You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
929 lines
67 KiB
JSON
929 lines
67 KiB
JSON
{
|
|
"01-ai/Yi-1.5-34B-Chat-16K": {
|
|
"description": "Yi-1.5 34B delivers superior performance in industry applications with a wealth of training samples."
|
|
},
|
|
"01-ai/Yi-1.5-9B-Chat-16K": {
|
|
"description": "Yi-1.5 9B supports 16K tokens, providing efficient and smooth language generation capabilities."
|
|
},
|
|
"360gpt-pro": {
|
|
"description": "360GPT Pro, as an important member of the 360 AI model series, meets diverse natural language application scenarios with efficient text processing capabilities, supporting long text understanding and multi-turn dialogue."
|
|
},
|
|
"360gpt-turbo": {
|
|
"description": "360GPT Turbo offers powerful computation and dialogue capabilities, with excellent semantic understanding and generation efficiency, making it an ideal intelligent assistant solution for enterprises and developers."
|
|
},
|
|
"360gpt-turbo-responsibility-8k": {
|
|
"description": "360GPT Turbo Responsibility 8K emphasizes semantic safety and responsibility, designed specifically for applications with high content safety requirements, ensuring accuracy and robustness in user experience."
|
|
},
|
|
"360gpt2-pro": {
|
|
"description": "360GPT2 Pro is an advanced natural language processing model launched by 360, featuring exceptional text generation and understanding capabilities, particularly excelling in generation and creative tasks, capable of handling complex language transformations and role-playing tasks."
|
|
},
|
|
"4.0Ultra": {
|
|
"description": "Spark4.0 Ultra is the most powerful version in the Spark large model series, enhancing text content understanding and summarization capabilities while upgrading online search links. It is a comprehensive solution for improving office productivity and accurately responding to demands, leading the industry as an intelligent product."
|
|
},
|
|
"Baichuan2-Turbo": {
|
|
"description": "Utilizes search enhancement technology to achieve comprehensive links between large models and domain knowledge, as well as knowledge from the entire web. Supports uploads of various documents such as PDF and Word, and URL input, providing timely and comprehensive information retrieval with accurate and professional output."
|
|
},
|
|
"Baichuan3-Turbo": {
|
|
"description": "Optimized for high-frequency enterprise scenarios, significantly improving performance and cost-effectiveness. Compared to the Baichuan2 model, content creation improves by 20%, knowledge Q&A by 17%, and role-playing ability by 40%. Overall performance is superior to GPT-3.5."
|
|
},
|
|
"Baichuan3-Turbo-128k": {
|
|
"description": "Features a 128K ultra-long context window, optimized for high-frequency enterprise scenarios, significantly improving performance and cost-effectiveness. Compared to the Baichuan2 model, content creation improves by 20%, knowledge Q&A by 17%, and role-playing ability by 40%. Overall performance is superior to GPT-3.5."
|
|
},
|
|
"Baichuan4": {
|
|
"description": "The model is the best in the country, surpassing mainstream foreign models in Chinese tasks such as knowledge encyclopedias, long texts, and creative generation. It also boasts industry-leading multimodal capabilities, excelling in multiple authoritative evaluation benchmarks."
|
|
},
|
|
"Gryphe/MythoMax-L2-13b": {
|
|
"description": "MythoMax-L2 (13B) is an innovative model suitable for multi-domain applications and complex tasks."
|
|
},
|
|
"Max-32k": {
|
|
"description": "Spark Max 32K is equipped with enhanced context processing capabilities, stronger context understanding, and logical reasoning abilities, supporting text input of up to 32K tokens, suitable for scenarios such as long document reading and private knowledge Q&A."
|
|
},
|
|
"Nous-Hermes-2-Mixtral-8x7B-DPO": {
|
|
"description": "Hermes 2 Mixtral 8x7B DPO is a highly flexible multi-model fusion designed to provide an exceptional creative experience."
|
|
},
|
|
"NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
|
|
"description": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) is a high-precision instruction model suitable for complex computations."
|
|
},
|
|
"NousResearch/Nous-Hermes-2-Yi-34B": {
|
|
"description": "Nous Hermes-2 Yi (34B) provides optimized language output and diverse application possibilities."
|
|
},
|
|
"Phi-3-5-mini-instruct": {
|
|
"description": "An update of the Phi-3-mini model."
|
|
},
|
|
"Phi-3-medium-128k-instruct": {
|
|
"description": "The same Phi-3-medium model, but with a larger context size for RAG or few-shot prompting."
|
|
},
|
|
"Phi-3-medium-4k-instruct": {
|
|
"description": "A 14B parameter model that provides better quality than Phi-3-mini, focusing on high-quality, reasoning-dense data."
|
|
},
|
|
"Phi-3-mini-128k-instruct": {
|
|
"description": "The same Phi-3-mini model, but with a larger context size for RAG or few-shot prompting."
|
|
},
|
|
"Phi-3-mini-4k-instruct": {
|
|
"description": "The smallest member of the Phi-3 family, optimized for both quality and low latency."
|
|
},
|
|
"Phi-3-small-128k-instruct": {
|
|
"description": "The same Phi-3-small model, but with a larger context size for RAG or few-shot prompting."
|
|
},
|
|
"Phi-3-small-8k-instruct": {
|
|
"description": "A 7B parameter model that provides better quality than Phi-3-mini, focusing on high-quality, reasoning-dense data."
|
|
},
|
|
"Pro-128k": {
|
|
"description": "Spark Pro-128K is configured with ultra-large context processing capabilities, able to handle up to 128K of contextual information, particularly suitable for long texts requiring comprehensive analysis and long-term logical connections, providing smooth and consistent logic and diverse citation support in complex text communication."
|
|
},
|
|
"Qwen/Qwen1.5-110B-Chat": {
|
|
"description": "As a beta version of Qwen2, Qwen1.5 utilizes large-scale data to achieve more precise conversational capabilities."
|
|
},
|
|
"Qwen/Qwen1.5-72B-Chat": {
|
|
"description": "Qwen 1.5 Chat (72B) provides quick responses and natural conversational abilities, suitable for multilingual environments."
|
|
},
|
|
"Qwen/Qwen2-72B-Instruct": {
|
|
"description": "Qwen2 is an advanced general-purpose language model that supports various types of instructions."
|
|
},
|
|
"Qwen/Qwen2.5-14B-Instruct": {
|
|
"description": "Qwen2.5 is a brand new series of large language models designed to optimize the handling of instruction-based tasks."
|
|
},
|
|
"Qwen/Qwen2.5-32B-Instruct": {
|
|
"description": "Qwen2.5 is a brand new series of large language models designed to optimize the handling of instruction-based tasks."
|
|
},
|
|
"Qwen/Qwen2.5-72B-Instruct": {
|
|
"description": "Qwen2.5 is a brand new series of large language models with enhanced understanding and generation capabilities."
|
|
},
|
|
"Qwen/Qwen2.5-7B-Instruct": {
|
|
"description": "Qwen2.5 is a brand new series of large language models designed to optimize the handling of instruction-based tasks."
|
|
},
|
|
"Qwen/Qwen2.5-Coder-7B-Instruct": {
|
|
"description": "Qwen2.5-Coder focuses on code writing."
|
|
},
|
|
"Qwen/Qwen2.5-Math-72B-Instruct": {
|
|
"description": "Qwen2.5-Math focuses on problem-solving in the field of mathematics, providing expert solutions for challenging problems."
|
|
},
|
|
"THUDM/glm-4-9b-chat": {
|
|
"description": "GLM-4 9B is an open-source version that provides an optimized conversational experience for chat applications."
|
|
},
|
|
"abab5.5-chat": {
|
|
"description": "Targeted at productivity scenarios, supporting complex task processing and efficient text generation, suitable for professional applications."
|
|
},
|
|
"abab5.5s-chat": {
|
|
"description": "Designed for Chinese persona dialogue scenarios, providing high-quality Chinese dialogue generation capabilities, suitable for various application contexts."
|
|
},
|
|
"abab6.5g-chat": {
|
|
"description": "Designed for multilingual persona dialogue, supporting high-quality dialogue generation in English and other languages."
|
|
},
|
|
"abab6.5s-chat": {
|
|
"description": "Suitable for a wide range of natural language processing tasks, including text generation and dialogue systems."
|
|
},
|
|
"abab6.5t-chat": {
|
|
"description": "Optimized for Chinese persona dialogue scenarios, providing smooth dialogue generation that aligns with Chinese expression habits."
|
|
},
|
|
"accounts/fireworks/models/firefunction-v1": {
|
|
"description": "Fireworks open-source function-calling model provides excellent instruction execution capabilities and customizable features."
|
|
},
|
|
"accounts/fireworks/models/firefunction-v2": {
|
|
"description": "Fireworks' latest Firefunction-v2 is a high-performance function-calling model developed based on Llama-3, optimized for function calls, dialogues, and instruction following."
|
|
},
|
|
"accounts/fireworks/models/firellava-13b": {
|
|
"description": "fireworks-ai/FireLLaVA-13b is a visual language model that can accept both image and text inputs, trained on high-quality data, suitable for multimodal tasks."
|
|
},
|
|
"accounts/fireworks/models/gemma2-9b-it": {
|
|
"description": "Gemma 2 9B instruction model, based on previous Google technology, suitable for answering questions, summarizing, and reasoning across various text generation tasks."
|
|
},
|
|
"accounts/fireworks/models/llama-v3-70b-instruct": {
|
|
"description": "Llama 3 70B instruction model, optimized for multilingual dialogues and natural language understanding, outperforming most competitive models."
|
|
},
|
|
"accounts/fireworks/models/llama-v3-70b-instruct-hf": {
|
|
"description": "Llama 3 70B instruction model (HF version), aligned with official implementation results, suitable for high-quality instruction following tasks."
|
|
},
|
|
"accounts/fireworks/models/llama-v3-8b-instruct": {
|
|
"description": "Llama 3 8B instruction model, optimized for dialogues and multilingual tasks, delivering outstanding and efficient performance."
|
|
},
|
|
"accounts/fireworks/models/llama-v3-8b-instruct-hf": {
|
|
"description": "Llama 3 8B instruction model (HF version), consistent with official implementation results, featuring high consistency and cross-platform compatibility."
|
|
},
|
|
"accounts/fireworks/models/llama-v3p1-405b-instruct": {
|
|
"description": "Llama 3.1 405B instruction model, equipped with massive parameters, suitable for complex tasks and instruction following in high-load scenarios."
|
|
},
|
|
"accounts/fireworks/models/llama-v3p1-70b-instruct": {
|
|
"description": "Llama 3.1 70B instruction model provides exceptional natural language understanding and generation capabilities, making it an ideal choice for dialogue and analysis tasks."
|
|
},
|
|
"accounts/fireworks/models/llama-v3p1-8b-instruct": {
|
|
"description": "Llama 3.1 8B instruction model, optimized for multilingual dialogues, capable of surpassing most open-source and closed-source models on common industry benchmarks."
|
|
},
|
|
"accounts/fireworks/models/mixtral-8x22b-instruct": {
|
|
"description": "Mixtral MoE 8x22B instruction model, featuring large-scale parameters and a multi-expert architecture, fully supporting efficient processing of complex tasks."
|
|
},
|
|
"accounts/fireworks/models/mixtral-8x7b-instruct": {
|
|
"description": "Mixtral MoE 8x7B instruction model, with a multi-expert architecture providing efficient instruction following and execution."
|
|
},
|
|
"accounts/fireworks/models/mixtral-8x7b-instruct-hf": {
|
|
"description": "Mixtral MoE 8x7B instruction model (HF version), performance consistent with official implementation, suitable for various efficient task scenarios."
|
|
},
|
|
"accounts/fireworks/models/mythomax-l2-13b": {
|
|
"description": "MythoMax L2 13B model, combining novel merging techniques, excels in narrative and role-playing."
|
|
},
|
|
"accounts/fireworks/models/phi-3-vision-128k-instruct": {
|
|
"description": "Phi 3 Vision instruction model, a lightweight multimodal model capable of handling complex visual and textual information, with strong reasoning abilities."
|
|
},
|
|
"accounts/fireworks/models/starcoder-16b": {
|
|
"description": "StarCoder 15.5B model supports advanced programming tasks, enhanced multilingual capabilities, suitable for complex code generation and understanding."
|
|
},
|
|
"accounts/fireworks/models/starcoder-7b": {
|
|
"description": "StarCoder 7B model, trained on over 80 programming languages, boasts excellent code completion capabilities and contextual understanding."
|
|
},
|
|
"accounts/yi-01-ai/models/yi-large": {
|
|
"description": "Yi-Large model, featuring exceptional multilingual processing capabilities, suitable for various language generation and understanding tasks."
|
|
},
|
|
"ai21-jamba-1.5-large": {
|
|
"description": "A 398B parameter (94B active) multilingual model, offering a 256K long context window, function calling, structured output, and grounded generation."
|
|
},
|
|
"ai21-jamba-1.5-mini": {
|
|
"description": "A 52B parameter (12B active) multilingual model, offering a 256K long context window, function calling, structured output, and grounded generation."
|
|
},
|
|
"ai21-jamba-instruct": {
|
|
"description": "A production-grade Mamba-based LLM model designed to achieve best-in-class performance, quality, and cost efficiency."
|
|
},
|
|
"anthropic.claude-3-5-sonnet-20240620-v1:0": {
|
|
"description": "Claude 3.5 Sonnet raises the industry standard, outperforming competitor models and Claude 3 Opus, excelling in a wide range of evaluations while maintaining the speed and cost of our mid-tier models."
|
|
},
|
|
"anthropic.claude-3-haiku-20240307-v1:0": {
|
|
"description": "Claude 3 Haiku is Anthropic's fastest and most compact model, providing near-instantaneous response times. It can quickly answer simple queries and requests. Customers will be able to build seamless AI experiences that mimic human interaction. Claude 3 Haiku can process images and return text output, with a context window of 200K."
|
|
},
|
|
"anthropic.claude-3-opus-20240229-v1:0": {
|
|
"description": "Claude 3 Opus is Anthropic's most powerful AI model, featuring state-of-the-art performance on highly complex tasks. It can handle open-ended prompts and unseen scenarios, demonstrating exceptional fluency and human-like understanding. Claude 3 Opus showcases the forefront of generative AI possibilities. Claude 3 Opus can process images and return text output, with a context window of 200K."
|
|
},
|
|
"anthropic.claude-3-sonnet-20240229-v1:0": {
|
|
"description": "Anthropic's Claude 3 Sonnet strikes an ideal balance between intelligence and speed—especially suited for enterprise workloads. It offers maximum utility at a price lower than competitors and is designed to be a reliable, durable workhorse for scalable AI deployments. Claude 3 Sonnet can process images and return text output, with a context window of 200K."
|
|
},
|
|
"anthropic.claude-instant-v1": {
|
|
"description": "A fast, economical, yet still highly capable model that can handle a range of tasks, including everyday conversations, text analysis, summarization, and document Q&A."
|
|
},
|
|
"anthropic.claude-v2": {
|
|
"description": "Anthropic's model demonstrates high capability across a wide range of tasks, from complex conversations and creative content generation to detailed instruction following."
|
|
},
|
|
"anthropic.claude-v2:1": {
|
|
"description": "An updated version of Claude 2, featuring double the context window and improvements in reliability, hallucination rates, and evidence-based accuracy in long documents and RAG contexts."
|
|
},
|
|
"anthropic/claude-3-haiku": {
|
|
"description": "Claude 3 Haiku is Anthropic's fastest and most compact model, designed for near-instantaneous responses. It features quick and accurate directional performance."
|
|
},
|
|
"anthropic/claude-3-opus": {
|
|
"description": "Claude 3 Opus is Anthropic's most powerful model for handling highly complex tasks. It excels in performance, intelligence, fluency, and comprehension."
|
|
},
|
|
"anthropic/claude-3.5-sonnet": {
|
|
"description": "Claude 3.5 Sonnet offers capabilities that surpass Opus and faster speeds than Sonnet, while maintaining the same pricing as Sonnet. Sonnet excels particularly in programming, data science, visual processing, and agent tasks."
|
|
},
|
|
"aya": {
|
|
"description": "Aya 23 is a multilingual model launched by Cohere, supporting 23 languages, facilitating diverse language applications."
|
|
},
|
|
"aya:35b": {
|
|
"description": "Aya 23 is a multilingual model launched by Cohere, supporting 23 languages, facilitating diverse language applications."
|
|
},
|
|
"charglm-3": {
|
|
"description": "CharGLM-3 is designed for role-playing and emotional companionship, supporting ultra-long multi-turn memory and personalized dialogue, with wide applications."
|
|
},
|
|
"chatgpt-4o-latest": {
|
|
"description": "ChatGPT-4o is a dynamic model that updates in real-time to stay current with the latest version. It combines powerful language understanding and generation capabilities, making it suitable for large-scale applications, including customer service, education, and technical support."
|
|
},
|
|
"claude-2.0": {
|
|
"description": "Claude 2 provides advancements in key capabilities for enterprises, including industry-leading 200K token context, significantly reducing the occurrence of model hallucinations, system prompts, and a new testing feature: tool invocation."
|
|
},
|
|
"claude-2.1": {
|
|
"description": "Claude 2 provides advancements in key capabilities for enterprises, including industry-leading 200K token context, significantly reducing the occurrence of model hallucinations, system prompts, and a new testing feature: tool invocation."
|
|
},
|
|
"claude-3-5-sonnet-20240620": {
|
|
"description": "Claude 3.5 Sonnet offers capabilities that surpass Opus and faster speeds than Sonnet, while maintaining the same price as Sonnet. Sonnet excels particularly in programming, data science, visual processing, and agent tasks."
|
|
},
|
|
"claude-3-haiku-20240307": {
|
|
"description": "Claude 3 Haiku is Anthropic's fastest and most compact model, designed for near-instantaneous responses. It features rapid and accurate directional performance."
|
|
},
|
|
"claude-3-opus-20240229": {
|
|
"description": "Claude 3 Opus is Anthropic's most powerful model for handling highly complex tasks. It excels in performance, intelligence, fluency, and comprehension."
|
|
},
|
|
"claude-3-sonnet-20240229": {
|
|
"description": "Claude 3 Sonnet provides an ideal balance of intelligence and speed for enterprise workloads. It offers maximum utility at a lower price, reliable and suitable for large-scale deployment."
|
|
},
|
|
"claude-instant-1.2": {
|
|
"description": "Anthropic's model for low-latency, high-throughput text generation, capable of generating hundreds of pages of text."
|
|
},
|
|
"codegeex-4": {
|
|
"description": "CodeGeeX-4 is a powerful AI programming assistant that supports intelligent Q&A and code completion in various programming languages, enhancing development efficiency."
|
|
},
|
|
"codegemma": {
|
|
"description": "CodeGemma is a lightweight language model dedicated to various programming tasks, supporting rapid iteration and integration."
|
|
},
|
|
"codegemma:2b": {
|
|
"description": "CodeGemma is a lightweight language model dedicated to various programming tasks, supporting rapid iteration and integration."
|
|
},
|
|
"codellama": {
|
|
"description": "Code Llama is an LLM focused on code generation and discussion, combining extensive programming language support, suitable for developer environments."
|
|
},
|
|
"codellama:13b": {
|
|
"description": "Code Llama is an LLM focused on code generation and discussion, combining extensive programming language support, suitable for developer environments."
|
|
},
|
|
"codellama:34b": {
|
|
"description": "Code Llama is an LLM focused on code generation and discussion, combining extensive programming language support, suitable for developer environments."
|
|
},
|
|
"codellama:70b": {
|
|
"description": "Code Llama is an LLM focused on code generation and discussion, combining extensive programming language support, suitable for developer environments."
|
|
},
|
|
"codeqwen": {
|
|
"description": "CodeQwen1.5 is a large language model trained on extensive code data, specifically designed to solve complex programming tasks."
|
|
},
|
|
"codestral": {
|
|
"description": "Codestral is Mistral AI's first code model, providing excellent support for code generation tasks."
|
|
},
|
|
"codestral-latest": {
|
|
"description": "Codestral is a cutting-edge generative model focused on code generation, optimized for intermediate filling and code completion tasks."
|
|
},
|
|
"cognitivecomputations/dolphin-mixtral-8x22b": {
|
|
"description": "Dolphin Mixtral 8x22B is a model designed for instruction following, dialogue, and programming."
|
|
},
|
|
"cohere-command-r": {
|
|
"description": "Command R is a scalable generative model targeting RAG and Tool Use to enable production-scale AI for enterprises."
|
|
},
|
|
"cohere-command-r-plus": {
|
|
"description": "Command R+ is a state-of-the-art RAG-optimized model designed to tackle enterprise-grade workloads."
|
|
},
|
|
"command-r": {
|
|
"description": "Command R is an LLM optimized for dialogue and long context tasks, particularly suitable for dynamic interactions and knowledge management."
|
|
},
|
|
"command-r-plus": {
|
|
"description": "Command R+ is a high-performance large language model designed for real enterprise scenarios and complex applications."
|
|
},
|
|
"databricks/dbrx-instruct": {
|
|
"description": "DBRX Instruct provides highly reliable instruction processing capabilities, supporting applications across multiple industries."
|
|
},
|
|
"deepseek-ai/DeepSeek-V2.5": {
|
|
"description": "DeepSeek V2.5 combines the excellent features of previous versions, enhancing general and coding capabilities."
|
|
},
|
|
"deepseek-ai/deepseek-llm-67b-chat": {
|
|
"description": "DeepSeek 67B is an advanced model trained for highly complex conversations."
|
|
},
|
|
"deepseek-chat": {
|
|
"description": "A new open-source model that integrates general and coding capabilities, retaining the general conversational abilities of the original Chat model and the powerful code handling capabilities of the Coder model, while better aligning with human preferences. Additionally, DeepSeek-V2.5 has achieved significant improvements in writing tasks, instruction following, and more."
|
|
},
|
|
"deepseek-coder-v2": {
|
|
"description": "DeepSeek Coder V2 is an open-source hybrid expert code model that performs excellently in coding tasks, comparable to GPT4-Turbo."
|
|
},
|
|
"deepseek-coder-v2:236b": {
|
|
"description": "DeepSeek Coder V2 is an open-source hybrid expert code model that performs excellently in coding tasks, comparable to GPT4-Turbo."
|
|
},
|
|
"deepseek-v2": {
|
|
"description": "DeepSeek V2 is an efficient Mixture-of-Experts language model, suitable for cost-effective processing needs."
|
|
},
|
|
"deepseek-v2:236b": {
|
|
"description": "DeepSeek V2 236B is the design code model of DeepSeek, providing powerful code generation capabilities."
|
|
},
|
|
"deepseek/deepseek-chat": {
|
|
"description": "A new open-source model that integrates general and coding capabilities, retaining the general conversational abilities of the original Chat model and the powerful code handling capabilities of the Coder model, while better aligning with human preferences. Additionally, DeepSeek-V2.5 has achieved significant improvements in writing tasks, instruction following, and more."
|
|
},
|
|
"emohaa": {
|
|
"description": "Emohaa is a psychological model with professional counseling capabilities, helping users understand emotional issues."
|
|
},
|
|
"gemini-1.0-pro-001": {
|
|
"description": "Gemini 1.0 Pro 001 (Tuning) offers stable and tunable performance, making it an ideal choice for complex task solutions."
|
|
},
|
|
"gemini-1.0-pro-002": {
|
|
"description": "Gemini 1.0 Pro 002 (Tuning) provides excellent multimodal support, focusing on effective solutions for complex tasks."
|
|
},
|
|
"gemini-1.0-pro-latest": {
|
|
"description": "Gemini 1.0 Pro is Google's high-performance AI model, designed for extensive task scaling."
|
|
},
|
|
"gemini-1.5-flash-001": {
|
|
"description": "Gemini 1.5 Flash 001 is an efficient multimodal model that supports extensive application scaling."
|
|
},
|
|
"gemini-1.5-flash-002": {
|
|
"description": "Gemini 1.5 Flash 002 is an efficient multimodal model that supports a wide range of applications."
|
|
},
|
|
"gemini-1.5-flash-8b-exp-0827": {
|
|
"description": "Gemini 1.5 Flash 8B 0827 is designed for handling large-scale task scenarios, providing unparalleled processing speed."
|
|
},
|
|
"gemini-1.5-flash-8b-exp-0924": {
|
|
"description": "Gemini 1.5 Flash 8B 0924 is the latest experimental model, showcasing significant performance improvements in both text and multimodal use cases."
|
|
},
|
|
"gemini-1.5-flash-exp-0827": {
|
|
"description": "Gemini 1.5 Flash 0827 offers optimized multimodal processing capabilities, suitable for a variety of complex task scenarios."
|
|
},
|
|
"gemini-1.5-flash-latest": {
|
|
"description": "Gemini 1.5 Flash is Google's latest multimodal AI model, featuring fast processing capabilities and supporting text, image, and video inputs, making it suitable for efficient scaling across various tasks."
|
|
},
|
|
"gemini-1.5-pro-001": {
|
|
"description": "Gemini 1.5 Pro 001 is a scalable multimodal AI solution that supports a wide range of complex tasks."
|
|
},
|
|
"gemini-1.5-pro-002": {
|
|
"description": "Gemini 1.5 Pro 002 is the latest production-ready model, delivering higher quality outputs, with notable enhancements in mathematics, long-context, and visual tasks."
|
|
},
|
|
"gemini-1.5-pro-exp-0801": {
|
|
"description": "Gemini 1.5 Pro 0801 offers excellent multimodal processing capabilities, providing greater flexibility for application development."
|
|
},
|
|
"gemini-1.5-pro-exp-0827": {
|
|
"description": "Gemini 1.5 Pro 0827 combines the latest optimization technologies to deliver more efficient multimodal data processing capabilities."
|
|
},
|
|
"gemini-1.5-pro-latest": {
|
|
"description": "Gemini 1.5 Pro supports up to 2 million tokens, making it an ideal choice for medium-sized multimodal models, providing multifaceted support for complex tasks."
|
|
},
|
|
"gemma-7b-it": {
|
|
"description": "Gemma 7B is suitable for medium to small-scale task processing, offering cost-effectiveness."
|
|
},
|
|
"gemma2": {
|
|
"description": "Gemma 2 is an efficient model launched by Google, covering a variety of application scenarios from small applications to complex data processing."
|
|
},
|
|
"gemma2-9b-it": {
|
|
"description": "Gemma 2 9B is a model optimized for specific tasks and tool integration."
|
|
},
|
|
"gemma2:27b": {
|
|
"description": "Gemma 2 is an efficient model launched by Google, covering a variety of application scenarios from small applications to complex data processing."
|
|
},
|
|
"gemma2:2b": {
|
|
"description": "Gemma 2 is an efficient model launched by Google, covering a variety of application scenarios from small applications to complex data processing."
|
|
},
|
|
"general": {
|
|
"description": "Spark Lite is a lightweight large language model with extremely low latency and efficient processing capabilities, completely free and open, supporting real-time online search functionality. Its fast response characteristics make it excel in inference applications and model fine-tuning on low-power devices, providing users with excellent cost-effectiveness and intelligent experiences, particularly in knowledge Q&A, content generation, and search scenarios."
|
|
},
|
|
"generalv3": {
|
|
"description": "Spark Pro is a high-performance large language model optimized for professional fields, focusing on mathematics, programming, healthcare, education, and more, supporting online search and built-in plugins for weather, dates, etc. Its optimized model demonstrates excellent performance and efficiency in complex knowledge Q&A, language understanding, and high-level text creation, making it an ideal choice for professional application scenarios."
|
|
},
|
|
"generalv3.5": {
|
|
"description": "Spark3.5 Max is the most comprehensive version, supporting online search and numerous built-in plugins. Its fully optimized core capabilities, along with system role settings and function calling features, enable it to perform exceptionally well in various complex application scenarios."
|
|
},
|
|
"glm-4": {
|
|
"description": "GLM-4 is the old flagship version released in January 2024, currently replaced by the more powerful GLM-4-0520."
|
|
},
|
|
"glm-4-0520": {
|
|
"description": "GLM-4-0520 is the latest model version designed for highly complex and diverse tasks, demonstrating outstanding performance."
|
|
},
|
|
"glm-4-air": {
|
|
"description": "GLM-4-Air is a cost-effective version with performance close to GLM-4, offering fast speed at an affordable price."
|
|
},
|
|
"glm-4-airx": {
|
|
"description": "GLM-4-AirX provides an efficient version of GLM-4-Air, with inference speeds up to 2.6 times faster."
|
|
},
|
|
"glm-4-alltools": {
|
|
"description": "GLM-4-AllTools is a multifunctional intelligent agent model optimized to support complex instruction planning and tool invocation, such as web browsing, code interpretation, and text generation, suitable for multitasking."
|
|
},
|
|
"glm-4-flash": {
|
|
"description": "GLM-4-Flash is the ideal choice for handling simple tasks, being the fastest and most cost-effective."
|
|
},
|
|
"glm-4-long": {
|
|
"description": "GLM-4-Long supports ultra-long text inputs, suitable for memory-based tasks and large-scale document processing."
|
|
},
|
|
"glm-4-plus": {
|
|
"description": "GLM-4-Plus, as a high-intelligence flagship, possesses strong capabilities for processing long texts and complex tasks, with overall performance improvements."
|
|
},
|
|
"glm-4v": {
|
|
"description": "GLM-4V provides strong image understanding and reasoning capabilities, supporting various visual tasks."
|
|
},
|
|
"glm-4v-plus": {
|
|
"description": "GLM-4V-Plus has the ability to understand video content and multiple images, suitable for multimodal tasks."
|
|
},
|
|
"google/gemini-flash-1.5-exp": {
|
|
"description": "Gemini 1.5 Flash 0827 provides optimized multimodal processing capabilities, suitable for various complex task scenarios."
|
|
},
|
|
"google/gemini-pro-1.5-exp": {
|
|
"description": "Gemini 1.5 Pro 0827 combines the latest optimization technologies to deliver more efficient multimodal data processing capabilities."
|
|
},
|
|
"google/gemma-2-27b-it": {
|
|
"description": "Gemma 2 continues the design philosophy of being lightweight and efficient."
|
|
},
|
|
"google/gemma-2-9b-it": {
|
|
"description": "Gemma 2 is Google's lightweight open-source text model series."
|
|
},
|
|
"google/gemma-2-9b-it:free": {
|
|
"description": "Gemma 2 is Google's lightweight open-source text model series."
|
|
},
|
|
"google/gemma-2b-it": {
|
|
"description": "Gemma Instruct (2B) provides basic instruction processing capabilities, suitable for lightweight applications."
|
|
},
|
|
"gpt-3.5-turbo": {
|
|
"description": "GPT 3.5 Turbo is suitable for various text generation and understanding tasks. Currently points to gpt-3.5-turbo-0125."
|
|
},
|
|
"gpt-3.5-turbo-0125": {
|
|
"description": "GPT 3.5 Turbo is suitable for various text generation and understanding tasks. Currently points to gpt-3.5-turbo-0125."
|
|
},
|
|
"gpt-3.5-turbo-1106": {
|
|
"description": "GPT 3.5 Turbo is suitable for various text generation and understanding tasks. Currently points to gpt-3.5-turbo-0125."
|
|
},
|
|
"gpt-3.5-turbo-instruct": {
|
|
"description": "GPT 3.5 Turbo is suitable for various text generation and understanding tasks. Currently points to gpt-3.5-turbo-0125."
|
|
},
|
|
"gpt-4": {
|
|
"description": "GPT-4 offers a larger context window, capable of handling longer text inputs, making it suitable for scenarios that require extensive information integration and data analysis."
|
|
},
|
|
"gpt-4-0125-preview": {
|
|
"description": "The latest GPT-4 Turbo model features visual capabilities. Now, visual requests can be made using JSON format and function calls. GPT-4 Turbo is an enhanced version that provides cost-effective support for multimodal tasks. It strikes a balance between accuracy and efficiency, making it suitable for applications requiring real-time interaction."
|
|
},
|
|
"gpt-4-0613": {
|
|
"description": "GPT-4 offers a larger context window, capable of handling longer text inputs, making it suitable for scenarios that require extensive information integration and data analysis."
|
|
},
|
|
"gpt-4-1106-preview": {
|
|
"description": "The latest GPT-4 Turbo model features visual capabilities. Now, visual requests can be made using JSON format and function calls. GPT-4 Turbo is an enhanced version that provides cost-effective support for multimodal tasks. It strikes a balance between accuracy and efficiency, making it suitable for applications requiring real-time interaction."
|
|
},
|
|
"gpt-4-1106-vision-preview": {
|
|
"description": "The latest GPT-4 Turbo model features visual capabilities. Now, visual requests can be made using JSON format and function calls. GPT-4 Turbo is an enhanced version that provides cost-effective support for multimodal tasks. It strikes a balance between accuracy and efficiency, making it suitable for applications requiring real-time interaction."
|
|
},
|
|
"gpt-4-32k": {
|
|
"description": "GPT-4 offers a larger context window, capable of handling longer text inputs, making it suitable for scenarios that require extensive information integration and data analysis."
|
|
},
|
|
"gpt-4-32k-0613": {
|
|
"description": "GPT-4 offers a larger context window, capable of handling longer text inputs, making it suitable for scenarios that require extensive information integration and data analysis."
|
|
},
|
|
"gpt-4-turbo": {
|
|
"description": "The latest GPT-4 Turbo model features visual capabilities. Now, visual requests can be made using JSON format and function calls. GPT-4 Turbo is an enhanced version that provides cost-effective support for multimodal tasks. It strikes a balance between accuracy and efficiency, making it suitable for applications requiring real-time interaction."
|
|
},
|
|
"gpt-4-turbo-2024-04-09": {
|
|
"description": "The latest GPT-4 Turbo model features visual capabilities. Now, visual requests can be made using JSON format and function calls. GPT-4 Turbo is an enhanced version that provides cost-effective support for multimodal tasks. It strikes a balance between accuracy and efficiency, making it suitable for applications requiring real-time interaction."
|
|
},
|
|
"gpt-4-turbo-preview": {
|
|
"description": "The latest GPT-4 Turbo model features visual capabilities. Now, visual requests can be made using JSON format and function calls. GPT-4 Turbo is an enhanced version that provides cost-effective support for multimodal tasks. It strikes a balance between accuracy and efficiency, making it suitable for applications requiring real-time interaction."
|
|
},
|
|
"gpt-4-vision-preview": {
|
|
"description": "The latest GPT-4 Turbo model features visual capabilities. Now, visual requests can be made using JSON format and function calls. GPT-4 Turbo is an enhanced version that provides cost-effective support for multimodal tasks. It strikes a balance between accuracy and efficiency, making it suitable for applications requiring real-time interaction."
|
|
},
|
|
"gpt-4o": {
|
|
"description": "ChatGPT-4o is a dynamic model that updates in real-time to stay current with the latest version. It combines powerful language understanding and generation capabilities, making it suitable for large-scale applications, including customer service, education, and technical support."
|
|
},
|
|
"gpt-4o-2024-05-13": {
|
|
"description": "ChatGPT-4o is a dynamic model that updates in real-time to stay current with the latest version. It combines powerful language understanding and generation capabilities, making it suitable for large-scale applications, including customer service, education, and technical support."
|
|
},
|
|
"gpt-4o-2024-08-06": {
|
|
"description": "ChatGPT-4o is a dynamic model that updates in real-time to stay current with the latest version. It combines powerful language understanding and generation capabilities, making it suitable for large-scale applications, including customer service, education, and technical support."
|
|
},
|
|
"gpt-4o-mini": {
|
|
"description": "GPT-4o mini is the latest model released by OpenAI after GPT-4 Omni, supporting both image and text input while outputting text. As their most advanced small model, it is significantly cheaper than other recent cutting-edge models, costing over 60% less than GPT-3.5 Turbo. It maintains state-of-the-art intelligence while offering remarkable cost-effectiveness. GPT-4o mini scored 82% on the MMLU test and currently ranks higher than GPT-4 in chat preferences."
|
|
},
|
|
"gryphe/mythomax-l2-13b": {
|
|
"description": "MythoMax l2 13B is a language model that combines creativity and intelligence by merging multiple top models."
|
|
},
|
|
"internlm/internlm2_5-20b-chat": {
|
|
"description": "The innovative open-source model InternLM2.5 enhances dialogue intelligence through a large number of parameters."
|
|
},
|
|
"internlm/internlm2_5-7b-chat": {
|
|
"description": "InternLM2.5 offers intelligent dialogue solutions across multiple scenarios."
|
|
},
|
|
"jamba-1.5-large": {},
|
|
"jamba-1.5-mini": {},
|
|
"llama-3.1-70b-instruct": {
|
|
"description": "Llama 3.1 70B Instruct model, featuring 70B parameters, delivers outstanding performance in large text generation and instruction tasks."
|
|
},
|
|
"llama-3.1-70b-versatile": {
|
|
"description": "Llama 3.1 70B provides enhanced AI reasoning capabilities, suitable for complex applications, supporting extensive computational processing while ensuring efficiency and accuracy."
|
|
},
|
|
"llama-3.1-8b-instant": {
|
|
"description": "Llama 3.1 8B is a high-performance model that offers rapid text generation capabilities, making it ideal for applications requiring large-scale efficiency and cost-effectiveness."
|
|
},
|
|
"llama-3.1-8b-instruct": {
|
|
"description": "Llama 3.1 8B Instruct model, featuring 8B parameters, supports efficient execution of visual instruction tasks, providing high-quality text generation capabilities."
|
|
},
|
|
"llama-3.1-sonar-huge-128k-online": {
|
|
"description": "Llama 3.1 Sonar Huge Online model, featuring 405B parameters, supports a context length of approximately 127,000 tokens, designed for complex online chat applications."
|
|
},
|
|
"llama-3.1-sonar-large-128k-chat": {
|
|
"description": "Llama 3.1 Sonar Large Chat model, featuring 70B parameters, supports a context length of approximately 127,000 tokens, suitable for complex offline chat tasks."
|
|
},
|
|
"llama-3.1-sonar-large-128k-online": {
|
|
"description": "Llama 3.1 Sonar Large Online model, featuring 70B parameters, supports a context length of approximately 127,000 tokens, suitable for high-capacity and diverse chat tasks."
|
|
},
|
|
"llama-3.1-sonar-small-128k-chat": {
|
|
"description": "Llama 3.1 Sonar Small Chat model, featuring 8B parameters, designed for offline chat, supports a context length of approximately 127,000 tokens."
|
|
},
|
|
"llama-3.1-sonar-small-128k-online": {
|
|
"description": "Llama 3.1 Sonar Small Online model, featuring 8B parameters, supports a context length of approximately 127,000 tokens, designed for online chat, efficiently handling various text interactions."
|
|
},
|
|
"llama3-70b-8192": {
|
|
"description": "Meta Llama 3 70B provides unparalleled complexity handling capabilities, tailored for high-demand projects."
|
|
},
|
|
"llama3-8b-8192": {
|
|
"description": "Meta Llama 3 8B delivers high-quality reasoning performance, suitable for diverse application needs."
|
|
},
|
|
"llama3-groq-70b-8192-tool-use-preview": {
|
|
"description": "Llama 3 Groq 70B Tool Use offers powerful tool invocation capabilities, supporting efficient processing of complex tasks."
|
|
},
|
|
"llama3-groq-8b-8192-tool-use-preview": {
|
|
"description": "Llama 3 Groq 8B Tool Use is a model optimized for efficient tool usage, supporting fast parallel computation."
|
|
},
|
|
"llama3.1": {
|
|
"description": "Llama 3.1 is a leading model launched by Meta, supporting up to 405B parameters, applicable in complex dialogues, multilingual translation, and data analysis."
|
|
},
|
|
"llama3.1:405b": {
|
|
"description": "Llama 3.1 is a leading model launched by Meta, supporting up to 405B parameters, applicable in complex dialogues, multilingual translation, and data analysis."
|
|
},
|
|
"llama3.1:70b": {
|
|
"description": "Llama 3.1 is a leading model launched by Meta, supporting up to 405B parameters, applicable in complex dialogues, multilingual translation, and data analysis."
|
|
},
|
|
"llava": {
|
|
"description": "LLaVA is a multimodal model that combines a visual encoder with Vicuna for powerful visual and language understanding."
|
|
},
|
|
"llava-v1.5-7b-4096-preview": {
|
|
"description": "LLaVA 1.5 7B offers integrated visual processing capabilities, generating complex outputs from visual information inputs."
|
|
},
|
|
"llava:13b": {
|
|
"description": "LLaVA is a multimodal model that combines a visual encoder with Vicuna for powerful visual and language understanding."
|
|
},
|
|
"llava:34b": {
|
|
"description": "LLaVA is a multimodal model that combines a visual encoder with Vicuna for powerful visual and language understanding."
|
|
},
|
|
"mathstral": {
|
|
"description": "MathΣtral is designed for scientific research and mathematical reasoning, providing effective computational capabilities and result interpretation."
|
|
},
|
|
"meta-llama-3-70b-instruct": {
|
|
"description": "A powerful 70-billion parameter model excelling in reasoning, coding, and broad language applications."
|
|
},
|
|
"meta-llama-3-8b-instruct": {
|
|
"description": "A versatile 8-billion parameter model optimized for dialogue and text generation tasks."
|
|
},
|
|
"meta-llama-3.1-405b-instruct": {
|
|
"description": "The Llama 3.1 instruction-tuned text-only models are optimized for multilingual dialogue use cases and outperform many of the available open-source and closed chat models on common industry benchmarks."
|
|
},
|
|
"meta-llama-3.1-70b-instruct": {
|
|
"description": "The Llama 3.1 instruction-tuned text-only models are optimized for multilingual dialogue use cases and outperform many of the available open-source and closed chat models on common industry benchmarks."
|
|
},
|
|
"meta-llama-3.1-8b-instruct": {
|
|
"description": "The Llama 3.1 instruction-tuned text-only models are optimized for multilingual dialogue use cases and outperform many of the available open-source and closed chat models on common industry benchmarks."
|
|
},
|
|
"meta-llama/Llama-2-13b-chat-hf": {
|
|
"description": "LLaMA-2 Chat (13B) offers excellent language processing capabilities and outstanding interactive experiences."
|
|
},
|
|
"meta-llama/Llama-3-70b-chat-hf": {
|
|
"description": "LLaMA-3 Chat (70B) is a powerful chat model that supports complex conversational needs."
|
|
},
|
|
"meta-llama/Llama-3-8b-chat-hf": {
|
|
"description": "LLaMA-3 Chat (8B) provides multilingual support, covering a rich array of domain knowledge."
|
|
},
|
|
"meta-llama/Meta-Llama-3-70B-Instruct-Lite": {
|
|
"description": "Llama 3 70B Instruct Lite is suitable for environments requiring high performance and low latency."
|
|
},
|
|
"meta-llama/Meta-Llama-3-70B-Instruct-Turbo": {
|
|
"description": "Llama 3 70B Instruct Turbo offers exceptional language understanding and generation capabilities, suitable for the most demanding computational tasks."
|
|
},
|
|
"meta-llama/Meta-Llama-3-8B-Instruct-Lite": {
|
|
"description": "Llama 3 8B Instruct Lite is designed for resource-constrained environments, providing excellent balanced performance."
|
|
},
|
|
"meta-llama/Meta-Llama-3-8B-Instruct-Turbo": {
|
|
"description": "Llama 3 8B Instruct Turbo is a high-performance large language model, supporting a wide range of application scenarios."
|
|
},
|
|
"meta-llama/Meta-Llama-3.1-405B-Instruct": {
|
|
"description": "LLaMA 3.1 405B is a powerful model for pre-training and instruction tuning."
|
|
},
|
|
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": {
|
|
"description": "The 405B Llama 3.1 Turbo model provides massive context support for big data processing, excelling in large-scale AI applications."
|
|
},
|
|
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
|
|
"description": "LLaMA 3.1 70B offers efficient conversational support in multiple languages."
|
|
},
|
|
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": {
|
|
"description": "Llama 3.1 70B model is finely tuned for high-load applications, quantized to FP8 for enhanced computational efficiency and accuracy, ensuring outstanding performance in complex scenarios."
|
|
},
|
|
"meta-llama/Meta-Llama-3.1-8B-Instruct": {
|
|
"description": "LLaMA 3.1 provides multilingual support and is one of the industry's leading generative models."
|
|
},
|
|
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
|
|
"description": "Llama 3.1 8B model utilizes FP8 quantization, supporting up to 131,072 context tokens, making it a standout in open-source models, excelling in complex tasks and outperforming many industry benchmarks."
|
|
},
|
|
"meta-llama/llama-3-70b-instruct": {
|
|
"description": "Llama 3 70B Instruct is optimized for high-quality conversational scenarios, demonstrating excellent performance in various human evaluations."
|
|
},
|
|
"meta-llama/llama-3-8b-instruct": {
|
|
"description": "Llama 3 8B Instruct is optimized for high-quality conversational scenarios, performing better than many closed-source models."
|
|
},
|
|
"meta-llama/llama-3.1-405b-instruct": {
|
|
"description": "Llama 3.1 405B Instruct is the latest version from Meta, optimized for generating high-quality dialogues, surpassing many leading closed-source models."
|
|
},
|
|
"meta-llama/llama-3.1-70b-instruct": {
|
|
"description": "Llama 3.1 70B Instruct is designed for high-quality conversations, excelling in human evaluations, particularly in highly interactive scenarios."
|
|
},
|
|
"meta-llama/llama-3.1-8b-instruct": {
|
|
"description": "Llama 3.1 8B Instruct is the latest version released by Meta, optimized for high-quality conversational scenarios, outperforming many leading closed-source models."
|
|
},
|
|
"meta-llama/llama-3.1-8b-instruct:free": {
|
|
"description": "LLaMA 3.1 offers multilingual support and is one of the industry's leading generative models."
|
|
},
|
|
"meta.llama3-1-405b-instruct-v1:0": {
|
|
"description": "Meta Llama 3.1 405B Instruct is the largest and most powerful model in the Llama 3.1 Instruct series. It is a highly advanced conversational reasoning and synthetic data generation model, which can also serve as a foundation for specialized continuous pre-training or fine-tuning in specific domains. The multilingual large language models (LLMs) provided by Llama 3.1 are a set of pre-trained, instruction-tuned generative models, including sizes of 8B, 70B, and 405B (text input/output). The instruction-tuned text models (8B, 70B, 405B) are optimized for multilingual conversational use cases and have outperformed many available open-source chat models in common industry benchmarks. Llama 3.1 is designed for commercial and research purposes across multiple languages. The instruction-tuned text models are suitable for assistant-like chat, while the pre-trained models can adapt to various natural language generation tasks. The Llama 3.1 models also support improving other models using their outputs, including synthetic data generation and refinement. Llama 3.1 is an autoregressive language model built using an optimized transformer architecture. The tuned versions utilize supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety."
|
|
},
|
|
"meta.llama3-1-70b-instruct-v1:0": {
|
|
"description": "The updated version of Meta Llama 3.1 70B Instruct includes an extended 128K context length, multilingual capabilities, and improved reasoning abilities. The multilingual large language models (LLMs) provided by Llama 3.1 are a set of pre-trained, instruction-tuned generative models, including sizes of 8B, 70B, and 405B (text input/output). The instruction-tuned text models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and have surpassed many available open-source chat models in common industry benchmarks. Llama 3.1 is designed for commercial and research purposes in multiple languages. The instruction-tuned text models are suitable for assistant-like chat, while the pre-trained models can adapt to various natural language generation tasks. The Llama 3.1 model also supports using its outputs to improve other models, including synthetic data generation and refinement. Llama 3.1 is an autoregressive language model using optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety."
|
|
},
|
|
"meta.llama3-1-8b-instruct-v1:0": {
|
|
"description": "The updated version of Meta Llama 3.1 8B Instruct includes an extended 128K context length, multilingual capabilities, and improved reasoning abilities. The multilingual large language models (LLMs) provided by Llama 3.1 are a set of pre-trained, instruction-tuned generative models, including sizes of 8B, 70B, and 405B (text input/output). The instruction-tuned text models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and have surpassed many available open-source chat models in common industry benchmarks. Llama 3.1 is designed for commercial and research purposes in multiple languages. The instruction-tuned text models are suitable for assistant-like chat, while the pre-trained models can adapt to various natural language generation tasks. The Llama 3.1 model also supports using its outputs to improve other models, including synthetic data generation and refinement. Llama 3.1 is an autoregressive language model using optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety."
|
|
},
|
|
"meta.llama3-70b-instruct-v1:0": {
|
|
"description": "Meta Llama 3 is an open large language model (LLM) aimed at developers, researchers, and enterprises, designed to help them build, experiment, and responsibly scale their generative AI ideas. As part of a foundational system for global community innovation, it is particularly suitable for content creation, conversational AI, language understanding, R&D, and enterprise applications."
|
|
},
|
|
"meta.llama3-8b-instruct-v1:0": {
|
|
"description": "Meta Llama 3 is an open large language model (LLM) aimed at developers, researchers, and enterprises, designed to help them build, experiment, and responsibly scale their generative AI ideas. As part of a foundational system for global community innovation, it is particularly suitable for those with limited computational power and resources, edge devices, and faster training times."
|
|
},
|
|
"microsoft/wizardlm 2-7b": {
|
|
"description": "WizardLM 2 7B is Microsoft's latest lightweight AI model, performing nearly ten times better than existing leading open-source models."
|
|
},
|
|
"microsoft/wizardlm-2-8x22b": {
|
|
"description": "WizardLM-2 8x22B is Microsoft's state-of-the-art Wizard model, demonstrating extremely competitive performance."
|
|
},
|
|
"minicpm-v": {
|
|
"description": "MiniCPM-V is a next-generation multimodal large model launched by OpenBMB, boasting exceptional OCR recognition and multimodal understanding capabilities, supporting a wide range of application scenarios."
|
|
},
|
|
"mistral": {
|
|
"description": "Mistral is a 7B model released by Mistral AI, suitable for diverse language processing needs."
|
|
},
|
|
"mistral-large": {
|
|
"description": "Mixtral Large is Mistral's flagship model, combining capabilities in code generation, mathematics, and reasoning, supporting a 128k context window."
|
|
},
|
|
"mistral-large-2407": {
|
|
"description": "Mistral Large (2407) is an advanced Large Language Model (LLM) with state-of-the-art reasoning, knowledge, and coding capabilities."
|
|
},
|
|
"mistral-large-latest": {
|
|
"description": "Mistral Large is the flagship model, excelling in multilingual tasks, complex reasoning, and code generation, making it an ideal choice for high-end applications."
|
|
},
|
|
"mistral-nemo": {
|
|
"description": "Mistral Nemo, developed in collaboration with Mistral AI and NVIDIA, is a high-performance 12B model."
|
|
},
|
|
"mistral-small": {
|
|
"description": "Mistral Small can be used for any language-based task that requires high efficiency and low latency."
|
|
},
|
|
"mistral-small-latest": {
|
|
"description": "Mistral Small is a cost-effective, fast, and reliable option suitable for use cases such as translation, summarization, and sentiment analysis."
|
|
},
|
|
"mistralai/Mistral-7B-Instruct-v0.1": {
|
|
"description": "Mistral (7B) Instruct is known for its high performance, suitable for various language tasks."
|
|
},
|
|
"mistralai/Mistral-7B-Instruct-v0.2": {
|
|
"description": "Mistral 7B is a model fine-tuned on demand, providing optimized answers for tasks."
|
|
},
|
|
"mistralai/Mistral-7B-Instruct-v0.3": {
|
|
"description": "Mistral (7B) Instruct v0.3 offers efficient computational power and natural language understanding, suitable for a wide range of applications."
|
|
},
|
|
"mistralai/Mixtral-8x22B-Instruct-v0.1": {
|
|
"description": "Mixtral-8x22B Instruct (141B) is a super large language model that supports extremely high processing demands."
|
|
},
|
|
"mistralai/Mixtral-8x7B-Instruct-v0.1": {
|
|
"description": "Mixtral 8x7B is a pre-trained sparse mixture of experts model for general text tasks."
|
|
},
|
|
"mistralai/mistral-7b-instruct": {
|
|
"description": "Mistral 7B Instruct is a high-performance industry-standard model optimized for speed and long context support."
|
|
},
|
|
"mistralai/mistral-nemo": {
|
|
"description": "Mistral Nemo is a multilingual model with 7.3 billion parameters, designed for high-performance programming."
|
|
},
|
|
"mixtral": {
|
|
"description": "Mixtral is an expert model from Mistral AI, featuring open-source weights and providing support in code generation and language understanding."
|
|
},
|
|
"mixtral-8x7b-32768": {
|
|
"description": "Mixtral 8x7B provides high fault-tolerant parallel computing capabilities, suitable for complex tasks."
|
|
},
|
|
"mixtral:8x22b": {
|
|
"description": "Mixtral is an expert model from Mistral AI, featuring open-source weights and providing support in code generation and language understanding."
|
|
},
|
|
"moonshot-v1-128k": {
|
|
"description": "Moonshot V1 128K is a model with ultra-long context processing capabilities, suitable for generating extremely long texts, meeting the demands of complex generation tasks, capable of handling up to 128,000 tokens, making it ideal for research, academia, and large document generation."
|
|
},
|
|
"moonshot-v1-32k": {
|
|
"description": "Moonshot V1 32K offers medium-length context processing capabilities, able to handle 32,768 tokens, particularly suitable for generating various long documents and complex dialogues, applicable in content creation, report generation, and dialogue systems."
|
|
},
|
|
"moonshot-v1-8k": {
|
|
"description": "Moonshot V1 8K is designed for generating short text tasks, featuring efficient processing performance, capable of handling 8,192 tokens, making it ideal for brief dialogues, note-taking, and rapid content generation."
|
|
},
|
|
"nousresearch/hermes-2-pro-llama-3-8b": {
|
|
"description": "Hermes 2 Pro Llama 3 8B is an upgraded version of Nous Hermes 2, featuring the latest internally developed datasets."
|
|
},
|
|
"o1-mini": {
|
|
"description": "o1-mini is a fast and cost-effective reasoning model designed for programming, mathematics, and scientific applications. This model features a 128K context and has a knowledge cutoff date of October 2023."
|
|
},
|
|
"o1-preview": {
|
|
"description": "o1 is OpenAI's new reasoning model, suitable for complex tasks that require extensive general knowledge. This model features a 128K context and has a knowledge cutoff date of October 2023."
|
|
},
|
|
"open-codestral-mamba": {
|
|
"description": "Codestral Mamba is a language model focused on code generation, providing strong support for advanced coding and reasoning tasks."
|
|
},
|
|
"open-mistral-7b": {
|
|
"description": "Mistral 7B is a compact yet high-performance model, excelling in batch processing and simple tasks such as classification and text generation, with good reasoning capabilities."
|
|
},
|
|
"open-mistral-nemo": {
|
|
"description": "Mistral Nemo is a 12B model developed in collaboration with Nvidia, offering outstanding reasoning and coding performance, easy to integrate and replace."
|
|
},
|
|
"open-mixtral-8x22b": {
|
|
"description": "Mixtral 8x22B is a larger expert model focused on complex tasks, providing excellent reasoning capabilities and higher throughput."
|
|
},
|
|
"open-mixtral-8x7b": {
|
|
"description": "Mixtral 8x7B is a sparse expert model that leverages multiple parameters to enhance reasoning speed, suitable for handling multilingual and code generation tasks."
|
|
},
|
|
"openai/gpt-4o-2024-08-06": {
|
|
"description": "ChatGPT-4o is a dynamic model that updates in real-time to maintain the latest version. It combines powerful language understanding and generation capabilities, making it suitable for large-scale application scenarios, including customer service, education, and technical support."
|
|
},
|
|
"openai/gpt-4o-mini": {
|
|
"description": "GPT-4o mini is the latest model released by OpenAI following GPT-4 Omni, supporting both text and image input while outputting text. As their most advanced small model, it is significantly cheaper than other recent cutting-edge models and over 60% cheaper than GPT-3.5 Turbo. It maintains state-of-the-art intelligence while offering remarkable cost-effectiveness. GPT-4o mini scored 82% on the MMLU test and currently ranks higher than GPT-4 in chat preferences."
|
|
},
|
|
"openai/o1-mini": {
|
|
"description": "o1-mini is a fast and cost-effective reasoning model designed for programming, mathematics, and scientific applications. This model features a 128K context and has a knowledge cutoff date of October 2023."
|
|
},
|
|
"openai/o1-preview": {
|
|
"description": "o1 is OpenAI's new reasoning model, suitable for complex tasks that require extensive general knowledge. This model features a 128K context and has a knowledge cutoff date of October 2023."
|
|
},
|
|
"openchat/openchat-7b": {
|
|
"description": "OpenChat 7B is an open-source language model library fine-tuned using the 'C-RLFT (Conditional Reinforcement Learning Fine-Tuning)' strategy."
|
|
},
|
|
"openrouter/auto": {
|
|
"description": "Based on context length, topic, and complexity, your request will be sent to Llama 3 70B Instruct, Claude 3.5 Sonnet (self-regulating), or GPT-4o."
|
|
},
|
|
"phi3": {
|
|
"description": "Phi-3 is a lightweight open model launched by Microsoft, suitable for efficient integration and large-scale knowledge reasoning."
|
|
},
|
|
"phi3:14b": {
|
|
"description": "Phi-3 is a lightweight open model launched by Microsoft, suitable for efficient integration and large-scale knowledge reasoning."
|
|
},
|
|
"pixtral-12b-2409": {
|
|
"description": "The Pixtral model demonstrates strong capabilities in tasks such as chart and image understanding, document question answering, multimodal reasoning, and instruction following. It can ingest images at natural resolutions and aspect ratios and handle an arbitrary number of images within a long context window of up to 128K tokens."
|
|
},
|
|
"qwen-coder-turbo-latest": {
|
|
"description": "The Tongyi Qianwen Coder model."
|
|
},
|
|
"qwen-long": {
|
|
"description": "Qwen is a large-scale language model that supports long text contexts and dialogue capabilities based on long documents and multiple documents."
|
|
},
|
|
"qwen-math-plus-latest": {
|
|
"description": "The Tongyi Qianwen Math model is specifically designed for solving mathematical problems."
|
|
},
|
|
"qwen-math-turbo-latest": {
|
|
"description": "The Tongyi Qianwen Math model is specifically designed for solving mathematical problems."
|
|
},
|
|
"qwen-max-latest": {
|
|
"description": "Tongyi Qianwen Max is a large-scale language model with hundreds of billions of parameters, supporting input in various languages, including Chinese and English. It is the API model behind the current Tongyi Qianwen 2.5 product version."
