Skip to main content

DeepSeek-V4-Flash

B.AI model routing

B.AI will progressively route requests made using the DeepSeek-V4-Flash and DeepSeek-V4-Flash-Vision-Exp model names to DeepSeek-V4.1-Flash. After routing takes effect, these requests are billed at the applicable DeepSeek-V4.1-Flash price.

Overview​

DeepSeek-V4-Flash is DeepSeek's high-efficiency open-source language model, released alongside V4-Pro on April 24, 2026 under the MIT License. With 284 billion total parameters and only 13 billion active parameters, it delivers performance within striking distance of V4-Pro at roughly one-third of the standard input and output price, making it one of the most cost-effective models available.

DeepSeek-V4-Flash

The DeepSeek-V4-Flash 50% offer takes effect at 17:00 on September 3, 2026 (UTC+8).

From the effective time, eligible DeepSeek-V4-Flash API usage is billed at 50% of the standard price for the applicable period. The discounted price changes in step with DeepSeek's Off-Peak and Peak pricing periods and remains at 50% in either period.

The pricing table below continues to show standard reference prices. Actual settlement and final billing are subject to the platform display.

Key Features​

  • Ultra-Efficient Architecture: 284B total parameters with just 13B activated per forward pass, resulting in a compact 160GB download that runs on significantly less hardware than frontier models while maintaining strong performance.
  • 1M-Token Context Window: Shares the same 1-million-token context and 384K max output as V4-Pro, powered by the same CSA/HCA hybrid attention mechanism for efficient long-context inference.
  • Near-Pro Performance at Lower Cost: Scores 79.0% on SWE-bench Verified, only 1.6 percentage points behind V4-Pro's 80.6%, while its standard reference price is 0.44/1.32 Credits per input/output token.
  • Flash-Max Reasoning Mode: When given a larger thinking budget (384K+ context), V4-Flash-Max achieves comparable reasoning performance to V4-Pro, closing the gap on complex tasks.

Best Use Cases​

  • High-Volume API Workloads: With a standard reference input price of 0.44 Credits per token, Flash is ideal for applications that process large volumes of text where cost per query matters more than marginal accuracy gains.
  • Self-Hosted Deployments: The 160GB model size and 13B active parameters make it feasible for on-premise or single-node GPU deployments, unlike larger frontier models.
  • Agentic Tool-Use Pipelines: Strong tool-calling and coding capabilities paired with low latency make it well-suited for multi-step agent workflows where many LLM calls are chained together.

Capabilities and Limitations​

CapabilityDescription
ReasoningCompetitive with Claude Sonnet 4.6 level intelligence (47 on Artificial Analysis Index)
Coding79.0% SWE-bench Verified; 64.4 average across coding benchmarks
MultimodalText-only; no image, audio, or video support
Response SpeedOptimized for high throughput with 13B active parameters and efficient attention
Context Window1,000,000 tokens
Max Output384,000 tokens
Tool UseFunction calling support; strong agentic task performance
MultilingualBroad multilingual support; strongest in English and Chinese

Known Limitations​

  • Text-only, with no multimodal capabilities.
  • Falls behind V4-Pro and frontier closed-source models on pure knowledge tasks and the most complex agentic workflows due to smaller parameter scale.
  • May require Flash-Max mode (larger thinking budget) to match Pro-level reasoning, increasing latency and cost for complex tasks.

Standard Pricing​

The token prices below are shown in USD per 1 million tokens; web search is billed in USD per use.

Billing PeriodInput
(USD / 1M Tokens)
Cache Write
(USD / 1M Tokens)
Cache Read
(USD / 1M Tokens)
Output
(USD / 1M Tokens)
Web Search
(USD / use)
Billing Notes
Off-Peak$0.15$0.15$0.003$0.60-Cache Write: 1x input; Cache Read: 0.02x input
Peak$0.30$0.30$0.006$1.20-Cache Write: 1x input; Cache Read: 0.02x input

Credits settlement: B.AI converts charges at 1 USD = 1,000,000 Credits and deducts Credits from the account balance.

Pricing note

The standard reference prices above take effect at 12:00 on September 10, 2026 (Beijing Time, UTC+8). The table shows the time-based standard reference price for DeepSeek-V4-Flash. Off-Peak prices are half of Peak prices. In Beijing Time (UTC+8), 09:00-12:00 and 14:00-18:00, Monday through Friday (excluding Chinese public holidays), are Peak periods; all other times, including weekends and Chinese public holidays, are Off-Peak periods. DeepSeek-V4-Flash usage in B.AI Chat is billed at Off-Peak rates. From 17:00 on September 3, 2026 (UTC+8), eligible API usage is billed at 50% of the standard price for the applicable period.

Model prices in the documentation are based on the model providers' official list prices and serve as B.AI standard reference prices. B.AI may offer discounts or limited-time promotions on this basis; offer details are shown in Promotions and Pricing Updates and the website's discount groups. Applicable prices, offer terms, and final charges are subject to the platform display and actual billing records.