DeepSeek: DeepSeek V3.1 Terminus

deepseek/deepseek-v3.1-terminus

119th smartest of 182ReasoningToolsJSON

Use via OpenRouter ↗

Intelligence

21.4

119th of 182

Design Elo

—

Speed

—

tokens/sec

Latency

—

first token

Input price

$0.270

130th cheapest

Context

164K

33K max out

How it compares

Smarter than35%

of all ranked models

Cheaper than61%

of all ranked models

Overview

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...

Benchmarks

independent · Artificial Analysis & Design Arena

Artificial Analysis63th percentile

Intelligence Index

21.4

GPQA Diamond

75%

Humanity's Last Exam

SciCode

32%

Tau²-Bench (agentic)

37%

Providers & pricing (5)

Provider	In $/M	Out $/M	Context	Uptime
DeepInfrafp4	$0.270	$0.950	164K	100%
SiliconFlowfp8	$0.270	$1.00	164K	99.3%
Novitafp8	$0.270	$1.00	131K	100%
AtlasCloudfp8	$0.300	$0.950	131K	100%
StreamLake	$0.343	$1.03	128K	100%

Specifications

Context window164K

Max output33K

Knowledge cutoffMar 2025

Input modalitiestext

Output modalitiestext

Prompt caching—

Cache read price$0.135/M

ModeratedNo

Open weightsdeepseek-ai/DeepSeek-V3.1-Terminus ↗

DeepSeek V3.1 Terminus FAQ

How much does DeepSeek V3.1 Terminus cost?

DeepSeek V3.1 Terminus costs $0.270 per million input tokens and $1.00 per million output tokens via OpenRouter, making it 130th cheapest of 332 paid models.

How smart is DeepSeek V3.1 Terminus?

DeepSeek V3.1 Terminus scores 21.4 on the Artificial Analysis Intelligence Index, ranking 119th of 182 benchmarked models, with a GPQA Diamond score of 75%.