Enterprise DNAEnterprise DNA
DeepSeek logo

Models · Best cheap

DeepSeek V3.1

by DeepSeek

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.

Visit DeepSeek ↗

Our verdict

Not reviewed yet

We have not reviewed DeepSeek V3.1 yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About DeepSeek V3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.

Notes

DeepSeek V3.1 is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$0.250 per million tokens
Checked OpenRouter models API
Output price
$0.950 per million tokens
Checked OpenRouter models API
Price on coreweave
$0.200 per million cached input tokens
Checked OpenRouter models API
Price on coreweave
$0.500 per million input tokens
Checked OpenRouter models API
Price on coreweave
$1.50 per million output tokens
Checked OpenRouter models API
Price on deepinfra
$0.130 per million cached input tokens
Checked OpenRouter models API
Price on deepinfra
$0.250 per million input tokens
Checked OpenRouter models API
Price on deepinfra
$0.950 per million output tokens
Checked OpenRouter models API
Price on mara
$0.600 per million input tokens
Checked OpenRouter models API
Price on mara
$1.70 per million output tokens
Checked OpenRouter models API
Price on sambanova
$0.650 per million input tokens
Checked OpenRouter models API
Price on sambanova
$1.50 per million output tokens
Checked OpenRouter models API

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `deepseek/deepseek-chat-v3.1`.

  • openrouter · deepseek/deepseek-chat-v3.1 · Docs

OpenRouter id: deepseek/deepseek-chat-v3.1

Price

What DeepSeek V3.1 costs, over time

Input price

$0.250 to $0.250

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$0.950 to $0.950

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
coreweaveCached input$0.200 per million cached input tokensSince 7 Nov 20261 changeOpenRouter models API
coreweaveInput$0.500 per million input tokensSince 7 Nov 20261 changeOpenRouter models API
coreweaveOutput$1.50 per million output tokensSince 7 Nov 20261 changeOpenRouter models API
deepinfraCached input$0.130 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraInput$0.250 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$0.950 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
maraInput$0.600 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
maraOutput$1.70 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
sambanovaInput$0.650 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
sambanovaOutput$1.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowInput$0.270 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowOutput$1.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much DeepSeek V3.1 is used

Tokens served a day

5B to 7.9B

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How DeepSeek V3.1 scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index13.7indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,420EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Design Arena rating (Elo)1,118EloAs of 10 Nov 2026Design Arena via OpenRouter

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    cached input per mtok: 0.55 to 0.2

    Source: OpenRouter models API

  2. Price changed

    output per mtok: 1.65 to 1.5

    Source: OpenRouter models API

  3. Price changed

    input per mtok: 0.55 to 0.5

    Source: OpenRouter models API

  4. Price changed

    output per mtok: 1.65 to 0.95

    Source: OpenRouter models API

  5. Price changed

    input per mtok: 0.55 to 0.25

    Source: OpenRouter models API

  6. Price changed

    output per mtok: 0.95 to 1.65

    Source: OpenRouter models API

  7. Price changed

    input per mtok: 0.25 to 0.55

    Source: OpenRouter models API

  8. Price changed

    output per mtok: 0.79 to 0.95

    Source: OpenRouter models API

  9. Price changed

    input per mtok: 0.21 to 0.25

    Source: OpenRouter models API

USAGE / OPENROUTER

How much DeepSeek V3.1 is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
51.9B ▲3.4%
Requests, last 7 days
18.2M
Tool calls, last 7 days
113K
People's vote
1420
Average cost per request
8.4¢
Price per million tokens
$0.25 in · $0.95 out
05B10B19 Sept: 5B tokens, 992K requests20 Sept: 5.8B tokens, 1.2M requests21 Sept: 6.6B tokens, 1.3M requests22 Sept: 6.4B tokens, 1.3M requests23 Sept: 5.8B tokens, 1.6M requests24 Sept: 8.5B tokens, 3.2M requests25 Sept: 9.4B tokens, 3.2M requests26 Sept: 6.9B tokens, 2.7M requests27 Sept: 7.6B tokens, 3.1M requests28 Sept: 7.6B tokens, 3.1M requests29 Sept: 7.3B tokens, 3M requests30 Sept: 7.8B tokens, 2.9M requests1 Oct: 7.7B tokens, 3.1M requests2 Oct: 7.7B tokens, 3M requests3 Oct: 7.8B tokens, 3.1M requests4 Oct: 7.8B tokens, 2.9M requests5 Oct: 7.8B tokens, 2.9M requests6 Oct: 7.1B tokens, 3M requests7 Oct: 6.8B tokens, 2.7M requests8 Oct: 6.7B tokens, 2.7M requests9 Oct: 7.1B tokens, 2.8M requests10 Oct: 7.2B tokens, 2.9M requests11 Oct: 7.7B tokens, 3.1M requests12 Oct: 8.2B tokens, 2.9M requests13 Oct: 7.5B tokens, 2.6M requests14 Oct: 7.4B tokens, 2.6M requests15 Oct: 7.7B tokens, 2.8M requests16 Oct: 7.3B tokens, 2.6M requests17 Oct: 7B tokens, 2.4M requests18 Oct: 7.1B tokens, 2.5M requests19 Oct: 7B tokens, 2.4M requests20 Oct: 7.3B tokens, 2.5M requests21 Oct: 6.9B tokens, 2.5M requests22 Oct: 7B tokens, 2.4M requests23 Oct: 6.6B tokens, 2.4M requests24 Oct: 6.8B tokens, 2.4M requests25 Oct: 7.2B tokens, 2.4M requests26 Oct: 7.4B tokens, 2.5M requests27 Oct: 6.8B tokens, 2.4M requests28 Oct: 7.3B tokens, 2.5M requests29 Oct: 7B tokens, 2.5M requests30 Oct: 7.1B tokens, 2.5M requests31 Oct: 6.8B tokens, 2.5M requests1 Nov: 7B tokens, 2.5M requests2 Nov: 7.7B tokens, 2.7M requests3 Nov: 7.4B tokens, 2.7M requests4 Nov: 7.2B tokens, 2.5M requests5 Nov: 7B tokens, 2.6M requests6 Nov: 7B tokens, 2.5M requests7 Nov: 6.8B tokens, 2.5M requests8 Nov: 8.1B tokens, 2.6M requests9 Nov: 7.9B tokens, 2.6M requests10 Nov: 7.9B tokens, 2.8M requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with DeepSeek V3.1.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-07. Hosting routes and app features can differ.

DeveloperDeepSeek
Exact model identifierdeepseek/deepseek-chat-v3.1
Inputtext
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
MIT, open weights
Context length
164K tokens
Knowledge cutoff
31 Mar 2025
Developer release date
Not established
First seen in the catalogue
21 Aug 2025
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

deepseek/deepseek-chat-v3.1: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-07
openrouter.ai ↗

Source for reasoning controls, first seen, tool calling, context length, input, knowledge cutoff, output, structured output.

Checked 2026-11-07
Licence source ↗

Licence declared in the deepseek-ai/DeepSeek-V3.1 model repository on Hugging Face, which holds the weights files. Read the licence terms before use.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Design Arena: 1118 (2026-11-09) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →