Home › Providers › deepseek › DeepSeek: DeepSeek V3.1

DeepSeek: DeepSeek V3.1 API Pricing

DeepSeek: DeepSeek V3.1 is an API model from deepseek. It costs $0.25 per 1M input tokens and $0.95 per 1M output tokens, with cached input at $0.13. Its context window is 163,840 tokens with up to 32,768 output tokens. A workload of 10M input + 2M output tokens costs about $4.4 per month.
Input
$0.25
per 1M tokens
Output
$0.95
per 1M tokens
Cached input
$0.13
per 1M tokens
Context window
163K
163,840 tokens
Blended (80/20)
$0.39
per 1M tokens

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: DeepSeek V3.1 cost for a real workload?

At 10M input + 2M output tokens per month, DeepSeek: DeepSeek V3.1 costs about $4.4 ($2.5 input + $1.9 output). Try your own volumes in the cost calculator.

What are cheaper alternatives to DeepSeek: DeepSeek V3.1?

Compare DeepSeek: DeepSeek V3.1 with other models

DeepSeek: DeepSeek V3.1 vs DeepSeek: DeepSeek V4.1 Flash (batch)DeepSeek: DeepSeek V3.1 vs DeepSeek: DeepSeek V4 Flash 0423DeepSeek: DeepSeek V3.1 vs DeepSeek: DeepSeek V4.1 FlashDeepSeek: DeepSeek V3.1 vs DeepSeek: DeepSeek V3.2 ExpDeepSeek: DeepSeek V3.1 vs DeepSeek: DeepSeek V3.2DeepSeek: DeepSeek V3.1 vs DeepSeek: DeepSeek V4.1 Flash 1017

Frequently asked questions

How much does DeepSeek: DeepSeek V3.1 cost?

DeepSeek: DeepSeek V3.1 costs $0.25 per 1M input tokens and $0.95 per 1M output tokens (list price, snapshot October 21, 2026). At 10M input + 2M output tokens per month that is about $4.4.

What is the context window of DeepSeek: DeepSeek V3.1?

DeepSeek: DeepSeek V3.1 has a context window of 163,840 tokens and can return up to 32,768 output tokens per response.

What are cheaper alternatives to DeepSeek: DeepSeek V3.1?

Cheaper models include Qwen: Qwen3 Next 80B A3B Instruct ($0.09 in / $1.1 out), Qwen: Qwen3 Coder Flash ($0.195 in / $0.975 out), Qwen: Qwen3.7 Plus (batch) ($0.23 in / $0.92 out). See the full list on this page.

Is DeepSeek: DeepSeek V3.1 free to use?

No. DeepSeek: DeepSeek V3.1 is a paid model at $0.25 input / $0.95 output per 1M tokens. 20 free models are listed on the free models page.

Provider: deepseek · Model ID: deepseek/deepseek-chat-v3.1 · Modality: text->text · Price snapshot October 21, 2026, refreshed daily. How we collect prices