DeepSeek V4 Flash Released: 284B Parameter MoE Model with 1M Context Window at $0.14 per Million Tokens

DeepSeek has released V4 Flash, a Mixture-of-Experts model with 284B total parameters and 13B activated parameters per request. The model supports a 1,048,576-token context window and is priced at $0.14 per million input tokens and $0.28 per million output tokens.

Model Architecture and Capabilities

DeepSeek V4 Flash uses a sparse Mixture-of-Experts architecture that activates only 13B of its 284B total parameters for each inference request. According to DeepSeek, the model includes hybrid attention mechanisms designed for efficient long-context processing.

The model supports configurable reasoning modes, allowing it to show step-by-step thinking processes. DeepSeek claims the model maintains strong performance on reasoning and coding tasks despite its efficiency optimizations.

Pricing and Availability

The model is available through OpenRouter at:

• Input: $0.14 per million tokens
• Output: $0.28 per million tokens

These prices position V4 Flash as a cost-effective option for high-throughput workloads compared to larger models with similar context windows.

Target Use Cases

DeepSeek designed V4 Flash for applications requiring fast inference and high throughput, including:

• Coding assistants
• Chat systems
• Agent workflows

The model's sparse activation pattern (activating only 4.6% of total parameters) enables faster inference speeds while attempting to preserve model quality.

Technical Details

Release date: April 24, 2026 (as listed on OpenRouter) Context window: 1,048,576 tokens Architecture: Sparse Mixture-of-Experts Reasoning support: Configurable reasoning modes with exposed thinking processes

What This Means

DeepSeek V4 Flash continues the trend of using sparse MoE architectures to deliver capable models at lower inference costs. The 13B activated parameter count per request allows for faster processing than dense models of similar capability, while the 1M token context window matches the extended context offerings from competitors like Anthropic and Google. The $0.14/$0.28 per million token pricing undercuts many competing models with similar context lengths, potentially making it attractive for high-volume production deployments where cost per token matters more than absolute peak performance.