deepseek

DeepSeek: DeepSeek V3.1

The DeepSeek V3.1 is a text-based AI model developed by deepseek that can handle reasoning and supports tools integration. It processes input with a context length of 163,840 characters and has a maximum completion token count of 32,768. The model only accepts text as input modality. For users looking for a paid model with strong reasoning capabilities and tool support, DeepSeek V3.1 might be worth considering. Its pricing is competitive at $0.25 per million input tokens and $0.95 per million output tokens. However, it has no independent benchmark coverage yet, which may affect its overall performance standing.

Quality Score
94/100
price + capability + benchmarks
Input Price
$0.25
per 1M tokens · checked 2026-09-10
Output Price
$0.95
per 1M tokens · checked 2026-09-10
Context Window
163,840
tokens
Model ID
deepseek/deepseek-chat-v3.1
Vendor
deepseek
Released
August 2025
Tokenizer
DeepSeek
Input Modalities
text
Output Modalities
text
Max Output
32,768 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.25/M input and $0.95/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.17
A month of a busy support chatbot 5M in / 2M out $3.15

Price & spec history

Tracked daily by PicksByModel since 2026-07-17.

DateInput /MOutput /MContext
2026-09-08 $0.25 $0.95 163,840
2026-09-04 $0.55 $1.65 163,840
2026-09-02 $0.25 $0.95 163,840
2026-08-22 $0.55 $1.65 163,840
2026-07-17 $0.25 $0.95 163,840

Similar models

Quick answers

How much does DeepSeek: DeepSeek V3.1 cost?
$0.25 per million input tokens and $0.95 per million output tokens.
What is DeepSeek: DeepSeek V3.1's context window?
163,840 tokens, roughly 245 pages of text in a single request.
Does DeepSeek: DeepSeek V3.1 support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can DeepSeek: DeepSeek V3.1 process images?
No, it is text-only on the input side.