deepseek-v4-pro on 4AICode

Use model ID deepseek-v4-pro (DeepSeek) through the 4AICode relay. Prices below come from the repository snapshot of the public model-rates API; the console remains the source of truth if rates change.

Model ID

deepseek-v4-pro

Pricing

Meter	4AICode (USD / 1M tokens)	Official reference
Input	$1.32	$1.32
Output	$3.96	$3.96
Cache read	$0.044	—
Cache write (5m)	$1.32	—
Cache write (1h)	$1.32	—

Snapshot pricing only. Always confirm the live rate in the dashboard before budgeting.

Compatibility

Vendor / channel: DeepSeek / codex
Billing mode: per token
Suggested endpoints: chat_completions
Capabilities: Streaming

Example request

POST /v1/chat/completions HTTP/1.1
Host: relay.4aicode.com
Authorization: Bearer sk-4ai-xxxxxxxxxxxxxxxx
content-type: application/json

{
  "model": "deepseek-v4-pro",
  "stream": true,
  "messages": [
    { "role": "user", "content": "Write a hello world in Go." }
  ]
}

Next steps

Create a token in Token management.
Point your client base_url to https://relay.4aicode.com (or https://relay.4aicode.net for mainland routing).
Set model to deepseek-v4-pro.