logo
返回模型列表

inclusionAI: Ling-3.0-tiny下线

inclusionai/ling-3.0-tiny
对比对话

Ling-3.0-tiny is an efficient 7.9B-parameter MoE model with only 1.3B active parameters per token. It is designed for responsive AI agents, reliable instruction following, and natural multi-turn conversations. The model features a 256K context window, native function calling, prompt caching, and switchable Thinking and Instant modes. It supports long-context, tool-using workflows with lower active-compute requirements.

由:inclusionAI输入类型:输出类型:发布时间:2026-08-07

供应商

在多个供应商之间路由请求。复制供应商标识以设置偏好供应商。

供应商缓存命中率上下文
Ant Ling下线
ant-ling
-$0/ 百万 token$0/ 百万 token读取：0/ 百万 token写入：-/ 百万 token262.14K2.94s1.68tps

可用率

24 小时

AI Gateway 直连请求及各供应商的成功率。

Oct 20, 07:04
Ant Ling0.00%

吞吐量

24 小时

AI Gateway 实时流量的 P50 吞吐量，单位为每秒 token 数（TPS）。

Oct 19, 18:00
Ant Ling1.68 tps

延迟

24 小时

AI Gateway 实时流量的 P50 首 token 延迟（TTFT），单位为毫秒。

Oct 19, 18:00
Ant Ling2.94s

活动

该模型随时间变化的 token 用量和请求流量。

Token 消耗
Oct 19
Ant Ling19.0K

按实际处理请求的供应商拆分 token 用量。区块越大，表示该供应商处理的模型流量越多。

基准测试

标准化评测得分。百分比越高越好，并展示排名百分位。

指标来源：Artificial Analysis

Ling-3.0-tinyinclusionAI
Intelligence Index11.1

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. View All

Token 排行
No data
No app usage is available for this period.

相关模型

更多模型来自 inclusionAI

inclusionAI: LLaDA-Image
-token

LLaDA-Image is a competitive 6B-parameter open-source unified image generation and editing model. It is the 50-step base variant for high-quality text-to-image generation and instruction-guided editing, supporting reference-image editing and Chinese-English text rendering with strong visual detail, natural lighting, and coherent composition.

inclusionAI: Ling-3.1-flash
12.16Btoken

Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.

inclusionAI: Ming Image 0.1 Design Layer
16.01Mtoken

Ming Image 0.1 Design Layer is an image-to-image model from inclusionAI that decomposes a flattened design image into separate RGBA layers, such as a background layer and foreground elements, and returns one image per layer. It requires exactly one reference image and a prompt describing the layer plan. Output format can be requested as PNG or WebP. Output dimensions follow the input image, so explicit sizes and aspect ratios are rejected instead of silently reshaped.