nexusflow
Online

Models Overview

nexusflow brings together industry-leading large language models and offers public endpoints such as OpenAI, Anthropic Messages, Responses API, Embeddings, Image Generations, and Tasks based on each model's capabilities. Choose the model that best fits your needs.

Protocols Overview

Model Families

Qwen Series

Alibaba Cloud

Alibaba Cloud's in-house models. Currently featuring the Qwen3.6 and Qwen3.5 series, with strong language understanding and ultra-long context support

Qwen3.7 MaxQwen3.6 Max PreviewQwen3.6 PlusQwen3.5 Omni PlusQwen3.5 Omni FlashQwen3.5 PlusQwen3.5 Flash

Claude Series

Differentiated
Anthropic

Anthropic flagship models with 1M-token context and excellent reasoning and coding. Called via the /v1/messages compatible endpoint

Claude Opus 4.7Claude Sonnet 4.6Claude Haiku 4.5

DeepSeek Series

Cost-effective
DeepSeek

High-performance reasoning and general-purpose models with strong coding ability, ideal for complex tasks and high-concurrency scenarios

DeepSeek V4 ProDeepSeek V4 FlashDeepSeek R1DeepSeek V3.2

Zhipu GLM Series

Zhipu AI

A leading large language model with comprehensive general capabilities and long-context support

GLM 5.2GLM 5.1GLM 5GLM 4.7

Kimi Series

Moonshot AI

Moonshot AI's models, with powerful long-text understanding and reasoning

Kimi K2.6Kimi K2.5

MiniMax Series

MiniMax

MiniMax models, ideal for general conversation and content creation

MiniMax M2.5MiniMax M2.1

HappyHorse Feature

New
Alibaba

The top-ranked video generation model on VBench, supporting text-to-video and image-to-video, integrated through nexusflow

happyhorse-1.0-t2vhappyhorse-1.0-i2vhappyhorse-1.0-r2v

PixVerse Video Models

PixVerse

Professional video generation models supporting text-to-video, image-to-video, first-and-last-frame, and reference-to-video

PixVerse V6

Price Comparison

Prices are in USD per 1M tokens

ModelContextInput PriceOutput PricePositioning
qwen3.7-max1M$12$36Flagship
qwen3.6-max-preview256K$9$54Flagship
qwen3.6-plus1M$2$12Balanced
qwen3.5-plus1M$0.8$4.8Balanced
qwen3.5-flash1M$0.2$2Ultra-fast
claude-opus-4-71M≈$34≈$170Flagship
claude-sonnet-4-61M≈$20.4≈$102Balanced
claude-haiku-4-5200K≈$6.8≈$34High-speed
deepseek-v4-pro1M$12$24Reasoning Flagship
deepseek-v4-flash1M$1$2High-speed
deepseek-r1128K$4$16Reasoning
deepseek-v3.2128K$2$3General
glm-5.21M$8$28Long-horizon Flagship
glm-5.1198K$6$24Flagship
glm-5198K$4$18Balanced
kimi-k2.6256K$6.5$27Reasoning
kimi-k2.5256K$4$21Balanced
MiniMax-M2.5192K$2.1$8.4Balanced

Selection Guide

Complex reasoning & coding
Qwen3 Max
Well-balanced flagship capabilities, ideal for complex reasoning, code generation, and system tasks
Everyday chat & creation
Qwen3.5 Plus
Balances performance and cost, ideal for most online chat and business scenarios
Long-document processing
Qwen3.5 Series
Excellent language understanding and generation, with ultra-long text support
Cost-effective needs
DeepSeek V3
Open-source model, affordable pricing, and outstanding coding ability

Not sure which model to choose?

Try each model for free in the Playground and find the best fit for you.

Open Playground