DeepSeek V4 Pro 0813 (Non-reasoning)
DeepSeek • text#244 of 704 in intelligence
Data source: Artificial Analysis · ID AA: d4f5b250-be37-4801-85e6-32fda4179337 · Snapshot published: 10/27/2026, 6:00:26 PM · Methodology version: 4.3
Specifications
AA Intelligence Index
20.4
Artificial Analysis · 4.3 · 10/27/2026, 6:00:26 PM
Context Window
—
Input Price/1M
$1.32
#300 of 445
Output Price/1M
$3.96
Parameters
—
Speed
98 tok/s
#82 of 160
Latency (TTFT)
1.8s
Cost per Task
$0.3555
USD / task · lower is better · Artificial Analysis · 4.3 · 10/27/2026, 6:00:26 PM
Benchmarks
Artificial Analysis metrics for DeepSeek V4 Pro 0813 (Non-reasoning). Higher is better for capability indexes; lower is better for cost per task.
Cost
| Benchmark | Score | Maximum | Methodology | Source / version / date |
|---|---|---|---|---|
| AA Cost Per Task | 0.4 | 100.0 | Artificial Analysis official API | Artificial Analysis · 4.3 · 10/27/2026 |
overall
| Benchmark | Score | Maximum | Methodology | Source / version / date |
|---|---|---|---|---|
| AA Intelligence Index | 20.4 | 100.0 | Artificial Analysis official API | Artificial Analysis · 4.3 · 10/27/2026 |
Information
- Release date
- August 13, 2026
- Tool Calling
- ❌ Not supported
- Vision
- ❌ Not supported
- Audio
- ❌ Not supported
Full Analysis: DeepSeek V4 Pro 0813 (Non-reasoning)
What is DeepSeek V4 Pro 0813 (Non-reasoning)?
DeepSeek V4 Pro 0813 (Non-reasoning) is an AI model developed by DeepSeek, classified as a text model. It focuses on text processing and natural language generation. As a proprietary model, it is available via DeepSeek's cloud API.
Pricing & Costs in 2026
DeepSeek V4 Pro 0813 (Non-reasoning) is usage-based, priced at $1.32/1M input tokens and $3.96/1M output tokens. For context: 1 million tokens is approximately 750,000 words, or about 10 average-length books. The mid-range pricing balances quality and cost for most professional applications.
Benchmarks & Performance
DeepSeek V4 Pro 0813 (Non-reasoning) was evaluated on 2 different benchmarks, covering categories like Cost, overall. Results show moderate performance across available evaluations.
It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.
Recommended Use Cases
DeepSeek V4 Pro 0813 (Non-reasoning) specializes in text, offering advanced capabilities for creating and processing text content.
Comparison with Alternatives
In the 2026 AI model ecosystem, DeepSeek V4 Pro 0813 (Non-reasoning) competes directly with similarly capable models. DeepSeek competes in this segment against OpenAI, Anthropic, Google, and Meta. The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.
For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.
Frequently Asked Questions
What is DeepSeek V4 Pro 0813 (Non-reasoning)?
DeepSeek V4 Pro 0813 (Non-reasoning) is an AI model developed by DeepSeek. It is a text model.
How much does DeepSeek V4 Pro 0813 (Non-reasoning) cost?
DeepSeek V4 Pro 0813 (Non-reasoning) costs $1.32/1M input tokens and $3.96/1M output tokens. For heavy usage (e.g., a chatbot handling 100k messages/month), costs can range from $10 to $1,000 depending on volume.
How does DeepSeek V4 Pro 0813 (Non-reasoning) compare with other models?
In available benchmarks, DeepSeek V4 Pro 0813 (Non-reasoning) scored: AA Cost Per Task: 0.3555/100, AA Intelligence Index: 20.4/100. See the full table above for a detailed comparison.
Is DeepSeek V4 Pro 0813 (Non-reasoning) open source?
No, DeepSeek V4 Pro 0813 (Non-reasoning) is a proprietary model from DeepSeek. It is available via cloud API. For open source alternatives, check our open source model ranking.
What is DeepSeek V4 Pro 0813 (Non-reasoning) best for?
DeepSeek V4 Pro 0813 (Non-reasoning) excels at general-purpose language tasks.
Last updated: October 27, 2026 • View methodology →