Skip to content

DeepSeek · Chat

DeepSeek v4 Flash 0731:us

DeepSeek 🇨🇳ChatDeepSeek family

Newer version: DeepSeek V4.1 Flash. Our catalogue has no release date for DeepSeek V4.1 Flash. We compared the version names in our catalogue.

From Nous Portal's listing:
DeepSeek V4 Flash is a hybrid-reasoning mixture-of-experts model tuned for high-throughput agentic work. This `:US` id is the Fireworks-hosted US SKU; `deepseek/deepseek-v4-flash-0731` is the Impala lane (overflow to OpenRouter). Thinking is on by default and can be disabled; control depth with the `reasoning` parameter.
Market median price
$0.5445 blended / 1M
Max context
1M
Listings
2
Providers
2

Evidence and sources

Released 31 Jul 2026Maker HQ: CN (according to DeepSeek's own website)
Sources: Alibaba Cloud Model Studio (DashScope) Multi-Region API, Nous Portal Inference Gateway data, llminfo researchPrimary data from Alibaba Cloud Model Studio (DashScope) Multi-Region API from Nous Portal Inference Gateway: description from llminfo research: release date

Advantages and trade-offs

Compared with 10 representative chat models
We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 6 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured output

Listings

 Nous Portaldeepseek/deepseek-v4-flash-0731:USSource: Nous Portal Inference Gateway data1M$0.363cache read $0.0115$1.089

1 listing without a price is hidden.

Benchmarks

No benchmark scores yet.

Also known as: deepseek-v4-flash-0731-us, deepseek/deepseek-v4-flash-0731:us

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works