ o1_mini = Model(

158 159 best_provider = Liaobots

159 160 )

160 161

162 # o3

163 o3_mini_low = Model(

164 name = 'o3-mini-low',

165 base_provider = 'OpenAI',

166 best_provider = CablyAI

167 )

168

161 169 ### GigaChat ###

162 170 gigachat = Model(

163 171 name = 'GigaChat:latest',

@@ -195,7 +203,7 @@ llama_3_70b = Model(

195 203 llama_3_1_8b = Model(

196 204 name = "llama-3.1-8b",

197 205 base_provider = "Meta Llama",

198 best_provider = IterListProvider([Blackbox, DeepInfraChat, Glider, Jmuz, PollinationsAI, Cloudflare])

206 best_provider = IterListProvider([Blackbox, DeepInfraChat, Glider, Jmuz, PollinationsAI, CablyAI, Cloudflare])

199 207 )

200 208

201 209 llama_3_1_70b = Model(

@@ -243,12 +251,6 @@ llama_3_3_70b = Model(

243 251 )

244 252

245 253 ### Mistral ###

246 mixtral_7b = Model(

247 name = "mixtral-7b",

248 base_provider = "Mistral",

249 best_provider = Blackbox

250 )

251

252 254 mixtral_8x7b = Model(

253 255 name = "mixtral-8x7b",

254 256 base_provider = "Mistral",

@@ -261,11 +263,17 @@ mistral_nemo = Model(

261 263 best_provider = IterListProvider([PollinationsAI, HuggingChat, HuggingFace])

262 264 )

263 265

266 mixtral_small_28b = Model(

267 name = "mixtral-small-28b",

268 base_provider = "Mistral",

269 best_provider = IterListProvider([Blackbox, BlackboxAPI])

270 )

271

264 272 ### NousResearch ###

265 273 hermes_2_dpo = Model(

266 274 name = "hermes-2-dpo",

267 275 base_provider = "NousResearch",

268 best_provider = Blackbox

276 best_provider = IterListProvider([Blackbox, BlackboxAPI])

269 277 )

270 278

271 279

@@ -356,7 +364,7 @@ claude_3_opus = Model(

356 364 claude_3_5_sonnet = Model(

357 365 name = 'claude-3.5-sonnet',

358 366 base_provider = 'Anthropic',

359 best_provider = IterListProvider([Blackbox, Jmuz, Liaobots])

367 best_provider = IterListProvider([Jmuz, Liaobots])

360 368 )

361 369

362 370 ### Reka AI ###

@@ -434,7 +442,7 @@ qwen_2_5_1m = Model(

434 442 qwq_32b = Model(

435 443 name = 'qwq-32b',

436 444 base_provider = 'Qwen',

437 best_provider = IterListProvider([Blackbox, DeepInfraChat, Jmuz, HuggingChat])

445 best_provider = IterListProvider([Blackbox, BlackboxAPI, DeepInfraChat, Jmuz, HuggingChat])

438 446 )

439 447 qvq_72b = VisionModel(

440 448 name = 'qvq-72b',

@@ -453,19 +461,19 @@ pi = Model(

453 461 deepseek_chat = Model(

454 462 name = 'deepseek-chat',

455 463 base_provider = 'DeepSeek',

456 best_provider = IterListProvider([Blackbox, Jmuz, PollinationsAI])

464 best_provider = IterListProvider([Blackbox, BlackboxAPI, Jmuz, PollinationsAI])

457 465 )

458 466

459 467 deepseek_v3 = Model(

460 468 name = 'deepseek-v3',

461 469 base_provider = 'DeepSeek',

462 best_provider = IterListProvider([Blackbox, DeepInfraChat])

470 best_provider = IterListProvider([Blackbox, BlackboxAPI, DeepInfraChat, CablyAI])

463 471 )

464 472

465 473 deepseek_r1 = Model(

466 474 name = 'deepseek-r1',

467 475 base_provider = 'DeepSeek',

468 best_provider = IterListProvider([Blackbox, Glider, PollinationsAI, Jmuz, HuggingChat, HuggingFace])

476

    best_provider = IterListProvider([Blackbox, BlackboxAPI, Glider, PollinationsAI, Jmuz, CablyAI, HuggingChat, HuggingFace])

469 477 )

470 478

471 479 ### x.ai ###

@@ -505,7 +513,7 @@ nemotron_70b = Model(

505 513 dbrx_instruct = Model(

506 514 name = 'dbrx-instruct',

507 515 base_provider = 'Databricks',

508 best_provider = Blackbox

516 best_provider = IterListProvider([Blackbox, BlackboxAPI])

509 517 )

510 518

511 519 ### PollinationsAI ###

@@ -657,9 +665,9 @@ class ModelUtils:

657 665 llama_3_3_70b.name: llama_3_3_70b,

658 666

659 667 ### Mistral ###

660 mixtral_7b.name: mixtral_7b,

661 668 mixtral_8x7b.name: mixtral_8x7b,

662 669 mistral_nemo.name: mistral_nemo,

670 mixtral_small_28b.name: mixtral_small_28b,

663 671

664 672 ### NousResearch ###

665 673 hermes_2_dpo.name: hermes_2_dpo,