DeepSeek V3.1
DeepSeek • LLM
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Specifications
Context Window
164K tokens
Input Price/1M
$0.56
Output Price/1M
$1.67
Parameters
—
Max Output
33K tokens
Benchmarks
DeepSeek V3.1 results on the main AI model evaluation benchmarks. Higher scores indicate better performance.
Agentic
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Terminal-Bench Hard | 25.0 | 100.0 | — |
Coding
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| LiveCodeBench | 78.0 | 100.0 | Artificial Analysis official API |
| SciCode | 39.0 | 100.0 | — |
| AA Coding Index | 29.7 | 100.0 | Artificial Analysis official API |
Knowledge
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU-Pro | 85.0 | 100.0 | — |
Long Context
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA-LCR | 53.0 | 100.0 | — |
Math
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AIME 2025 | 90.0 | 100.0 | Artificial Analysis official API |
| AA Math Index | 89.7 | 100.0 | Artificial Analysis official API |
overall
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Intelligence Index | 28.1 | 100.0 | Artificial Analysis official API |
Reasoning
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| MMLU Pro | 85.1 | 100.0 | Artificial Analysis official API |
| GPQA Diamond | 78.0 | 100.0 | Artificial Analysis official API |
| IFBench | 41.0 | 100.0 | — |
| HLE | 13.0 | 100.0 | — |
Tool Use
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| Tau²-Bench | 37.0 | 100.0 | — |
Information
- Release date
- August 21, 2025
- Tool Calling
- ✅ Supported
- Vision
- ❌ Not supported
- Audio
- ❌ Not supported
Full Analysis: DeepSeek V3.1
What is DeepSeek V3.1?
DeepSeek V3.1 is an AI model developed by DeepSeek, classified as a large language model (LLM). It focuses on text processing and natural language generation. As an open source model, it is available for download, customization, and on-premises deployment. With a context window of 164K tokens, it is suitable for processing long documents such as contracts, books, and complete codebases.
Pricing & Costs in 2026
DeepSeek V3.1 is usage-based, priced at $0.555/1M input tokens and $1.67/1M output tokens. For context: 1 million tokens is approximately 750,000 words, or about 10 average-length books. At this aggressive price point, it is one of the most cost-effective options on the market, ideal for high-volume applications like chatbots, bulk document analysis, and automation.
Benchmarks & Performance
DeepSeek V3.1 was evaluated on 14 different benchmarks, covering categories like Agentic, Coding, Knowledge, Long Context, Math, overall, Reasoning, Tool Use. Results show exceptional 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 V3.1 is suitable for a wide range of AI applications: long document analysis (contracts, legal proceedings, codebases), automation with tool calling (API integration, databases, external systems), high-volume chatbots and automated support, complex reasoning, math problem solving, and logical analysis, text generation, summarization, translation, and general assistance.
Comparison with Alternatives
In the 2026 AI model ecosystem, DeepSeek V3.1 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 V3.1?
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
How much does DeepSeek V3.1 cost?
DeepSeek V3.1 costs $0.555/1M input tokens and $1.67/1M 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 V3.1 compare with other models?
In available benchmarks, DeepSeek V3.1 scored: Terminal-Bench Hard: 25/100, LiveCodeBench: 78/100, SciCode: 39/100. See the full table above for a detailed comparison.
Is DeepSeek V3.1 open source?
Yes, DeepSeek V3.1 is an open source model. You can deploy it on-premises, customize it via fine-tuning, and maintain full control over your data. Check the official repository for the specific license.
What is DeepSeek V3.1 best for?
DeepSeek V3.1 excels at complex reasoning and problem solving. With its large context window, it handles long documents, codebases, and extended conversations. It supports tool calling for API integrations and automation.
Last updated: June 01, 2026 • View methodology →