Models/nvidia/deepseek-ai/deepseek-v4-flash
nvidia

deepseek-ai/deepseek-v4-flash

1M context$0.13/M input$0.25/M output
nvidia/deepseek-ai/deepseek-v4-flash

Description

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...

Quick Start

curl https://router.tangle.tools/v1/chat/completions \
  -H "Authorization: Bearer $TANGLE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/deepseek-ai/deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Modalities

Input: TextOutput: Text

Pricing

Input$0.13/M
Output$0.25/M
Context1M tokens

Model Info

Providernvidia
IDnvidia/deepseek-ai/deepseek-v4-flash