Enterprise DNAEnterprise DNA
DeepSeek logo

Models · Best cheap

DeepSeek V3

by DeepSeek

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions.

Visit DeepSeek ↗

Our verdict

Not reviewed yet

We have not reviewed DeepSeek V3 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

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions.

Best for

High-volume cheap inference and drafts

Use cases

  • classification
  • draft generation
  • bulk enrichment

Enterprise DNA angle

Route bulk Omni jobs to cheap DeepSeek rows; escalate only failures to frontier models.

Notes

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

Pros

  • Low $/Mtoken for high volume
  • Solid general chat and light coding

Cons

  • Not the top pick for hardest reasoning
  • Needs eval gates for brand-sensitive copy

Key facts

What we have checked

Input price
$0.320 per million tokens
Checked OpenRouter models API
Output price
$0.890 per million tokens
Checked OpenRouter models API
Price on deepinfra
$0.256 per million input tokens
Checked OpenRouter models API
Price on deepinfra
$0.712 per million output tokens
Checked OpenRouter models API
Price on streamlake
$0.257 per million input tokens
Checked OpenRouter models API
Price on streamlake
$1.03 per million output tokens
Checked OpenRouter models API
Latest version
deepseek/deepseek-chat-v3
Checked OpenRouter models API
Time to first token (ms)
1,000
Checked Artificial Analysis
Time to first token (ms) on deepinfra
2,001
Checked OpenRouter models API
Time to first token (ms) on streamlake
957
Checked OpenRouter models API
Output speed (tokens a second)
59.5
Checked Artificial Analysis
Output speed (tokens a second) on deepinfra
21
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`.

  • openrouter · deepseek/deepseek-chat · Docs

OpenRouter id: deepseek/deepseek-chat

Price

What DeepSeek V3 costs, over time

Input price

$0.320 to $0.320

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

Source: OpenRouter models API. Checked .

Output price

$0.890 to $0.890

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
deepinfraInput$0.256 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$0.712 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
streamlakeInput$0.257 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
streamlakeOutput$1.03 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much DeepSeek V3 is used

Tokens served a day

2.4B to 2.6B

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 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 Index8.5indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index23indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index0.8indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,375EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Design Arena rating (Elo)1,116EloAs of 10 Nov 2026Design Arena via OpenRouter

Sources

Where this comes from

  • OpenRouter models APIRegistry

    Checked · Latest version

  • OpenRouter models APIThird party

    Checked · Price on deepinfra, Price on streamlake, Time to first token (ms) on deepinfra, Time to first token (ms) on streamlake, Output speed (tokens a second) on deepinfra

  • OpenRouter models APIOfficial

    Checked · Input price, Output price

  • Artificial AnalysisThird party

    Checked · Time to first token (ms), Output speed (tokens a second)

