DeepSeek: DeepSeek V4 Flash
Analysis Summary
DeepSeek V4 Flash is the lighter, faster sibling of V4 Pro, with an intelligence index of 40.3 and a coding index of 56.2. It supports tool use, function calling, and a 1M token context window, and its instruction-following score of 0.792 is among the highest in the database, making it particularly reliable for structured output and content workflows.
For businesses, it is well-suited to high-volume coding assistance, SEO content pipelines, agentic automation, and long-document processing where cost efficiency matters. The agentic index of 65.3 confirms reliable multi-step tool use. Its text-only modality is the main limitation for teams needing vision capabilities.
At $0.098 input and $0.196 output per million tokens, it offers exceptional price-performance for its capability level. Teams running large-scale inference workloads will find it one of the most cost-effective options at this intelligence tier. A -4 point regional accessibility adjustment applies.
Assessed June 30, 2026
Editorial notes
DeepSeek V4 Flash pairs strong reasoning and coding capability with a 1M token context and aggressive pricing at $0.098 input, making it one of the best value options in its performance tier.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How DeepSeek: DeepSeek V4 Flash compares
DeepSeek: DeepSeek V4 Flash ranks #26 of 385 AI models we track for overall intelligence, #23 of 129 for coding, #39 of 293 for agentic tasks. Its 1M-token context window is larger than 97% of the models we list. At $0.10 per million input tokens it is cheaper than 67% of comparable models.
About DeepSeek: DeepSeek V4 Flash
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does DeepSeek: DeepSeek V4 Flash stack up?
Compare side-by-side with other professional models.
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.10 | $0.000098 |
| Output | $0.20 | $0.000196 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about DeepSeek: DeepSeek V4 Flash
How much does DeepSeek: DeepSeek V4 Flash cost?
DeepSeek: DeepSeek V4 Flash costs $0.10 per million input tokens and $0.20 per million output tokens.
What is the context window of DeepSeek: DeepSeek V4 Flash?
DeepSeek: DeepSeek V4 Flash has a context window of 1,048,576 tokens (1M).
Is DeepSeek: DeepSeek V4 Flash good for coding?
On our coding benchmark index, DeepSeek: DeepSeek V4 Flash ranks #23 of 129 models, placing it in the top quartile of the field for code generation and debugging.
What can DeepSeek: DeepSeek V4 Flash do?
DeepSeek: DeepSeek V4 Flash supports tool use and function calling.
Who created DeepSeek: DeepSeek V4 Flash?
DeepSeek: DeepSeek V4 Flash is developed by DeepSeek and was released on April 24, 2026.
