Skip to content
English

Switch theme

// DeepSeek

DeepSeek-V3.1

A DeepSeek model. 3 prices across 3 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.

Official in/out per 1M
—
Lowest (DeepInfra)
$0.25 / $0.95
Context
164K
AA index
13.7

Prices checked 2026-10-22Official sources linked on every rowNo estimates

01Specs at a glance

Official values first; gaps filled from OpenRouter’s API where the vendor page is silent.

VendorDeepSeek
Context window164K (163,840 tokens)
Max output33K
InputText
OutputText
Tool calling / JSONYes / Yes
Weights & licenceOpen weights · MIT · Hugging Face
Parameters685B (from weight files)
ReleasedAug 21, 2025
Model IDsdeepseek-v3.1 · deepseek/deepseek-chat-v3.1

02Prices on 3 channels

Per 1M tokens, in the currency each source publishes (1 USD = 6.7 CNY for the blended column). Sorted: official first, then cheapest.

ChannelSourceInputOutputCache hitBlended $ContextNotes
DeepInfra
Inference platform (own price page)
Platform 10-10 $0.25 $0.95 $0.13 0.425 164K DeepInfra own pricing page
SiliconFlow · fp8
Via OpenRouter / provider listed there
OpenRouter 10-22 $0.27 $1 — 0.453 164K SiliconFlow price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against SiliconFlow's own page
SambaNova · fp8
Via OpenRouter / provider listed there
OpenRouter 10-22 $0.65 $1.5 — 0.863 131K SambaNova price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against SambaNova's own page

“Official” = vendor pricing page; “Platform” = the platform’s own pricing page; “OpenRouter” = price listed on OpenRouter, not checked on the platform’s site. Click a source tag to open the original page.

03Where you can use it

Derived only from the price sources above. Country restrictions are set by each vendor – check their terms before you sign up.

04Performance

Speed and AA index from Artificial Analysis public leaderboards (not our own tests); benchmark scores from our benchmark library, best result per benchmark.

AA indexDeepSeek V3.1 (Non-reasoning)
13.7
Output speed (median)
71 tok/s
Time to first token
1.47s
AA index per $ (blended)
32.25
BenchmarkBest scoreSourceDate
LMArena Text1417official2026-10-08
MMLU-Pro84.8%vendor2026-03-11

05Price changes we recorded

All price changes →

From our daily re-checks of the sources above.

No price change recorded since we started tracking (2026-10-10).

06More from DeepSeek

FAQ

How much does the DeepSeek-V3.1 API cost?

There is no official pay-as-you-go price in our data. The lowest listed price is $0.25 / $0.95 on DeepInfra.

What is the context window of DeepSeek-V3.1?

164K tokens of context, up to 33K output tokens. Platforms may cap it lower – see the table.

Is DeepSeek-V3.1 open source?

Yes, the weights are published on Hugging Face (deepseek-ai/DeepSeek-V3.1). Licence: MIT.

Data updated: Model API prices · HF model metadata(UTC+8)