Pass IndexThe State of AISign in

DeepSeek V3.1 Terminus

DeepSeek-V3.1-Terminus delivers more stable & reliable outputs across benchmarks compared to the previous version and addresses user feedback (i.e.

text → text · made by DeepSeek

$0.27$0.95per Mtok in / out
DeepInfra · 10 sellers

Sold by 14 ways

SellerLaneRate
DeepInfra aggregatorstandard$0.27per Mtok in$0.95per Mtok outapi.deepinfra.com · read 2026-08-25
Hugging Face Inference Providers 2 ways$0.27per Mtok in$0.95per Mtok out
Hugging Face Inference Providers aggregatordeepinfra$0.27per Mtok in$0.95per Mtok outrouter.huggingface.co · read 2026-08-25
Hugging Face Inference Providers aggregatornovita$0.27per Mtok in$1per Mtok outrouter.huggingface.co · read 2026-08-25
Nous Research aggregatorstandard$0.27per Mtok in$1per Mtok out$0.11per Mtok cachedinference-api.nousresearch.com · read 2026-09-12
Novita AI aggregatorstandard$0.27per Mtok in$1per Mtok out$0.14per Mtok cachedapi.novita.ai · read 2026-08-25
OpenRouter 4 ways$0.27per Mtok in$1per Mtok out$0.14per Mtok cached
OpenRouter aggregatorstandard$0.27per Mtok in$1per Mtok out$0.14per Mtok cachedopenrouter.ai · read 2026-08-24
OpenRouter aggregatorsiliconflow/fp8$0.27per Mtok in$1per Mtok outopenrouter.ai · read 2026-08-25
OpenRouter aggregatoratlas-cloud/fp8$0.3per Mtok in$0.95per Mtok out$0.13per Mtok cachedopenrouter.ai · read 2026-08-25
OpenRouter aggregatorstreamlake$0.34per Mtok in$1.03per Mtok outopenrouter.ai · read 2026-08-25
SiliconFlow aggregatorstandard$0.27per Mtok in$1per Mtok outmodels.dev · read 2026-09-16
Vercel AI Gateway aggregatorstandard$0.27per Mtok in$1per Mtok out$0.14per Mtok cachedai-gateway.vercel.sh · read 2026-08-25
ElectronHub aggregatorstandard$0.5per Mtok in$1.5per Mtok outapi.electronhub.ai · read 2026-09-16
Fireworks AI aggregatorstandard$0.56per Mtok in$1.68per Mtok outraw.githubusercontent.com · read 2026-09-16
PPIO aggregatorstandard$4per Mtok in$12per Mtok outapi.ppinfra.com · read 2026-09-10

Measured 15 standings

PlaceBoardMetricScore
61stof 161Dtbench — Epoch AIAccuracy81.33
68thof 112Ale bench — Epoch AIPerformance745.17
72ndof 123Lmca — Epoch AIScore28.58
75thof 150Design Arena · uicomponent (models)Elo1197
80thof 147Design Arena · 3d (models)Elo1169
82ndof 156Design Arena · codecategories (models)Elo1191
85thof 162Design Arena · website (models)Elo1199
90thof 152Design Arena · dataviz (models)Elo1183
90thof 109Design Arena · svg (models)Elo1090
98thof 143Artificial Analysis · Agentic IndexIndex8.9
100thof 155Design Arena · gamedev (models)Elo1153
103rdof 177Critpt — Epoch AIAccuracy1.714
107thof 184Artificial Analysis · Coding IndexIndex43.5
111thof 168Scicode — Epoch AIScore40.625
127thof 402LMArena · TextScore (Elo)1415

About

DeepSeek V3.1 Terminus — a text model from DeepSeek, sold by 10 companies from $0.27 in and $0.95 out per million tokens, placed 127th of 402 on LMArena · Text.

It takes text and returns text, with a context window of 131,072 tokens. It was published in 2024. Its sellers say it can reason step by step and call a tool. The catalogue files it under chat. Ten companies sell it. The cheapest is $0.27 in and $0.95 out per million tokens at DeepInfra. Beside the standard rate there are separately routed and regional lanes. It has been measured on 15 boards, and stands best at 127th of 402 on LMArena · Text.

Every current figure

Maker
DeepSeek
Register
model
Takes
text
Returns
text
Context
131,072 tokens
Published
2024
Parameters
685 billion
Licence
not read
Sellers
10
Maker's own price
not read
Price
$0.27 in and $0.95 out per million tokens — DeepInfra
Boards
15
Best place
127th of 402 — LMArena · Text

Known as 2 names

deepseek-ai/DeepSeek-V3.1-Terminusdeepseek/deepseek-v3.1-terminus