DeepSeekDeepSeek V4 Flash
DeepSeek develops the DeepSeek V 4 Flash, a chat model that excels at handling long contexts with its support for up to 1,048,576 tokens, making it well-suited for tasks requiring extensive contextual understanding. Notably, it features a hybrid attention architecture combining Compressed Sparse Attention and Heavily Compressed Attention, which enhances efficiency in long-context settings.
Input
Output
Context
1M
Max Output
384K
Parameters
290.9B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Served variants
The same model in other encodings or serving configurations. Requesting deepseek-v4-flash lets routing pick among them; the ids below pin one build.
deepseek-v4-flash:fp8quantized
Benchmarks
Resources & Links
Estimated GPU requirements for DeepSeek V4 Flash
Estimates based on INT8 quantization at up to 32K context. A count above one assumes tensor parallelism across the cards. Actual requirements vary by framework and configuration.
More models by DeepSeek
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about DeepSeek V4 Flash
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
DeepSeek V4 Flash advertises a context window of 1,048,576 tokens, with a maximum output of 384,000 tokens in a single response. The figure is the creator's published maximum; a given provider may serve less, and the gateway routes on what each provider actually serves.
Yes. DeepSeek V4 Flash is an open-weight model released under the MIT license, so the weights can be downloaded and self-hosted within that license's terms.
DeepSeek V4 Flash accepts Text and produces Text. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
DeepSeek V4 Flash has published results from Artificial Analysis, shown by suite in the benchmarks card above exactly as the publisher reported them. Scores are not combined across suites, and a suite that has not measured DeepSeek V4 Flash is shown as not available rather than estimated.
Yes. DeepSeek V4 Flash is served on the managed pool through the OpenAI-compatible endpoint as deepseek-v4-flash, pinned by name or chosen by routing when it is the best fit for a request. The Try in Playground button opens it directly.
About 286.1 GB at INT8 for the weights and a default context, from the catalog's 290.9B parameter count; FP16 needs roughly twice that, and long contexts or many concurrent requests add KV cache on top. The GPU section on this page lists cards that hold it, and the capacity planner sizes it for your context length and traffic.
Fields collected from public registries, provider APIs and benchmark publishers, each tagged with its source.
Last updated: Nov 6, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start on the free plan with 5,000 requests a month, no card required.