# deepseek-v4-flash on Novita AI

> DeepSeek V4 Flash on Novita AI provides 1M context, reasoning, and JSON mode at $0.14 per million input tokens.

Source: https://tokenmojo.ai/models/novita-ai/deepseek-v4-flash

## Stats

- Quality: 63.6
- Speed: 35.9 tok/s
- Reliability: 70.4%
- Input price: $0.14 per 1M tokens
- Output price: $0.28 per 1M tokens
- Context window: 1,048,576 tokens
- Max output: 393,216 tokens
- Streaming: yes
- Tools: no
- Tasks covered: 4
- Total samples: 189

## Description

Hosted by Novita AI, this model offers a 1048576 token context window and 393216 max output tokens. Input rates are $0.1400 per million tokens and output rates are $0.2800 per million tokens, with support for reasoning and JSON mode.