AiCostCompare

DeepSeek V3.1 Terminus

by DeepSeek · deepseek/deepseek-v3.1-terminus · #116 cheapest of 325 paid models

Prices updated Jul 22, 2026, 2:49 AM UTC · refreshed hourly

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...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol

Pricing

Input

$0.27

per 1M tokens

Output

$1.00

per 1M tokens

Blended (3:1)

$0.453

3 input : 1 output

Cache read

$0.135

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for DeepSeek V3.1 Terminus with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.453$0.0285
50%$0.402$0.0218−24%
90%$0.361$0.0164−43%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.000435$0.435
Document summary8,0001,000$0.00316$3.16
Codebase question (RAG)30,0002,000$0.0101$10.10
Long-context analysis150,0005,000$0.0455$45.50

Performance

Intelligence Index

21.4

AA composite quality

Coding Index

43.5

Math Index

53.7

Agentic Index

18.1

Output speed

0 tok/s

median

Time to first token

0s

median

Time to first answer

0s

after reasoning tokens

Artificial Analysis benchmarks

BenchmarkScore
MMLU-Pro83.6%
GPQA Diamond75.1%
Humanity's Last Exam8.4%
LiveCodeBench52.9%
SciCode32.1%
AIME 202553.7%
IFBench41.2%
AA-LCR (Long Context Reasoning)43.3%
Terminal-Bench Hard31.8%
τ²-Bench (Telecom)37.1%

Design Arena Elo

CategoryElo
Website1,214
UI components1,224
Data viz1,200
SVG1,112
3D1,199
Game dev1,189
Code categories1,209

Specs

Context window

164K

tokens

Max output

33K

tokens

Input modalities

text

Tokenizer

DeepSeek