DeepSeek V4 Pro - GENGEN API

Higher-capability DeepSeek text generation model for long-context chat completions.

Model ID

deepseek-v4-pro-260425

Pass this exact public ID in the top-level model field. Do not substitute an upstream provider alias.

Property	Value
Provider	`byteplus-modelark`
Modality	`reasoning`
Processing	`Synchronous response`
Endpoint	`/api/gengen/v1/chat/completions`
Rate limit	`15K`
Context window	`1024K`
Max input tokens	`1024K`
Max output tokens	`384K`
Max reasoning tokens	`384K`
Token rate limit	`1500K`

Availability and final customer prices can change. Check the Dashboard model catalog before production use.

See the API reference overview for authentication, request conventions, and response schemas.