Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
DeepSeek

DeepSeek R1

Legacy$$Standard
DeepSeek#51 of 92
CompareChat

Open-source reasoning model matching OpenAI o1 performance. 671B parameters with 37B active, fully transparent reasoning tokens. Groundbreaking open-weights reasoning model. Superseded by R1-0528.

▼

DeepSeek R1 by DeepSeek has a Capability Index of 72.4, making it comparable to the field average. It ranks #51 out of 92 models on the idapt capability leaderboard. DeepSeek R1 is somewhat expensive at $0.70/M tokens input and $2.50/M tokens output. The model supports extended reasoning, a 64K context window.

Best forFrontier reasoningMath & competitionCost-effective
Replaced by
DeepSeekDeepSeek R1 (0528)
See the full deprecation timeline

Benchmarks

CodingInsufficient data
AgenticInsufficient data
Sources:Epoch ECI·Epoch AI·OpenRouter· as of 2026-07-10

Category Rankings

Capability
#51of 92
Math
#34of 70
Reasoning
#45of 78

Specifications

Vision
Audio
Reasoning
MoE
Architecture
671B
Parameters
37B
Active
64K
Context
16K
Max output

Performance

Providers

Misc

January 20, 2025
Released
Same family
DeepSeekDeepSeek R1 (0528)DeepSeekDeepSeek R1 Distill Llama 70BDeepSeekDeepSeek R1 Distill Qwen 32B
CompareChat with DeepSeek R1

Compare with

OpenAIGPT 5.6 Solvs DeepSeek R1OpenAIGPT 5.6 Lunavs DeepSeek R1AnthropicClaude Fable 5vs DeepSeek R1AnthropicClaude Opus 4.8vs DeepSeek R1AnthropicClaude Sonnet 5vs DeepSeek R1AnthropicClaude Haiku 4.5vs DeepSeek R1GoogleGemini 3.6 Flashvs DeepSeek R1GoogleGemini 3.5 Flashvs DeepSeek R1GoogleGemini 3.5 Flash-Litevs DeepSeek R1GoogleGemma 4 31Bvs DeepSeek R1xAIGrok 4.5vs DeepSeek R1xAIGrok Build 0.1vs DeepSeek R1xAIGrok 4.1 Fastvs DeepSeek R1MetaMuse Spark 1.1vs DeepSeek R1DeepSeekDeepSeek V4 Provs DeepSeek R1DeepSeekDeepSeek V4 Flashvs DeepSeek R1MiniMaxMiniMax M3vs DeepSeek R1MoonshotAIKimi K3vs DeepSeek R1MoonshotAIKimi K2.7 Codevs DeepSeek R1Zhipu AIGLM 5.2vs DeepSeek R1QwenQwen3.7 Maxvs DeepSeek R1QwenQwen3.7 Plusvs DeepSeek R1QwenQwen3 Coder Nextvs DeepSeek R1NVIDIANemotron 3 Ultravs DeepSeek R1Mistral AIMistral Small 4vs DeepSeek R1
Frequently Asked Questions about DeepSeek R1▼

When was DeepSeek R1 released?

▼

DeepSeek R1 was released on January 20, 2025.

Who created DeepSeek R1?

▼

DeepSeek R1 was created by DeepSeek.

How capable is DeepSeek R1?

▼

DeepSeek R1 has a Capability Index of 72.4/100, making it comparable to the field average. It ranks #51 out of 92 models.

How much does DeepSeek R1 cost?

▼

DeepSeek R1 costs $0.70/M input tokens and $2.50/M output tokens.

What is DeepSeek R1 API pricing?

▼

The DeepSeek R1 API is priced at $0.70 per million input tokens and $2.50 per million output tokens. You can access DeepSeek R1 through idapt.app alongside 200+ other AI models in one workspace.

Is DeepSeek R1 a reasoning model?

▼

Yes, DeepSeek R1 is a reasoning model. It can think step-by-step through complex problems before providing an answer, often yielding better results on difficult tasks like math, coding, and multi-step logic.

Does DeepSeek R1 support image or vision input?

▼

No, DeepSeek R1 does not currently support image or vision input. It is a text-only model.

Does DeepSeek R1 support audio?

▼

No, DeepSeek R1 does not support audio input.

What is the context window of DeepSeek R1?

▼

DeepSeek R1 has a context window of 64K tokens, meaning it can process approximately 48,000 words of context at once.

Is DeepSeek R1 open source?

▼

DeepSeek R1 is a proprietary model developed by DeepSeek. The model weights and training data are not publicly available.

Where can I use DeepSeek R1?

▼

You can chat with DeepSeek R1 on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access DeepSeek R1 through DeepSeek's own API or platform.

  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Containers · Soon
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Skills
  • Learn
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)