NEWClaude Sonnet 5 is live — 1M context · 128K output
One API, every leading AI model

NexusFlow

Between question and answer, there is always a path. NexusFlow turns that uncertainty into one deliberate API for text, vision, image and video intelligence.

Start buildingRead quickstart
77+model options
1MClaude Sonnet 5 context
128KClaude Sonnet 5 max output
Claude Sonnet 5Featured
Anthropic via HiModels1M context
In ¥13.6 · Out ¥68
Qwen3.8 MaxNew
Tongyi Qianwen1M context
In ¥12 · Out ¥36
Kimi K3New
Moonshot AI1M context
In ¥20 · Out ¥100
Qwen3.7 MaxFlagship
Tongyi Qianwen1M context
In ¥12 · Out ¥36
Qwen3 MaxStable
Tongyi Qianwen262K context
In ¥2.5 · Out ¥10
Qwen LongLong
Tongyi Qianwen10M context
In ¥0.5 · Out ¥2
Qwen3.6 PlusPopular
Tongyi Qianwen1M context
In ¥2 · Out ¥12
Qwen3.5 PlusBalanced
Tongyi Qianwen1M context
In ¥0.8 · Out ¥4.8
Qwen3.5 FlashFast
Tongyi Qianwen1M context
In ¥0.2 · Out ¥2
Qwen3.5 Omni PlusOmni
Tongyi Qianwen262K omni
In ¥7 · Out ¥40
Qwen3.5 Omni FlashOmni
Tongyi Qianwen262K omni
In ¥2.2 · Out ¥13.3
Qwen3 VL FlashVision
Tongyi Qianwen262K vision
In ¥0.15 · Out ¥1.5
Qwen3 Coder FlashCode
Tongyi Qianwen1M code
In ¥1 · Out ¥4
DeepSeek V4 FlashFast
DeepSeek1M context
In ¥1 · Out ¥2
DeepSeek V4 Flash 0731Snapshot
DeepSeek1M context
In ¥1 · Out ¥2
DeepSeek V4 Pro 0813Snapshot
DeepSeek1M context
In ¥9 · Out ¥27
DeepSeek V4 ProReasoning
DeepSeek1M context
In ¥12 · Out ¥24
DeepSeek V3.2General
DeepSeek131K context
In ¥2 · Out ¥3
GLM 5.2Flagship
Zhipu AI1M context
In ¥8 · Out ¥28
Text Embedding V4Vector
Tongyi Qianwen8K vectors
¥0.5 / 1M input
Qwen Image MaxImage
Tongyi QianwenImage
per image
PixVerse V6Video
PixVerseAsync video
from ¥0.15/s
HappyHorse 1.0Video
Tongyi QianwenAsync video
from ¥0.9/s
Featured LLM首选by Anthropic · HiModels

Claude Sonnet 5

Claude Sonnet 5 是 NexusFlow 当前优先推荐的 Claude 模型，面向生产级对话、复杂分析与长上下文工作流——使用稳定公开 ID claude-sonnet-5。

通过 HiModels 原生 Anthropic Messages 兼容上游接入。输入 ¥13.6/M、输出 ¥68/M；首页始终使用不带日期后缀的稳定模型 ID。

1M
Token 上下文窗口
128K
最大输出
¥13.6/M
输入价格
¥68/M
输出价格
Flagship LLM最新上线by 通义千问 · 阿里云百炼

Qwen3.8 Max

通义千问 3.8 代旗舰：2.4 万亿参数 MoE，编程与办公能力全面跃升，可自主编程十数天交付完整项目。胜任法律、金融、设计等数百种专业任务，一次对话端到端交付生产级成果——直接调用 qwen3.8-max。

原生视觉理解贯穿规划、执行与验证全流程，支持超长文档与长视频深度解析。输入 ¥12/M、输出 ¥36/M、显式缓存命中低至 ¥1/M。

2.4T
MoE 总参数
1M
Token 上下文窗口
128K
最大输出
¥1/M
显式缓存命中价
Fast LLM最新上线by DeepSeek · 阿里云百炼

DeepSeek V4 Flash

高效轻量化 MoE 模型：总参 284B、激活 13B，原生支持百万超长上下文。推理速度快、延迟低、成本低，面向高并发对话、内容创作、基础 RAG 与批量任务——直接调用 deepseek-v4-flash。

