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
| Provider | DeepSeek |
|---|---|
| Context window | 163,840 tokens (164K) |
| Input price | $0.25 / 1M tokens |
| Output price | $0.95 / 1M tokens |
| Input modalities | text |
| Output modalities | text |
| Model ID | deepseek/deepseek-chat-v3.1 |
Pricing is per 1M tokens, indicative pricing via OpenRouter (updated 2026-08-22); a provider's own list price may differ.
Frequently asked questions
How much does DeepSeek V3.1 cost?
Indicative pricing (via OpenRouter, updated 2026-08-22) is $0.25 per 1M input tokens and $0.95 per 1M output tokens. A provider's own list price may differ. On Vincony, DeepSeek V3.1 is available on credit-based pricing alongside 800+ other models.
What is DeepSeek V3.1's context window?
DeepSeek V3.1 supports a context window of up to 163,840 tokens (164K), which is how much text it can consider at once.
Who makes DeepSeek V3.1?
DeepSeek V3.1 is built by DeepSeek. You can access it — and compare it against other providers' models — through Vincony's multi-model platform.
How do I use DeepSeek V3.1?
You can use DeepSeek V3.1 directly through DeepSeek, or via Vincony, which aggregates 800+ models (including DeepSeek V3.1) into one interface with side-by-side comparison and credit-based pricing.