DeepSeek V4 Flash 0731

deepseek-v4-flash-0731 · DeepSeek

DeepSeek-V4-Flash-0731(deepseek-v4-flash-0731) is an open-source MoE large language model developed by the Chinese AI company DeepSeek, with support for a million-token context window. It is designed for coding, complex reasoning, tool use, agentic workflows, and long-document processing. Its advantages include strong performance with fewer active parameters and improved efficiency through DSpark speculative decoding. Compared with DeepSeek V4-Flash Preview, it offers significantly stronger coding and agent capabilities, while outperforming DeepSeek V4-Pro Preview on several benchmarks with fewer active parameters.

API Pricing

Input$0.142 / 1M tokens
Output$0.284 / 1M tokens
Cache read$0.028 / 1M tokens

Specifications

Context1M tokens
Modalitiestext
CapabilitiesThinking, Streaming, Tool calling, Web search, Structured outputs, Prompt caching
Endpointschat_completions, claude_api

Frequently asked questions

What is DeepSeek V4 Flash 0731?

DeepSeek-V4-Flash-0731(deepseek-v4-flash-0731) is an open-source MoE large language model developed by the Chinese AI company DeepSeek, with support for a million-token context window. It is designed for coding, complex reasoning, tool use, agentic workflows, and long-document processing. Its advantages include strong performance with fewer active parameters and improved efficiency through DSpark speculative decoding. Compared with DeepSeek V4-Flash Preview, it offers significantly stronger coding and agent capabilities, while outperforming DeepSeek V4-Pro Preview on several benchmarks with fewer active parameters.

What is the context length of DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731 has a 1,000,000 token context window.

How much does DeepSeek V4 Flash 0731 cost?

On AIHubMix, DeepSeek V4 Flash 0731 costs $0.142 per million input tokens and $0.284 per million output tokens. Cached input reads are billed at $0.028 per million tokens.

What modalities does DeepSeek V4 Flash 0731 support?

DeepSeek V4 Flash 0731 accepts text input.

What capabilities does DeepSeek V4 Flash 0731 support?

DeepSeek V4 Flash 0731 supports tool calling, function calling, structured outputs and thinking. Per-protocol parameter support is listed in the capability table on this page.

How do I call DeepSeek V4 Flash 0731 via API?

DeepSeek V4 Flash 0731 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to deepseek-v4-flash-0731 — no other code changes needed.

Who created DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731 is developed by DeepSeek. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

When was DeepSeek V4 Flash 0731 released?

DeepSeek V4 Flash 0731 was released on July 31, 2026 by DeepSeek.

More models from DeepSeek

See all DeepSeek models →

DeepSeek V4 Flash Vision Exp

by DeepSeek

DeepSeek’s officially released new multimodal visual-understanding model…

$0.142/1M in · $0.284/1M out
1,000,000 tokens context

DeepSeek V4 Pro 0813

by DeepSeek

DeepSeek V4 Pro 0813 is DeepSeek’s high-performance general-purpose reasoning and agent…

$0.692/1M in · $2.075/1M out
1,000,000 tokens context

DeepSeek V4 Flash 0731 Fast

by DeepSeek

DeepSeek V4 Flash 0731 Fast is a high-speed deployment of DeepSeek’s agentic model…

$0.28/1M in · $0.56/1M out
1,000,000 tokens context

DeepSeek V4 Flash

by DeepSeek

(This model currently points to the older 0423 version; if you need to request the latest…

$0.142/1M in · $0.284/1M out
1,000,000 tokens context

DeepSeek V4 Pro

by DeepSeek

(This model currently points to the older 0423 version; if you need to request the latest…

$1.69/1M in · $3.38/1M out
1,000,000 tokens context

DeepSeek V3.2

by DeepSeek

DeepSeek-V3.2 is an efficient large language model equipped with DeepSeek Sparse…

$0.302/1M in · $0.453/1M out
128,000 tokens context

Use DeepSeek V4 Flash 0731 via the AIHubMix unified API — one interface for every major LLM.