Enterprise DNAEnterprise DNA
DeepSeek logo

Models · Reasoning

R1

by DeepSeek

DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens.

Visit DeepSeek ↗

Our verdict

Not reviewed yet

We have not reviewed R1 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 R1

DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.

Best for

Cost-sensitive reasoning and coding agents

Use cases

  • batch analysis
  • coding assistants on a budget
  • eval baselines

Enterprise DNA angle

Omni lets teams A/B DeepSeek against Sonnet on real jobs with shared eval harnesses.

Notes

R1 is listed in the EDNA Models directory from the OpenRouter catalogue.

Pros

  • Strong reasoning at aggressive price points
  • Good coding signal for the cost
  • Useful open-weight-adjacent economics via OpenRouter

Cons

  • Ecosystem and safety tooling less mature than frontier US labs
  • Quality variance across tasks — eval before production

Key facts

What we have checked

Time to first token (ms)
1,020
Checked Artificial Analysis
Output speed (tokens a second)
156
Checked Artificial Analysis
Tokens served on OpenRouter in a day
124.9M (for 19 Oct 2026)
Checked OpenRouter model activity (748 of 748 series)
Tool calls on OpenRouter in a day
303 (for 19 Oct 2026)
Checked OpenRouter model activity (748 of 748 series)
Artificial Analysis Intelligence Index
11.4
Checked Artificial Analysis via OpenRouter
Artificial Analysis Coding Index
24.6
Checked Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index
1.1
Checked Artificial Analysis via OpenRouter
LMArena text rating (Elo)
1,428
Checked LMArena (CC-BY-4.0), published 2026-11-09
Gpqa diamond
71.7% (for 20 Jan 2025)
Checked Epoch AI (CC BY 4.0)
Arc agi 2
1.3% (for 20 Jan 2025)
Checked Epoch AI (CC BY 4.0)
Aider polyglot
56.9% (for 20 Jan 2025)
Checked Epoch AI (CC BY 4.0)
Arc agi
15.8% (for 20 Jan 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-r1`.

  • openrouter · deepseek/deepseek-r1 · Docs

OpenRouter id: deepseek/deepseek-r1

Usage

How much R1 is used

Tokens served a day

268.1M to 124.9M

tokens a day on OpenRouter. 19 Sept 2026 to 19 Oct 2026, 31 readings.

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

Scores

How R1 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 Index11.4indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index24.6indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index1.1indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,428EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Aider polyglot (best-across-versions)56.9percentAs of 20 Jan 2025Epoch AI (CC BY 4.0)
Arc agi (best-across-versions)15.8percentAs of 20 Jan 2025Epoch AI (CC BY 4.0)
Arc agi 2 (best-across-versions)1.3percentAs of 20 Jan 2025Epoch AI (CC BY 4.0)
Balrog (best-across-versions)34.9percentAs of 20 Jan 2025Epoch AI (CC BY 4.0)
Fiction livebench (best-across-versions)69.4percentAs of 20 Jan 2025Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)71.7percentAs of 20 Jan 2025Epoch AI (CC BY 4.0)
Lech mazur writing (best-across-versions)83percentAs of 20 Jan 2025Epoch AI (CC BY 4.0)
Math level 5 (best-across-versions)93.1percentAs of 20 Jan 2025Epoch AI (CC BY 4.0)
Show 4 more scores
ScoreValueSourceChecked
Metr time horizons (best-across-versions)51.9percentAs of 20 Jan 2025Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated53.3percentAs of 20 Jan 2025Epoch AI (CC BY 4.0)
Simplebench (best-across-versions)30.9percentAs of 20 Jan 2025Epoch AI (CC BY 4.0)
Weirdml (best-across-versions)36.5percentAs of 20 Jan 2025Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

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 R1 is used

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

Tokens, last 7 days
—
Requests, last 7 days
—
Tool calls, last 7 days
—
People's vote
1428
0250M500M19 Sept: 268M tokens, 36.6K requests20 Sept: 293M tokens, 39.3K requests21 Sept: 361M tokens, 43.6K requests22 Sept: 306M tokens, 90.2K requests23 Sept: 267M tokens, 38.6K requests24 Sept: 247M tokens, 35.1K requests25 Sept: 260M tokens, 36.1K requests26 Sept: 257M tokens, 39.2K requests27 Sept: 266M tokens, 37.5K requests28 Sept: 307M tokens, 47.6K requests29 Sept: 466M tokens, 62.3K requests30 Sept: 230M tokens, 39.8K requests1 Oct: 323M tokens, 42.3K requests2 Oct: 263M tokens, 43.3K requests3 Oct: 237M tokens, 44.1K requests4 Oct: 286M tokens, 47.7K requests5 Oct: 332M tokens, 66.4K requests6 Oct: 308M tokens, 76K requests7 Oct: 315M tokens, 68.6K requests8 Oct: 233M tokens, 33.4K requests9 Oct: 221M tokens, 32.4K requests10 Oct: 210M tokens, 29.8K requests11 Oct: 233M tokens, 34.5K requests12 Oct: 266M tokens, 38.7K requests13 Oct: 250M tokens, 37.9K requests14 Oct: 262M tokens, 38.7K requests15 Oct: 325M tokens, 43.8K requests16 Oct: 342M tokens, 47.5K requests17 Oct: 276M tokens, 43.3K requests18 Oct: 263M tokens, 33.8K requests19 Oct: 125M tokens, 27.8K requests19 Sept3 Oct17 Oct19 OctSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with R1.

No longer listed by its catalogue; the facts shown are as last listed. Sources checked 2026-11-07. Hosting routes and app features can differ.

DeveloperDeepSeek
Exact model identifierdeepseek/deepseek-r1
InputNot established
OutputNot established
Tool calling
Not established
Structured output
Not established
Reasoning controls
Not established
Availability
unknown
Price basis
token
Licence verification
Check the developer licence; the model name is insufficient
Context length
Not established
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
Not established
Listed retirement date
Not established
Last listed by its catalogue
18 Oct 2026

Not in the OpenRouter catalogue when checked; last listed 2026-10-18. Retirement is not confirmed by a source.

Inspect the sources and their scope
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.

Write a clear business documentWorkflow & starter prompt ↗Analyse a spreadsheetWorkflow & starter prompt ↗Research a companyWorkflow & starter prompt ↗Build an appWorkflow & 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: 18 Oct 2026, from the price listed on this record. 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: 24.6 (2026-11-09) ↗Agentic Index: 1.1 (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 →