PromptShuttle
Home

/

Models

/

deepseek-v4-flash

deepseek-v4-flash

Retired

Access deepseek-v4-flash through PromptShuttle's OpenAI-compatible API via DeepSeek. It offers a 1,000,000-token context window and up to 384,000 output tokens, priced at $0.44 per million input tokens and $1.32 per million output tokens.

Retired

Scheduled shutdown: September 10, 2026

Recommended replacement: deepseek-flash

Provider

DeepSeek

Context window

1,000,000 tokens

Max output

384,000 tokens

Input price

$0.44 / 1M

Output price

$1.32 / 1M

Input modalities

Text

Output modalities

Text

Structured output

No

Pricing

USD per 1,000,000 tokens.

InputOutputCached input
$ 0.44$ 1.32$ 0.014

Start building with deepseek-v4-flash

Point your OpenAI SDK at PromptShuttle and call deepseek-v4-flash with a single base-URL change — with cost tracking, model routing and agent orchestration built in.

Browse all models