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

    output per mtok: 1.0287 to 0.89

    Source: OpenRouter models API

  2. Price changed

    input per mtok: 0.2574 to 0.32

    Source: OpenRouter models API

  3. Price changed

    output per mtok: 0.89 to 1.0287

    Source: OpenRouter models API

  4. Price changed

    input per mtok: 0.32 to 0.2574

    Source: OpenRouter models API

  5. Price changed

    output per mtok: 1.0287 to 0.89

    Source: OpenRouter models API

  6. Price changed

    input per mtok: 0.2574 to 0.32

    Source: OpenRouter models API

  7. Price changed

    output per mtok: 0.89 to 1.0287

    Source: OpenRouter models API

  8. Price changed

    input per mtok: 0.32 to 0.2574

    Source: OpenRouter models API

  9. Price changed

    output per mtok: 1.0287 to 0.89

    Source: OpenRouter models API

  10. Price changed

    input per mtok: 0.2574 to 0.32

    Source: OpenRouter models API

  11. Price changed

    output per mtok: 0.89 to 1.0287

    Source: OpenRouter models API

  12. Price changed

    input per mtok: 0.32 to 0.2574

    Source: OpenRouter models API

  13. Price changed

    output per mtok: 0.8001 to 0.89

    Source: OpenRouter models API

  14. Price changed

    input per mtok: 0.2002 to 0.32

    Source: OpenRouter models API

USAGE / OPENROUTER

How much DeepSeek V3 is used

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

Tokens, last 7 days
18.4B ▲4.6%
Requests, last 7 days
7.7M
Tool calls, last 7 days
215K
02.5B5B19 Sept: 2.4B tokens, 1M requests20 Sept: 2.7B tokens, 1M requests21 Sept: 3.3B tokens, 1.2M requests22 Sept: 3B tokens, 1.2M requests23 Sept: 2.8B tokens, 1.1M requests24 Sept: 2.8B tokens, 1.1M requests25 Sept: 2.8B tokens, 1.2M requests26 Sept: 2.5B tokens, 1.1M requests27 Sept: 2.5B tokens, 934K requests28 Sept: 2.7B tokens, 1.1M requests29 Sept: 2.7B tokens, 1.1M requests30 Sept: 2.5B tokens, 1.3M requests1 Oct: 2.6B tokens, 970K requests2 Oct: 2.5B tokens, 988K requests3 Oct: 2.4B tokens, 1M requests4 Oct: 2.5B tokens, 1M requests5 Oct: 2.8B tokens, 1.2M requests6 Oct: 3.2B tokens, 1.3M requests7 Oct: 3.8B tokens, 1.4M requests8 Oct: 3.6B tokens, 1.4M requests9 Oct: 3.8B tokens, 1.5M requests10 Oct: 2.6B tokens, 1000K requests11 Oct: 2.5B tokens, 1.1M requests12 Oct: 2.9B tokens, 1.4M requests13 Oct: 3.1B tokens, 1.3M requests14 Oct: 2.6B tokens, 1.2M requests15 Oct: 2.8B tokens, 1.6M requests16 Oct: 2.5B tokens, 1.2M requests17 Oct: 2.3B tokens, 978K requests18 Oct: 2.3B tokens, 928K requests19 Oct: 2.5B tokens, 1.1M requests20 Oct: 2.6B tokens, 1.2M requests21 Oct: 2.6B tokens, 1.2M requests22 Oct: 2.7B tokens, 1.2M requests23 Oct: 2.5B tokens, 1.1M requests24 Oct: 2.3B tokens, 883K requests25 Oct: 2.5B tokens, 979K requests26 Oct: 2.9B tokens, 1.1M requests27 Oct: 2.9B tokens, 1.1M requests28 Oct: 2.8B tokens, 1.1M requests29 Oct: 2.6B tokens, 1.1M requests30 Oct: 2.4B tokens, 1M requests31 Oct: 2B tokens, 847K requests1 Nov: 2.3B tokens, 911K requests2 Nov: 2.9B tokens, 1.2M requests3 Nov: 2.4B tokens, 1.1M requests4 Nov: 2.5B tokens, 1.1M requests5 Nov: 2.8B tokens, 1.3M requests6 Nov: 2.6B tokens, 1.2M requests7 Nov: 2.6B tokens, 1M requests8 Nov: 2.7B tokens, 989K requests9 Nov: 2.6B tokens, 1M requests10 Nov: 2.6B tokens, 1.1M requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with DeepSeek V3.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-06. Hosting routes and app features can differ.

DeveloperDeepSeek
Exact model identifierdeepseek/deepseek-chat
Inputtext
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Not established
Availability
available
Price basis
token
Licence verification
Check the developer licence; the model name is insufficient
Context length
164K tokens
Knowledge cutoff
31 Jul 2024
Developer release date
Not established
First seen in the catalogue
26 Dec 2024
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

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

Checked 2026-11-06
openrouter.ai ↗

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

Checked 2026-11-06
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.

Build an appWorkflow & starter prompt ↗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.

Coding Index: 23 (2026-11-09) ↗Agentic Index: 0.8 (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 →