DeepSeek: DeepSeek V3.1

Public pricingIntelligence 79/100Medium memory深度思考工具调用

DeepSeek: DeepSeek V3.1 是一款文本模型，适合推理与问题求解。它结合了深度推理与规划、33K tokens上下文和低成本定位，可在reasoning, analysis, and hard problem solving中提供可靠表现。它适合重视质量、速度与成本的团队，能带来稳定输出、灵活部署与扩展空间。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。 它适合需要稳定回答、较长上下文、清晰结构和可扩展部署的团队。

Input

$0.15/1M

Output

$0.75/1M

Cached

$0.07/1M

Batch

$0.07/1M

Calculate your DeepSeek V3.1 bill.

Set your workload — see cost at your exact volume.

What would DeepSeek V3.1 cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

DeepSeek V3.1 at a glance.

Memory

32,768

tokens

Max reply

7,168

tokens

Memory tier

Medium

a long report or a codebase file

Tokenizer

deepseek

Released

Aug 2025

Training cutoff

May 2025

Availability

Public pricing

Status

active

Benchmarks

Quality benchmarks

Independent evaluations from public leaderboards. Higher is better.

  • aa_intelligence_index

    28

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick DeepSeek V3.1

  • Multi-step reasoning, research agents, or hard math.
  • Agentic workflows that call tools or APIs.
  • High-volume workloads where unit cost matters.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.

Alternatives

Similar models to compare.

FAQ

DeepSeek V3.1 — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, DeepSeek V3.1 costs roughly $41 per month. Input is $0.15 /1M tokens and output is $0.75 /1M tokens.
DeepSeek V3.1 has a 32,768-token context window (medium memory — a long report or a codebase file). That means you can fit about 6,144 words of input and history in a single call.
Beyond text generation, DeepSeek V3.1 supports deep step-by-step reasoning, calling functions / tools, strict JSON output. It streams replies by default.
DeepSeek V3.1 was released in August 2025, with training data cut off around May 2025.
Models in a similar class include DeepSeek V3.1 Terminus, DeepSeek V3.2, DeepSeek V3.2 Exp. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare DeepSeek V3.1 against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard