Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized for Korean with English and Japanese support. Solar Pro 3: Better reasoning at production scale

输入价格

$0.25 / 1M Tokens

输出价格

$0.25 / 1M Tokens

复杂推理企业工作流韩英日多语言

厂商文档价格

模型详情

语言模型Liquid AI稳定版

LFM2.5-1.2B-Instruct

Instruction-tuned 1.2B parameter model optimized for chat and general-purpose tasks

输入价格

公开资料未说明

输出价格

公开资料未说明

聊天助手指令跟随Tool Use

厂商文档官网

模型详情

语言模型Liquid AI即将下线

LFM2-1.2B-Tool

1.2B parameter model for tool calling (deprecated)

输入价格

公开资料未说明

输出价格

公开资料未说明

Tool Use工作流编排函数调用

厂商文档官网

模型详情

语言模型Arcee AI预览版

Trinity Nano 6B

Pricing Integration List chevron-right Language Models chevron-right Trinity-Nano (6B) Trinity-Mini (26B) Trinity-Large-Preview Trinity-Large-Thinking API Reference chevron-right Your First API Call Chat Completion Usage Models Capabilities chevron-right Streaming Messages Multi-Turn Conversations Function Calling Structured Outputs Reasoning Traces Quick Deploys chevron-right Download Models arrow-up-right Hardware Prerequisites Consumer Hardware chevron-right Inference Engines chevron-right Policies chevron-right Deprecation Policy chevron-up chevron-down gitbook Powered by GitBook gitbook xmark block-quote On this page xmark xmark copy Copy chevron-down block-quote On this page block-quote Language Models Trinity-Nano (6B) Overview Trinity Nano is a 6B-parameter (1B active) sparse mixture-of-experts language model, optimized for high-efficiency inference in real-time, on-device, and embedded AI applications.

输入价格

公开资料未说明

输出价格

公开资料未说明

端侧部署低延迟轻量 Agent

厂商文档价格

模型详情

语言模型Arcee AI稳定版

Trinity Mini

Pricing Integration List chevron-right Language Models chevron-right Trinity-Nano (6B) Trinity-Mini (26B) Trinity-Large-Preview Trinity-Large-Thinking API Reference chevron-right Your First API Call Chat Completion Usage Models Capabilities chevron-right Streaming Messages Multi-Turn Conversations Function Calling Structured Outputs Reasoning Traces Quick Deploys chevron-right Download Models arrow-up-right Hardware Prerequisites Consumer Hardware chevron-right Inference Engines chevron-right Policies chevron-right Deprecation Policy chevron-up chevron-down gitbook Powered by GitBook gitbook xmark block-quote On this page xmark xmark copy Copy chevron-down block-quote On this page block-quote Language Models Trinity-Mini (26B) Overview Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model, engineered for efficient inference over long contexts with robust function calling and multi-step agent workflows.

输入价格

公开资料未说明

输出价格

公开资料未说明

函数调用Agent 工作流长上下文

厂商文档价格

模型详情