# DeepSeek V4 Flash

> DeepSeek V4 Flash — fast, cheapest V4, thinking + non-thinking modes.

Canonical: https://routemux.com/deepseek/deepseek-v4-flash
Provider: DeepSeek

## Key facts

| Field | Value |
| --- | --- |
| Model ID | deepseek/deepseek-v4-flash |
| Official model ID | deepseek-v4-flash |
| Context window | 1M |
| Max output | 393K |
| Input modalities | text |
| Output modalities | text |
| Capabilities | Reasoning, Tool Calling, Coding, Cache |
| Upstream release | 2026-07-31 |
| Availability | available |

## Pricing

- RouteMux input: $0.41958 per 1M tokens
- RouteMux output: $1.258741 per 1M tokens
- Official input: $0.41958 per 1M tokens
- Official output: $1.258741 per 1M tokens
- Cache read: $0.013986 per 1M tokens
- Official price source: deepseek_official_2026-08-17_peak_fx7.15, verified 2026-06-08

Billing is prepaid wallet, charged per successful request only.

## API access

Base URL: https://api.routemux.com

Supported protocols:

- openai_chat
- openai_responses
- anthropic_messages

## Other variants in this family

- DeepSeek V4 Pro (`deepseek/deepseek-v4-pro`)
- DeepSeek V4 Flash Vision (exp) (`deepseek/deepseek-v4-flash-vision-exp`)