DeepSeek-V3.1
Overview
Overview
DeepSeek-V3.1 is a hybrid model supporting both thinking and non-thinking modes through different chat templates. Built on DeepSeek-V3.1-Base with a two-phase long context extension (32K phase: 630B tokens, 128K phase: 209B tokens), it features 671B total parameters with 37B activated. Key improvements include smarter tool calling through post-training optimization, higher thinking efficiency achieving comparable quality to DeepSeek-R1-0528 while responding more quickly, and UE8M0 FP8 scale data format for model weights and activations. The model excels in both reasoning tasks (thinking mode) and practical applications (non-thinking mode), with particularly strong performance in code agent tasks, math competitions, and search-based problem solving.
DeepSeek-V3.1 was released on January 10, 2025. API access is available through DeepInfra, Novita.
Performance
Timeline
Specifications
Benchmarks
Benchmarks
DeepSeek-V3.1 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Thu Feb 12 2026Pricing
Pricing
Pricing, performance, and capabilities for DeepSeek-V3.1 across different providers:
| Provider | Input ($/M) | Output ($/M) | Max Input | Max Output | Latency (s) | Throughput | Quantization | Input | Output |
|---|---|---|---|---|---|---|---|---|---|
 DeepInfraint4 | $0.27 | $1.00 | 163.8K | 163.8K | — | — | int4 | Text Image Audio Video | Text Image Audio Video |
 Novitafp8 | $0.27 | $1.00 | 163.8K | 163.8K | — | — | fp8 | Text Image Audio Video | Text Image Audio Video |
Price Comparison for DeepSeek-V3.1
Price per 1M input tokens (USD), lower is better
llm-stats.com - Thu Feb 12 2026API Access
API Access Coming Soon
API access for DeepSeek-V3.1 will be available soon through our gateway.
Recent Posts
Recent Reviews
FAQ
Common questions about DeepSeek-V3.1