|
|
},
|
|
"qwen-plus-latest": {
|
|
"description": "Tongyi Qianwen Plus is an enhanced version of the large-scale language model, supporting input in various languages, including Chinese and English."
|
|
},
|
|
"qwen-turbo-latest": {
|
|
"description": "Tongyi Qianwen is a large-scale language model that supports input in various languages, including Chinese and English."
|
|
},
|
|
"qwen-vl-chat-v1": {
|
|
"description": "Qwen VL supports flexible interaction methods, including multi-image, multi-turn Q&A, and creative capabilities."
|
|
},
|
|
"qwen-vl-max": {
|
|
"description": "Qwen is a large-scale visual language model. Compared to the enhanced version, it further improves visual reasoning and instruction-following capabilities, providing higher levels of visual perception and cognition."
|
|
},
|
|
"qwen-vl-plus": {
|
|
"description": "Qwen is a large-scale visual language model enhanced version. It significantly improves detail recognition and text recognition capabilities, supporting images with resolutions over one million pixels and any aspect ratio."
|
|
},
|
|
"qwen-vl-v1": {
|
|
"description": "Initialized with the Qwen-7B language model, this pre-trained model adds an image model with an input resolution of 448."
|
|
},
|
|
"qwen/qwen-2-7b-instruct:free": {
|
|
"description": "Qwen2 is a brand new series of large language models with enhanced understanding and generation capabilities."
|
|
},
|
|
"qwen2": {
|
|
"description": "Qwen2 is Alibaba's next-generation large-scale language model, supporting diverse application needs with excellent performance."
|
|
},
|
|
"qwen2.5-14b-instruct": {
|
|
"description": "The 14B model of Tongyi Qianwen 2.5 is open-sourced."
|
|
},
|
|
"qwen2.5-32b-instruct": {
|
|
"description": "The 32B model of Tongyi Qianwen 2.5 is open-sourced."
|
|
},
|
|
"qwen2.5-72b-instruct": {
|
|
"description": "The 72B model of Tongyi Qianwen 2.5 is open-sourced."
|
|
},
|
|
"qwen2.5-7b-instruct": {
|
|
"description": "The 7B model of Tongyi Qianwen 2.5 is open-sourced."
|
|
},
|
|
"qwen2.5-coder-1.5b-instruct": {
|
|
"description": "The open-source version of the Tongyi Qianwen Coder model."
|
|
},
|
|
"qwen2.5-coder-7b-instruct": {
|
|
"description": "The open-source version of the Tongyi Qianwen Coder model."
|
|
},
|
|
"qwen2.5-math-1.5b-instruct": {
|
|
"description": "The Qwen-Math model possesses strong capabilities for solving mathematical problems."
|
|
},
|
|
"qwen2.5-math-72b-instruct": {
|
|
"description": "The Qwen-Math model possesses strong capabilities for solving mathematical problems."
|
|
},
|
|
"qwen2.5-math-7b-instruct": {
|
|
"description": "The Qwen-Math model possesses strong capabilities for solving mathematical problems."
|
|
},
|
|
"qwen2:0.5b": {
|
|
"description": "Qwen2 is Alibaba's next-generation large-scale language model, supporting diverse application needs with excellent performance."
|
|
},
|
|
"qwen2:1.5b": {
|
|
"description": "Qwen2 is Alibaba's next-generation large-scale language model, supporting diverse application needs with excellent performance."
|
|
},
|
|
"qwen2:72b": {
|
|
"description": "Qwen2 is Alibaba's next-generation large-scale language model, supporting diverse application needs with excellent performance."
|
|
},
|
|
"solar-1-mini-chat": {
|
|
"description": "Solar Mini is a compact LLM that outperforms GPT-3.5, featuring strong multilingual capabilities, supporting English and Korean, and providing an efficient and compact solution."
|
|
},
|
|
"solar-1-mini-chat-ja": {
|
|
"description": "Solar Mini (Ja) extends the capabilities of Solar Mini, focusing on Japanese while maintaining efficiency and excellent performance in English and Korean usage."
|
|
},
|
|
"solar-pro": {
|
|
"description": "Solar Pro is a highly intelligent LLM launched by Upstage, focusing on single-GPU instruction-following capabilities, with an IFEval score above 80. Currently supports English, with a formal version planned for release in November 2024, which will expand language support and context length."
|
|
},
|
|
"step-1-128k": {
|
|
"description": "Balances performance and cost, suitable for general scenarios."
|
|
},
|
|
"step-1-256k": {
|
|
"description": "Equipped with ultra-long context processing capabilities, especially suitable for long document analysis."
|
|
},
|
|
"step-1-32k": {
|
|
"description": "Supports medium-length dialogues, applicable to various application scenarios."
|
|
},
|
|
"step-1-8k": {
|
|
"description": "Small model, suitable for lightweight tasks."
|
|
},
|
|
"step-1-flash": {
|
|
"description": "High-speed model, suitable for real-time dialogues."
|
|
},
|
|
"step-1v-32k": {
|
|
"description": "Supports visual input, enhancing multimodal interaction experiences."
|
|
},
|
|
"step-1v-8k": {
|
|
"description": "A small visual model suitable for basic text and image tasks."
|
|
},
|
|
"step-2-16k": {
|
|
"description": "Supports large-scale context interactions, suitable for complex dialogue scenarios."
|
|
},
|
|
"taichu_llm": {
|
|
"description": "The ZD Taichu language model possesses strong language understanding capabilities and excels in text creation, knowledge Q&A, code programming, mathematical calculations, logical reasoning, sentiment analysis, and text summarization. It innovatively combines large-scale pre-training with rich knowledge from multiple sources, continuously refining algorithmic techniques and absorbing new knowledge in vocabulary, structure, grammar, and semantics from vast text data, resulting in an evolving model performance. It provides users with more convenient information and services, as well as a more intelligent experience."
|
|
},
|
|
"taichu_vqa": {
|
|
"description": "Taichu 2.0V integrates capabilities such as image understanding, knowledge transfer, and logical reasoning, excelling in the field of image-text question answering."
|
|
},
|
|
"togethercomputer/StripedHyena-Nous-7B": {
|
|
"description": "StripedHyena Nous (7B) provides enhanced computational capabilities through efficient strategies and model architecture."
|
|
},
|
|
"upstage/SOLAR-10.7B-Instruct-v1.0": {
|
|
"description": "Upstage SOLAR Instruct v1 (11B) is suitable for refined instruction tasks, offering excellent language processing capabilities."
|
|
},
|
|
"wizardlm2": {
|
|
"description": "WizardLM 2 is a language model provided by Microsoft AI, excelling in complex dialogues, multilingual capabilities, reasoning, and intelligent assistant applications."
|
|
},
|
|
"wizardlm2:8x22b": {
|
|
"description": "WizardLM 2 is a language model provided by Microsoft AI, excelling in complex dialogues, multilingual capabilities, reasoning, and intelligent assistant applications."
|
|
},
|
|
"yi-large": {
|
|
"description": "A new trillion-parameter model, providing super strong question-answering and text generation capabilities."
|
|
},
|
|
"yi-large-fc": {
|
|
"description": "Based on the yi-large model, supports and enhances tool invocation capabilities, suitable for various business scenarios requiring agent or workflow construction."
|
|
},
|
|
"yi-large-preview": {
|
|
"description": "Initial version, recommended to use yi-large (new version)."
|
|
},
|
|
"yi-large-rag": {
|
|
"description": "High-level service based on the yi-large super strong model, combining retrieval and generation techniques to provide precise answers and real-time information retrieval services."
|
|
},
|
|
"yi-large-turbo": {
|
|
"description": "Exceptional performance at a high cost-performance ratio. Conducts high-precision tuning based on performance, inference speed, and cost."
|
|
},
|
|
"yi-medium": {
|
|
"description": "Medium-sized model upgraded and fine-tuned, balanced capabilities, and high cost-performance ratio. Deeply optimized instruction-following capabilities."
|
|
},
|
|
"yi-medium-200k": {
|
|
"description": "200K ultra-long context window, providing deep understanding and generation capabilities for long texts."
|
|
},
|
|
"yi-spark": {
|
|
"description": "Small yet powerful, lightweight and fast model. Provides enhanced mathematical computation and coding capabilities."
|
|
},
|
|
"yi-vision": {
|
|
"description": "Model for complex visual tasks, providing high-performance image understanding and analysis capabilities."
|
|
}
|
|
}
|