全部模型

llama 4 17b
10240K 4 服务商
暂无简介
对话 函数调用视觉
已收录
Llama 4 Maverick 17B Instruct
1049K 3 服务商
暂无简介
对话 函数调用视觉
已收录
Grok 4
256K 4 服务商
Our newest and strongest flagship model, excelling in NLP, math, and reasoning—an ideal all-rounder.
对话 函数调用推理
已收录
Command A 2503
256K 1 服务商
Command A is our most capable model to date, excelling at tool use, agents, RAG, and multilingual scenarios. It has a 25...
对话 函数调用
已收录
Qwen2.5 Coder 14B
131K 2 服务商
Open-source Qwen code model.
对话
已收录
Qwen2.5 14B
131K 6 服务商
Qwen2.5 open-source 14B model.
对话 函数调用
已收录
DeepSeek R1 Distill Qwen 1.5B
131K 4 服务商
DeepSeek-R1 distilled models use RL and cold-start data to improve reasoning and set new open-model multi-task benchmark...
对话 推理
已收录
Qwen2.5 72B Instruct
131K 6 服务商
Qwen2.5 is a decoder-only LLM series developed by the Qwen team and Alibaba Cloud, offering 0.5B, 1.5B, 3B, 7B, 14B, 32B...
对话 函数调用
已收录
Llama 3.2 90B Vision Instruct
131K 3 服务商
An instruction-tuned vision reasoning model from Meta with 90B parameters, optimized for visual recognition, image reaso...
对话 函数调用视觉
已收录
Llama 3.2 11B Vision Instruct
131K 3 服务商
An instruction-tuned vision reasoning model from Meta with 11B parameters, optimized for visual recognition, image reaso...
对话 函数调用视觉
已收录
Llama 3.2 3B Instruct
131K 4 服务商
Llama 3.2 3B Instruct is a lightweight multilingual model from Meta, designed for efficient runtime with significant lat...
对话 函数调用
已收录
Llama 3.3 70B Instruct
131K 6 服务商
Llama 3.3 70B Instruct is the December update to Llama 3.1 70B. It improves tool use, multilingual text support, math, a...
对话 函数调用
已收录
DeepSeek V3.1 Terminus
131K 6 服务商
暂无简介
对话 函数调用推理
已收录
gemma 3 12b
131K 3 服务商
暂无简介
对话
已收录
qwen2.5 coder 32b
131K 6 服务商
暂无简介
对话 函数调用
已收录
Qwen 3 235B Instruct
131K 1 服务商
暂无简介
对话 函数调用
已收录
GLM 4.7
131K 1 服务商
This model delivers strong coding performance with advanced reasoning capabilities, superior tool use, and enhanced real...
对话 函数调用推理
已收录
Llama 4 Maverick (17Bx128E)
131K 1 服务商
Llama 4 Maverick is a large MoE model with efficient expert activation for strong reasoning performance.
对话 视觉
已收录
DeepSeek V3.1 (Fast)
131K 1 服务商
DeepSeek V3.1 Fast is the high-TPS fast variant of DeepSeek V3.1. Hybrid thinking mode: via chat templates, one model su...
对话 函数调用推理
已收录
DeepSeek V3.1 (Think)
131K 1 服务商
DeepSeek-V3.1 thinking mode: a new hybrid reasoning model with thinking and non-thinking modes, more efficient than Deep...
对话 函数调用推理
已收录
grok-3-mini-beta
131K 1 服务商
暂无简介
对话
已收录
grok-3-beta
131K 1 服务商
暂无简介
对话
已收录
Aya Expanse 32B
128K 1 服务商
Aya Expanse is a high-performance 32B multilingual model that uses instruction tuning, data arbitrage, preference traini...
对话
已收录
Command Nightly
128K 1 服务商
To shorten the gap between major releases, we offer nightly Command builds. For the Command series this is called comman...
对话 函数调用
已收录