DeepSeek-V3.1: Benchmarks, Pricing & Context Window
DeepSeek-V3.1 is a language model from DeepSeek, released in January 2025.
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
DeepSeek-V3.1 pricing
Providers
DeepSeek-V3.1 starts at $0.270 per million input tokens and $1.00 per million output tokens via DeepInfra. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Output $/M | Max Input | Max Output | Latency s | Throughput | Quant | Input | Output |
|---|---|---|---|---|---|---|---|---|---|
 DeepInfra | $0.270 | $1.00 | 163.8K | 163.8K | — | — | int4 | ||
 Novita | $0.270 | $1.00 | 163.8K | 163.8K | — | — | fp8 |
DeepSeek-V3.1 API
API access coming soon
DeepSeek-V3.1 will be available through our gateway shortly.
DeepSeek-V3.1 examples
Recent arena outputs from DeepSeek-V3.1, picked from the highest-ranked matchups.
DeepSeek-V3.1 license
DeepSeek-V3.1 is released under the MIT license, which permits commercial use, has 671.0B parameters.
- License
- MIT
- Commercial use allowed
- Parameters
- 671.0B
MIT License - allows commercial use
FAQ
Common questions about DeepSeek-V3.1.