AI OrbitExplore • Compare • Stay Ahead
DeepSeek-R1 AI model logo
ActiveReleased Jan 20, 2025 Updated Sep 3, 2026

DeepSeek-R1

By DeepSeek

COMMUNITY RATING Rate DeepSeek-R1 Be the first to share a community rating.
Tap a star to rate instantly
Technical Performance composite76.7/100 verified composite
Context window128,000tokens
Pricing modelPricing not classifiedProvider terms
Pricing evidenceSource observed · verification pendingSource linked · review pending
MODEL OVERVIEW

About DeepSeek-R1

DeepSeek-R1 is a model from DeepSeek, released on January 20, 2025. Its verified profile includes Text Generation, Reasoning, Code Generation, and API Access, with a 128,000-token context window.

DeepSeek-R1 is provided by DeepSeek. AI Orbit records its release date as January 20, 2025. The current profile lists a 128,000 context window.

Cataloged capabilities include Text Generation, Reasoning, Code Generation, and API Access. AI Orbit maps the model to use cases including General AI Assistance, Writing & Editing, Summarization, Brainstorming, and Question Answering.

The current AI Orbit benchmark composite is 76.7/100. 20 verified benchmark results are linked to this profile, including MMLU, MMLU-Redux, MMLU-Pro, and DROP (3-shot F1).

Related model coverage includes DeepSeek-V3.1, DeepSeek-V3, DeepSeek-Coder-V2, and GPT-5. AI Orbit currently links this model to 4 published comparisons.

ProviderDeepSeek
ReleasedJan 20, 2025
Context window128,000
Benchmark composite76.7/100
Verified benchmarks20
ProviderDeepSeek
Version—
Release dateJanuary 20, 2025
StatusActive
Context window128,000
Associated product—
PROFILE EVIDENCE COVERAGE56/1005/7 checks verified

This score measures how much of the profile AI Orbit can support with stored evidence. It is not a rating of the model's quality, intelligence or performance.

IdentityExact version mapping still required
ProfileProfile verification is incomplete
Official evidenceOfficial-source evidence linked
CapabilitiesCapability taxonomy populated
Release dateOfficial release date stored
Context windowContext specification stored
BenchmarksVerified benchmark evidence available
How AI Orbit verifies model data
WHAT IT CAN DO

Capabilities & use cases

PERFORMANCE

Verified benchmark profile

AI Orbit only presents benchmark rows here when the underlying result is marked verified. Scores should still be interpreted alongside methodology and test date.

MMLUTechnical Performance · DeepSeek
90.8
MMLU-ReduxTechnical Performance · DeepSeek
92.9
MMLU-ProTechnical Performance · DeepSeek
84.0
DROP (3-shot F1)Technical Performance · DeepSeek
92.2
IF-Eval (Prompt Strict)Technical Performance · DeepSeek
83.3
GPQA DiamondTechnical Performance · DeepSeek
71.5
SimpleQATechnical Performance · DeepSeek
30.1
FRAMESTechnical Performance · DeepSeek
82.5
AlpacaEval2.0Technical Performance · DeepSeek
87.6
ArenaHardTechnical Performance · DeepSeek
92.3
LiveCodeBenchTechnical Performance · DeepSeek
65.9
Codeforces PercentileTechnical Performance · DeepSeek
96.3
SWE-bench Verified (DeepSeek Resolved)Technical Performance · DeepSeek
49.2
Aider PolyglotTechnical Performance · DeepSeek
53.3
AIME 2024Technical Performance · DeepSeek
79.8
MATH-500Technical Performance · DeepSeek
97.3
CNMO 2024Technical Performance · DeepSeek
78.8
CLUEWSCTechnical Performance · DeepSeek
92.8
C-EvalTechnical Performance · DeepSeek
91.8
C-SimpleQATechnical Performance · DeepSeek
63.7
API ECONOMICS

Pricing & availability

Commercial terms are shown in the unit that actually applies to this model instead of forcing every model into text-token pricing.

Source observed · verification pending
Pricing modelPricing not classified
Billing unitNot classified
Evidence statusSource linked · review pending
VERIFIED PRICING BASISPricing not classified

The applicable commercial model has been classified, but an exact universal numeric price is not pinned for this model.

Verified economics evidence Official source
SOURCE TRANSPARENCY

Verification evidence

Official source coverage

AI Orbit separates structured evidence records, official provider links and benchmark-specific sources so missing evidence is not mistaken for a negative claim.

Official provider source linked

The profile is connected to an official provider page. Structured evidence records are shown separately when available.

Open source
COMMON QUESTIONS

DeepSeek-R1 FAQ

Quick answers based on the verified information currently available in this model profile.

What is DeepSeek-R1?

DeepSeek-R1 is a model from DeepSeek, released on January 20, 2025. Its verified profile includes Text Generation, Reasoning, Code Generation, and API Access, with a 128,000-token context window. Deployment and pricing can depend on the hosting or self-hosting provider rather than a single universal first-party token rate. The current AI Orbit profile lists...

Who created DeepSeek-R1?

DeepSeek-R1 is provided by DeepSeek.

What can DeepSeek-R1 do?

Its listed capabilities include Text Generation, Reasoning, Code Generation, API Access.

What is DeepSeek-R1 useful for?

AI Orbit currently maps DeepSeek-R1 to use cases including General AI Assistance, Writing & Editing, Summarization, Brainstorming and Question Answering.

What is the context window of DeepSeek-R1?

AI Orbit currently lists the context window as 128,000.

How much does DeepSeek-R1 cost?

Verified commercial pricing is not currently listed on this profile; check the provider for current terms.

SIDE-BY-SIDE RESEARCH

DeepSeek-R1 comparisons

All model comparisons

Compare DeepSeek-R1 with other public AI models using linked specs, pricing and available benchmark evidence.