Enterprise DNAEnterprise DNA
DeepSeek logo

Models · Best cheap

DeepSeek V3.2 Exp

by DeepSeek

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures.

Visit DeepSeek ↗

Our verdict

Not reviewed yet

We have not reviewed DeepSeek V3.2 Exp 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 V3.2 Exp

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures.

Notes

DeepSeek V3.2 Exp is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$0.270 per million tokens
Checked OpenRouter models API
Output price
$0.410 per million tokens
Checked OpenRouter models API
Price on siliconflow
$0.270 per million input tokens
Checked OpenRouter models API
Price on siliconflow
$0.410 per million output tokens
Checked OpenRouter models API
Latest preview version
deepseek/deepseek-v3.2-exp
Checked OpenRouter models API
Time to first token (ms) on siliconflow
2,267
Checked OpenRouter models API
Output speed (tokens a second) on siliconflow
16
Checked OpenRouter models API
Tokens served on OpenRouter in a day
1.7B (for 10 Nov 2026)
Checked OpenRouter model activity (748 of 748 series)
Tool calls on OpenRouter in a day
3.4K (for 10 Nov 2026)
Checked OpenRouter model activity (748 of 748 series)
Aider polyglot
74.2% (for 29 Sept 2025)
Checked Epoch AI (CC BY 4.0)
Cl bench
13.2% (for 29 Sept 2025)
Checked Epoch AI (CC BY 4.0)
Cl bench life
9.5% (for 29 Sept 2025)
Checked Epoch AI (CC BY 4.0)

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-v3.2-exp`.

  • openrouter · deepseek/deepseek-v3.2-exp · Docs

OpenRouter id: deepseek/deepseek-v3.2-exp

Price

What DeepSeek V3.2 Exp costs, over time

Input price

$0.270 to $0.270

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

Source: OpenRouter models API. Checked .

Output price

$0.410 to $0.410

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
siliconflowInput$0.270 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowOutput$0.410 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much DeepSeek V3.2 Exp is used

Tokens served a day

2.3B to 1.7B

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 V3.2 Exp 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 Index16.6indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,425EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
LMArena web development rating (Elo)1,270EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Design Arena rating (Elo)1,175EloAs of 10 Nov 2026Design Arena via OpenRouter
Aider polyglot (best-across-versions)74.2percentAs of 29 Sept 2025Epoch AI (CC BY 4.0)
Cl bench (best-across-versions)13.2percentAs of 29 Sept 2025Epoch AI (CC BY 4.0)
Cl bench life (best-across-versions)9.5percentAs of 29 Sept 2025Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)87.7percentAs of 29 Sept 2025Epoch AI (CC BY 4.0)
Fiction livebench (best-across-versions)83.3percentAs of 29 Sept 2025Epoch AI (CC BY 4.0)
Lmca (best-across-versions)29.1percentAs of 29 Sept 2025Epoch AI (CC BY 4.0)
The agent company (best-across-versions)42.9percentAs of 29 Sept 2025Epoch AI (CC BY 4.0)
Weirdml (best-across-versions)39.5percentAs of 29 Sept 2025Epoch AI (CC BY 4.0)

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

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

USAGE / OPENROUTER

How much DeepSeek V3.2 Exp is used

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

Tokens, last 7 days
11.5B ▼4.7%
Requests, last 7 days
1.2M
Tool calls, last 7 days
15.8K
People's vote
1425
Average cost per request
19.5¢
Price per million tokens
$0.27 in · $0.41 out
02.5B5B19 Sept: 2.3B tokens, 249K requests20 Sept: 2.1B tokens, 212K requests21 Sept: 3B tokens, 425K requests22 Sept: 3B tokens, 378K requests23 Sept: 2.6B tokens, 366K requests24 Sept: 2.6B tokens, 374K requests25 Sept: 3.1B tokens, 425K requests26 Sept: 2.1B tokens, 217K requests27 Sept: 2.2B tokens, 215K requests28 Sept: 2.8B tokens, 429K requests29 Sept: 2.1B tokens, 335K requests30 Sept: 1.8B tokens, 295K requests1 Oct: 1.9B tokens, 312K requests2 Oct: 2.1B tokens, 357K requests3 Oct: 1.5B tokens, 174K requests4 Oct: 1.5B tokens, 157K requests5 Oct: 2B tokens, 283K requests6 Oct: 1.6B tokens, 198K requests7 Oct: 2.9B tokens, 409K requests8 Oct: 1.8B tokens, 272K requests9 Oct: 2.1B tokens, 321K requests10 Oct: 1.4B tokens, 153K requests11 Oct: 1.8B tokens, 156K requests12 Oct: 2.3B tokens, 318K requests13 Oct: 2B tokens, 269K requests14 Oct: 1.9B tokens, 276K requests15 Oct: 2B tokens, 351K requests16 Oct: 2.1B tokens, 375K requests17 Oct: 1.6B tokens, 184K requests18 Oct: 1.9B tokens, 183K requests19 Oct: 2.4B tokens, 317K requests20 Oct: 1.8B tokens, 222K requests21 Oct: 1.9B tokens, 256K requests22 Oct: 2.1B tokens, 271K requests23 Oct: 1.7B tokens, 227K requests24 Oct: 1.6B tokens, 191K requests25 Oct: 1.6B tokens, 138K requests26 Oct: 2B tokens, 244K requests27 Oct: 1.6B tokens, 212K requests28 Oct: 1.6B tokens, 197K requests29 Oct: 1.6B tokens, 188K requests30 Oct: 1.6B tokens, 173K requests31 Oct: 1.5B tokens, 148K requests1 Nov: 1.9B tokens, 523K requests2 Nov: 2.2B tokens, 771K requests3 Nov: 1.8B tokens, 219K requests4 Nov: 1.6B tokens, 194K requests5 Nov: 1.6B tokens, 148K requests6 Nov: 1.5B tokens, 139K requests7 Nov: 1.6B tokens, 130K requests8 Nov: 1.8B tokens, 192K requests9 Nov: 1.8B tokens, 206K requests10 Nov: 1.7B tokens, 146K requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with DeepSeek V3.2 Exp.

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-v3.2-exp
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 Jul 2025
Developer release date
Not established
First seen in the catalogue
29 Sept 2025
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

deepseek/deepseek-v3.2-exp: 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-V3.2-Exp 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: 1175 (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 →