ANNOUNCEMENT
PAYMENTSAutomated VietQR & USDT Gateway: Instant 24/7 account top-ups with competitive commercial FX rates. Top Up Now → •
GATEWAYHigh-Performance OpenAI-Compatible API: Low latency, 99.99% SLA uptime, unified endpoint integration. Read Docs → •
CATALOGProduction-ready frontier model cluster: Claude 3.7 Sonnet, DeepSeek V3/R1 & GPT-4o. View Pricing → •
ENTERPRISEVolume Licensing & Technical Support: Direct 24/7 engineering assistance for corporate clients. Contact Team ↗ •
GIA HUY NEXUS
Select Language8
Detected IP Location: US
AUTO
VN
Tiếng ViệtVietnamese
VI
US
English
EN
CN
中文 (简体)Chinese
ZH
IN
हिन्दीHindi
HI
ID
Bahasa IndonesiaIndonesian
ID
KH
ភាសាខ្មែរKhmer
KM
JP
日本語Japanese
JA
LA
ພາສາລາວLao
LO
Auto-Saved PreferenceACTIVE

Your language preference is automatically saved

Sign InSign Up

Universal AI Gateway Search

Instantly find 100+ frontier AI models, real-time token pricing, API documentation, Cursor IDE setups, and enterprise billing.

Trending: Lập trình Code test ' encodeURIComponent(q) test'|| $ne != null test'|| ''==' test'$regex': '.*' test'$where': '1==1' test'$ne':null test'$ne test'|| 1==1 ||'
All Results (21) AI Models (16) Docs & Guides (5)
About 21 results (2.1 ms)
AI Models

Frontier AI Models

View all 100+ models →
Xiaomi
Xiaomi
1,000k ctx

Xiaomi: MiMo-V2.5

mimo-v2.5

High-performance Xiaomi: MiMo-V2.5 model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
127 ₫$0.0049
Completion / 1M
127 ₫$0.0049
Muse
Muse
256k ctx

Muse: Spark 1.2

muse-spark-1.2

High-performance Muse: Spark 1.2 model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
127 ₫$0.0049
Completion / 1M
127 ₫$0.0049
Xiaomi
Xiaomi
1,000k ctx

Xiaomi: MiMo-V2.5 (Cursor)

mimo-v2.5-cursor

High-performance Xiaomi: MiMo-V2.5 (Cursor) model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
127 ₫$0.0049
Completion / 1M
127 ₫$0.0049
Nvidia
Nvidia
1,000k ctx

NVIDIA: Nemotron 3 Ultra

nemotron-3-ultra

High-performance NVIDIA: Nemotron 3 Ultra model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
127 ₫$0.0049
Completion / 1M
127 ₫$0.0049
Muse
Muse
256k ctx

Muse: Spark 1.2 (Cursor)

muse-spark-1.2-cursor

High-performance Muse: Spark 1.2 (Cursor) model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
127 ₫$0.0049
Completion / 1M
127 ₫$0.0049
Nvidia
Nvidia
1,000k ctx

NVIDIA: Nemotron 3.5 Lightning

nemotron-3.5-lightning

High-performance NVIDIA: Nemotron 3.5 Lightning model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
127 ₫$0.0049
Completion / 1M
127 ₫$0.0049
Nvidia
Nvidia
1,000k ctx

NVIDIA: Nemotron 3 Ultra (Cursor)

nemotron-3-ultra-cursor

High-performance NVIDIA: Nemotron 3 Ultra (Cursor) model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
127 ₫$0.0049
Completion / 1M
127 ₫$0.0049
Nvidia
Nvidia
1,000k ctx

NVIDIA: Nemotron 3.5 Lightning (Cursor)

nemotron-3.5-lightning-cursor

High-performance NVIDIA: Nemotron 3.5 Lightning (Cursor) model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
127 ₫$0.0049
Completion / 1M
127 ₫$0.0049
Qwen
Qwen
1,000k ctx

Qwen: Qwen3.7 Plus

qwen3.7-plus

High-performance Qwen: Qwen3.7 Plus model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
253 ₫$0.0098
Completion / 1M
253 ₫$0.0098
DeepSeek
DeepSeek
1,000k ctx

DeepSeek: DeepSeek V4 Flash

deepseek-v4-flash

High-performance DeepSeek: DeepSeek V4 Flash model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
253 ₫$0.0098
Completion / 1M
253 ₫$0.0098
Qwen
Qwen
1,000k ctx

Qwen: Qwen3.7 Plus (Cursor)

qwen3.7-plus-cursor

High-performance Qwen: Qwen3.7 Plus (Cursor) model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
253 ₫$0.0098
Completion / 1M
253 ₫$0.0098
DeepSeek
DeepSeek
1,000k ctx

DeepSeek: DeepSeek V4 Flash (Cursor)

deepseek-v4-flash-cursor

High-performance DeepSeek: DeepSeek V4 Flash (Cursor) model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
253 ₫$0.0098
Completion / 1M
253 ₫$0.0098
Qwen
Qwen
1,000k ctx

Qwen: Qwen3.7 Max

qwen3.7-max

High-performance Qwen: Qwen3.7 Max model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
504 ₫$0.0195
Completion / 1M
504 ₫$0.0195
Qwen
Qwen
1,000k ctx

Qwen: Qwen3.7 Max (Cursor)

qwen3.7-max-cursor

High-performance Qwen: Qwen3.7 Max (Cursor) model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
504 ₫$0.0195
Completion / 1M
504 ₫$0.0195
OpenAI
OpenAI
1,000k ctx

OpenAI: GPT-5.6 Luna

gpt-5.6-luna

High-performance OpenAI: GPT-5.6 Luna model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
553 ₫$0.0214
Completion / 1M
553 ₫$0.0214
OpenAI
OpenAI
1,000k ctx

OpenAI: GPT-5.6 Luna (Cursor)

gpt-5.6-luna-cursor

High-performance OpenAI: GPT-5.6 Luna (Cursor) model optimized for coding, deep reasoning, and enterprise AI workflows.

Prompt / 1M
553 ₫$0.0214
Completion / 1M
553 ₫$0.0214
Documentation

API Guides, IDE Setups & Policies

Browse full docs →

Endpoint POST /v1/chat/completions supports streaming, reasoning tokens, JSON mode, and function calling for 100+ models.

Step-by-step setup for Cursor IDE, Cline, Roo Code to program with Claude 3.7 Sonnet, DeepSeek R1 & GPT-4o.

Instant 3-second top-up processing via Vietnamese banking VietQR and USDT (TRC20/BEP20).

Enterprise 99.99% SLA uptime, dedicated RPM/TPM rate limits, commercial contracts, and compliant tax invoices.

Chat and test 100+ frontier models live in browser before integrating into production applications.