支持混合思考、Function Calling、联网搜索与上下文缓存。输入 ¥1/M、输出 ¥2/M、缓存命中输入低至 ¥0.2/M。

284B
MoE 总参数
13B
单次激活参数
1M
Token 上下文窗口
¥0.2/M
缓存命中输入价
Flagship LLM最新上线by 月之暗面 Moonshot AI

Kimi K3

Kimi 迄今能力最强的旗舰模型：2.8 万亿参数，基于 KDA 混合线性注意力与注意力残差架构，原生视觉理解 + 深度思考，100 万 token 上下文。面向长程编程、知识工作与推理场景——OpenAI 与 Anthropic 协议均可直接调用 kimi-k3。

全球首个开源的 3 万亿级别模型。输入 ¥20/M、输出 ¥100/M、缓存命中低至 ¥2/M，与 Qwen、GLM、DeepSeek 共用同一个 API Key 与计费体系。

2.8T
万亿级参数
1M
Token 上下文窗口
1M
最大输出长度
¥2/M
缓存命中输入价
Speed LLM新品预览by 智谱AI Zhipu AI

GLM 5.2 Fast

GLM-5.2 的高速版本：能力对齐标准版，1M 超长上下文，输出 TPS 可达标准版的 1.5~2 倍。为实时对话、Agent 多轮调用与流式代码生成而生——直接调用 glm-5.2-fast-preview。

推理加速不减智商。输入 ¥16/M、输出 ¥56/M、缓存命中 ¥4/M，支持思考模式、函数调用与结构化输出。

1.5~2×
输出速度提升
1M
Token 上下文窗口
131K
最大输出长度
¥4/M
缓存命中输入价
Video Gen4K HDRby 火山方舟 Volcengine

Seedance 2.0

火山引擎最新一代旗舰视频生成模型：多模态参考生视频（图 + 视频 + 音频），4K HDR 10bit 输出，有声视频自动生成，支持首尾帧图生视频与文生视频。

时长 4-15 秒，4K / 1080P / 720P 多档分辨率，按秒计费、异步任务制，与文本模型共用同一个 API Key 与余额。

4K
HDR 10bit 输出
15s
单次最长时长
9图
多模态参考输入
有声
音画同步生成
Model access

Every request begins as a choice

Route requests across chat, reasoning, long-context, image and video models without multiplying accounts, keys and invoices. Live catalog data is temporarily unavailable; the preview below is clearly marked fallback content.

Claude Sonnet 5Anthropic via HiModels1Minput ¥13.6 / output ¥68 per 1M
Qwen3.8 MaxTongyi Qianwen1Minput ¥12 / output ¥36 per 1M
Kimi K3Moonshot AI1Minput ¥20 / output ¥100 per 1M
Qwen3.7 MaxTongyi Qianwen1Minput ¥12 / output ¥36 per 1M
GLM 5.2Zhipu AI1Minput ¥8 / output ¥28 per 1M
DeepSeek V4 FlashDeepSeek1Minput ¥1 / output ¥2 per 1M
DeepSeek V4 Flash 0731DeepSeek1Minput ¥1 / output ¥2 per 1M
DeepSeek V4 Pro 0813DeepSeek1Minput ¥9 / output ¥27 per 1M
Seedance 2.0Volcengine ArkAsync videofrom ¥0.44 / second
Platform

Designed for teams, not demos

Unified API

Use one OpenAI-compatible endpoint for chat, embeddings, image, video, Anthropic Messages and Responses API calls.

Billing Control

Pre-call balance checks, precise micro-cost ledger entries, API key-level usage and account-level transaction history.

Operational Guardrails

Rate limits, upload authorization, production-safe payment handling, provider routing and health monitoring foundations.

Developer Console

Create keys, test prompts, inspect usage, monitor latency and manage tickets without switching provider dashboards.

Developer workflow

Give the question a path to follow

  1. Create an account and generate a one-time API key
  2. Point your SDK to https://nexusflow.hk/v1
  3. Choose a model per request or test in Playground
  4. Track cost, latency, errors and rate limits in the console

Not all answers are equal.Choose the route before the reply.

Validate in Playground, then ship through the same model names, keys and billing path in production.

Start building