Admin Panel

View your account balance, API Key, models, and latest announcements.

Account Balance

Account Balance
API Tier

New Models

View All Models →
DeepSeek

DeepSeek V4 Flash Vision Exp

DeepSeek V4 Flash Vision Exp is the experimental vision variant of V4 Flash. Text capability matches the stable V4 Flash, and images are billed as token-equivalent. Supports 1M context and 384K max output.

ctx1.0Mmax384K
In¥1.50Out¥4.50
InOut
2026-08-21
AlibabaCloud

DeepSeek V4 Pro 0813 (Alibaba Cloud)

DeepSeek V4 Pro 0813 (official weights) hosted on Alibaba Cloud Model Studio.

ctx1.0Mmax384K
In$0.636Out$1.908
InOut
2026-08-16
TencentCloud

GLM-5.3

Zhipu AI's latest flagship model, served via Tencent Cloud, with 1M context window and configurable thinking depth.

ctx1.0Mmax128K
In¥7.20Out¥25.20
InOut
2026-08-1410% off
AlibabaCloud

DeepSeek V4 Pro (Alibaba Cloud)

DeepSeek V4 Pro hybrid-thinking model hosted on Alibaba Cloud Model Studio.

ctx1.0Mmax384K
In$0.99Out$1.9806
InOut
2026-08-14
AlibabaCloud

DeepSeek V4 Flash (Alibaba Cloud)

DeepSeek V4 Flash hybrid-thinking model hosted on Alibaba Cloud Model Studio.

ctx1.0Mmax384K
In$0.1104Out$0.22
InOut
2026-08-14
AlibabaCloud

DeepSeek V4 Flash 0731 (Alibaba Cloud)

DeepSeek V4 Flash 0731 weight snapshot hosted on Alibaba Cloud Model Studio.

ctx1.0Mmax384K
In$0.1104Out$0.22
InOut
2026-08-14
AlibabaCloud

Kimi K2.7 Code (Alibaba Cloud)

Moonshot Kimi K2.7 Code hosted on Alibaba Cloud Model Studio.

ctx1.0Mmax66K
In$0.71512Out$2.97048
InOut
2026-08-14
AlibabaCloud

Kimi K2.5 (Alibaba Cloud)

Moonshot Kimi K2.5 hosted on Alibaba Cloud Model Studio (DE/JP regions).

ctx262Kmax262K
In$0.4592Out$2.4088
InOut
2026-08-14
AlibabaCloud

GLM-5.2 (Alibaba Cloud)

Zhipu GLM-5.2 hosted on Alibaba Cloud Model Studio.

ctx1.0Mmax66K
In$0.66Out$2.3106
InOut
2026-08-14
AlibabaCloud

GLM-5.1 (Alibaba Cloud)

Zhipu GLM-5.1 hosted on Alibaba Cloud Model Studio.

ctx200Kmax128K
In$0.66Out$2.6408
InOut
2026-08-14
DeepSeek

DeepSeek V4 Pro

DeepSeek V4 Pro is the higher-capability hybrid-thinking model in the V4 family. It supports both non-thinking and thinking modes, with 1M context and 384K max output.

ctx1.0Mmax384K
In¥4.50Out¥13.50
InOut
2026-08-13
Google

Gemini 3.7 Flash

Google's most intelligent workhorse model for coding and agents, with substantial gains over 3.6 Flash in software engineering (DeepSWE v1.1 65.3%), web development (WebDev Arena Elo 1588), and knowledge-dense document processing (GDP.pdf 34.0%), at half the introductory cost.

ctx1.0Mmax64K
In$0.675Out$3.375
InOut
2026-08-1310% off

Platform Features

API Access

Unified OpenAI-compatible API

Model Library

Multiple AI providers available

Usage Analysis

Detailed consumption tracking

Configure Code Agent

Run 'npx omgvibe' to set up Code Agent access

Announcements

Loading...