continue

Bot Image Bot Name Description Status

Generated Table

Bot NameDescriptionProviderStatusCategory
Gemini-1.5-ProMulti-modal model from Google's Gemini family that balances model performance and speed. Accepts text, image, and video input with restriction of one video per message.GoogleOFFICIALText Generation
Llama-3-70b-GroqLlama 3 70b powered by the Groq LPU™ Inference EngineMeta/GroqOFFICIALText Generation
GPT-4.5-PreviewResearch preview of GPT-4.5, designed to be more conversational, empathetic & helpful. Supports 128k token context window.OpenAIOFFICIALText Generation
Claude-3.5-HaikuThe latest generation of Anthropic's fastest model. Has fast speeds and improved instruction following.AnthropicOFFICIALText Generation
o1OpenAI's model designed to reason before responding. Supports 200k tokens of input context and can reason through images.OpenAIOFFICIAL SUBSCRIBER ACCESSReasoning
Mistral-MediumMistral AI's medium-sized model with 32k token context window. Stronger than Mixtral-8x7b on benchmarks.Mistral AIOFFICIALText Generation
o1-proOpenAI's highly capable reasoning model for complex, compute-intensive tasks. Spends more time for accurate answers.OpenAIOFFICIAL SUBSCRIBER ACCESSReasoning
Qwen-QwQ-32bQwQ is the reasoning model of the Qwen series, achieving competitive performance against models like DeepSeek-R1 and o1-mini.AlibabaOFFICIALReasoning
QwQ-32B-TCompact, open-source reasoning model with 32B parameters. Strong performance on math, coding, and problem-solving tasks.QwenOFFICIALReasoning
ChatGPT-4o-LatestDynamic model continuously updated to the current version of GPT-4o in ChatGPT. Supports 128k token context window.OpenAIOFFICIALText Generation
o3-miniOpenAI's recent reasoning model for science, math, and coding. Supports 200k tokens of input/output context.OpenAIOFFICIALReasoning
Llama-4-ScoutVersatile LLM with multi-modal capabilities for tasks like multi-document summarization. Supports 131k tokens context.MetaOFFICIAL NEWText Generation
Llama-4-Maverick-TState-of-art multimodal model. MoE powerhouse for multilingual image/text understanding across 12 languages. 500k token context.MetaOFFICIAL NEWText Generation
o3-mini-highOpenAI's reasoning model with high reasoning effort. Excels at science, math, and coding tasks. 200k token context.OpenAIOFFICIAL SUBSCRIBER ACCESSReasoning
o1-miniSmaller version of OpenAI's o1 model for complex reasoning tasks. Supports 128k tokens of context.OpenAIOFFICIALReasoning
DeepSeek-V3Open-source LLM with state-of-the-art performance in coding, mathematics, and reasoning. 131k context window.TogetherOFFICIALText Generation
Gemini-1.5-FlashGoogle's model optimized for speed-sensitive tasks. Accepts text, image, and video input with one video per message restriction.GoogleOFFICIALText Generation
Llama-3.3-70B-FWMeta's Llama 3.3 70B, hosted by Fireworks AI. Delivers leading performance at fraction of inference cost.Meta/FireworksOFFICIALText Generation
Llama-3.3-70BSimilar performance to Llama 3.1 405B while faster and smaller. Excels in synthetic data generation.MetaOFFICIALText Generation
GPT-4o-miniSmart, cost-effective model from OpenAI. As fast as GPT-3.5 Turbo but significantly smarter.OpenAIOFFICIALText Generation
Llama-3.3-70B-FP16Pretrained and instruction tuned LLM optimized for multilingual dialogue use cases.MetaOFFICIALText Generation
Claude-3.7-Sonnet-ReasoningAnthropic's most intelligent model with reasoning capabilities enabled by default. 200k token context window.AnthropicOFFICIALReasoning
DeepSeek-R1Open-source reasoning LLM rivaling OpenAI's o1. Excels in math, code, and reasoning tasks. 164k token context.Together AIOFFICIALReasoning
DeepSeek-R1-FWState-of-the-art reasoning model for problem solving, math, and coding with chain-of-thought explanations. 164k token context.Fireworks AIOFFICIALReasoning
Web-SearchWeb-enabled assistant that searches the internet for responses. Good for up-to-date information and facts.GPT 4o MiniOFFICIALWeb Search

Comments

Post a Comment