DeepSeek-V4-Flash

DeepSeek-V4-Flash is a Mixture-of-Experts language model developed by DeepSeek as part of the broader DeepSeek-V4 collection. It carries 284B total parameters with only 13B activated per token, a configuration that aims to deliver strong capability while keeping inference costs and latency manageable. The model is positioned as an efficiency-optimized variant of the V4 line, designed for fast inference and high-throughput workloads without sacrificing core reasoning quality. Its open weights are published under the deepseek-ai organization on Hugging Face, making it accessible for self-hosting, fine-tuning, and research use.

DeepSeek-V4-Flash supports a one-the cataloged API limit and incorporates hybrid attention to handle long inputs more efficiently, which makes it well suited for coding assistants, conversational chat systems, and agent workflows where long documents and sustained responsiveness matter. Configurable reasoning effort is available, with both high and xhigh settings supported and xhigh mapping to maximum reasoning depth. On standardized evaluations listed through OpenRouter, the model posts an Intelligence Index of 24.2, a Coding Index of 56.2, and an Agentic Index of 22.2 under max-effort reasoning, indicating a balanced profile rather than a single-axis specialist.

Azuredeepseek-v4-flashdeepseek-flash

Open provider page Provider docs

Quick Info

Provider: Azure
Model key: deepseek-v4-flash
Release date: Apr 24, 2026
Last updated: Apr 24, 2026
Knowledge cutoff: 2025-05
AI SDK package: @ai-sdk/openai-compatible
Input modalities
Output modalities
Capabilities

Cost

Input token cost: $0.19
Output token cost: $0.51

Limits

Output tokens: 384,000 tokens
Context window: 1,000,000 tokens

Transparent token rates

Compare DeepSeek-V4-Flash pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about DeepSeek-V4-Flash

InferX

Coverage

The AI Free API guide, dated August 26, 2026, maps DeepSeek's current official API surface and assigns the `deepseek-v4-flash` text route to the DeepSeek-V4-Flash-0731 build, with `deepseek-v4-pro` mapped to DeepSeek-V4-Pro-0813 and `deepseek-v4-flash-vision-exp` released on the API platform on August 21 as an experime The specification section states that all three current routes share a 1-million-token context window and a 384,000-token maximum output, with JSON output, tool calls, Responses API support, and an Anthropic-compatible interface listed for each, while FIM completion is limited (excerpt cuts off). The page also notes th

InferX

CoverageBenchmark

The BenchLM profile tracks the most likely exact variant behind InferX's `deepseek-v4-flash` key: DeepSeek V4 Flash 0731, released July 31, 2026, with the API model ID `deepseek-v4-flash`, a 1M-token context window, text input and output modalities, and reasoning support. It lists a published input price of $0.14 and o BenchLM flags the model as tracked but not yet publicly ranked, noting no category has enough eligible evidence for a comparative rank and that provisional rows remain visible separately from verified ones. Maximum output length, knowledge cutoff, and several other spec fields are marked "Not sourced yet," so those att

Azure

CoverageBenchmark

DeepSeek shipped the official DeepSeek-V4-Flash-0731 release on 31 July 2026, superseding the April preview with the same architecture and initial price. According to the article's source material, the model is a Mixture-of-Experts design in the open-weight V4 family with 284 billion total parameters and 13 billion act The piece details efficiency gains at long context: at one million tokens V4-Flash is said to use roughly 10% of the single-token inference FLOPs and 7% of the KV cache of DeepSeek V3.2, extending the same family of improvements credited to V4-Pro. Distribution is via Hugging Face under the MIT License, the DeepSeek AP