One stable endpoint for multiple AI models

LLM API for GPT, Claude, and Gemini

One stable endpoint for multiple AI models with transparent token pricing, OpenAI-compatible APIs, and production-ready integration.

Open Console Client setup guide
System online
ONLINE
Available models
7
Today requests
583
Showing 7 models
Total requests: 640
GPT

gpt-5.4-mini

gpt-5.4-mini

GPT Token
Input / 1M
0.053 USD
Output / 1M
0.428 USD
Requests
401
Success
15.7%
Tokens
143.6K
Use now
GPT

gpt-5.3-codex

gpt-5.3-codex

GPT Token
Input / 1M
0.137 USD
Output / 1M
1.102 USD
Requests
124
Success
34.7%
Tokens
64.5K
Use now
Claude

claude-opus-4-6

claude-opus-4-6

Claude Token
Input / 1M
0.357 USD
Output / 1M
1.785 USD
Requests
63
Success
4.8%
Tokens
76
Use now
GPT

gpt-5.4

gpt-5.4

GPT Token
Input / 1M
0.178 USD
Output / 1M
1.428 USD
Requests
5
Success
40.0%
Tokens
20
Use now
Claude

claude-opus-4.6

claude-opus-4.6

Claude Token
Input / 1M
0.357 USD
Output / 1M
1.785 USD
Requests
4
Success
75.0%
Tokens
59
Use now
Claude

claude-sonnet-4-6

claude-sonnet-4-6

Claude Token
Input / 1M
0.214 USD
Output / 1M
1.071 USD
Requests
3
Success
33.3%
Tokens
31
Use now
Claude

claude-sonnet-4.6

claude-sonnet-4.6

Claude Token
Input / 1M
0.214 USD
Output / 1M
1.071 USD
Requests
1
Success
100.0%
Tokens
31
Use now

Per-model pricing

Model Input / 1M Output / 1M Per request Usage
gpt-5.4-mini
gpt-5.4-mini
 0.053 USD 0.428 USD 0 USD 401
gpt-5.3-codex
gpt-5.3-codex
 0.137 USD 1.102 USD 0 USD 124
claude-opus-4-6
claude-opus-4-6
 0.357 USD 1.785 USD 0 USD 63
gpt-5.4
gpt-5.4
 0.178 USD 1.428 USD 0 USD 5
claude-opus-4.6
claude-opus-4.6
 0.357 USD 1.785 USD 0 USD 4
claude-sonnet-4-6
claude-sonnet-4-6
 0.214 USD 1.071 USD 0 USD 3
claude-sonnet-4.6
claude-sonnet-4.6
 0.214 USD 1.071 USD 0 USD 1

Quickstart API

Use the shared /v1 base URL. The example below prefers a route from the selected model supported_paths. Actual requests are still forwarded to the upstream gateway, which makes the final payload validation decision. Pass max_tokens or max_output_tokens when you want explicit output budget control.

Base URL

https://ckey.vn/v1
Client setup guide

Quickstart API key

YOUR_API_KEY

Login to auto-fill your API key in examples.

Model
gpt-5.4-mini
Example route
https://ckey.vn/v1/chat/completions

cURL example

JavaScript example

Getting started

  • 1. Add balance to your account.
  • 2. Get your API key in API AI Console.
  • 3. Call a route that the model actually supports, such as /v1/chat/completions, /v1/responses, /v1/messages, or /v1/models.
  • 4. Monitor input/output tokens and spend in Console.