Question 1

What is DeepSeek Flash?

Accepted Answer

DeepSeek's Flash model, now served by DeepSeek-V4.1-Flash-1017, with thinking (default) and non-thinking modes.

Question 2

How much does DeepSeek Flash cost?

Accepted Answer

From $0.3 per million input tokens and $1.2 per million output tokens, at the provider's price. Credits add a platform fee when you top up; with your own provider keys there is no fee.

Question 3

Which providers serve DeepSeek Flash?

Accepted Answer

DeepSeek. DigitSpace sends each request to whichever of them is healthy and cheapest, and fails over automatically.

Question 4

How long a prompt can DeepSeek Flash take?

Accepted Answer

Up to 1,000,000 tokens of context, with up to 384,000 tokens of output.

Question 5

How do I call DeepSeek Flash?

Accepted Answer

Use any OpenAI-compatible SDK with the base URL https://api.digitspace.ai/v1 and set model to "deepseek-flash". To pin a provider, use "provider/deepseek-flash".

DeepSeek Flash

Providers

What users think

Questions

More from deepseek