← Market
Chat · 深度求索
DeepSeek: DeepSeek V4 Flash 0423NEW
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Playground
Run this model with a pre-filled form — the same billed path as the API.
Conversation
✦
How can I help you today?
This demo page does not include the full memory features of the client. For the complete experience, please use the client or the CLI.
Rate card
| input | 22.5 credits 1M tokens |
| output | 45 credits 1M tokens |
Flat price per run — it does not change with duration.
Quick start
POST/v1/jobs/createTask
curl -X POST https://modelfold.ai/v1/jobs/createTask \
-H "Authorization: Bearer $MODELFOLD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-v4-flash","input":{"prompt":"..."}}'