PromptShuttle
Home

/

Models

/

deepseek-flash

deepseek-flash

Active

Access deepseek-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 $0.3 per million input tokens and $1.2 per million output tokens. It accepts image input for multimodal prompts.

Provider

DeepSeek

Context window

1,000,000 tokens

Max output

384,000 tokens

Input price

$0.3 / 1M

Output price

$1.2 / 1M

Input modalities

Text, Image

Output modalities

Text

Structured output

No

Pricing

USD per 1,000,000 tokens.

InputOutputCached input
$ 0.3$ 1.2$ 0.006

Start building with deepseek-flash

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

Browse all models