Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
DeepSeek

DeepSeek V3 (0324)

Legacy$$Standard
DeepSeek#57 of 92
CompareChat

March 2024 iteration of the DeepSeek V3 685B MoE model. Significant update to DeepSeek V3 with improved coding and math. Superseded by DeepSeek V3.1 and V3.2.

▼

DeepSeek V3 (0324) by DeepSeek has a Capability Index of 70.0, making it comparable to the field average. It ranks #57 out of 92 models on the idapt capability leaderboard. DeepSeek V3 (0324) is somewhat expensive at $0.27/M tokens input and $1.12/M tokens output. Cached input reads are priced at $0.14/M tokens, making repeated context cheaper. The model supports a 164K context window.

Best forFrontier reasoningCost-effective
Replaced by
DeepSeekDeepSeek V3.2
See the full deprecation timeline

Benchmarks

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

Category Rankings

Capability
#57of 92
Math
#41of 70
Reasoning
#47of 78

Specifications

Vision
Audio
Reasoning
MoE
Architecture
685B
Parameters
164K
Context
66K
Max output

Performance

Providers

Misc

March 24, 2025
Released
Same family
DeepSeekDeepSeek V3.2DeepSeekDeepSeek V3.2 ExpDeepSeekDeepSeek V3DeepSeekDeepSeek V3.1
CompareChat with DeepSeek V3 (0324)

Compare with

OpenAIGPT 5.6 Solvs DeepSeek V3 (0324)OpenAIGPT 5.6 Lunavs DeepSeek V3 (0324)AnthropicClaude Fable 5vs DeepSeek V3 (0324)AnthropicClaude Opus 4.8vs DeepSeek V3 (0324)AnthropicClaude Sonnet 5vs DeepSeek V3 (0324)AnthropicClaude Haiku 4.5vs DeepSeek V3 (0324)GoogleGemini 3.6 Flashvs DeepSeek V3 (0324)GoogleGemini 3.5 Flashvs DeepSeek V3 (0324)GoogleGemini 3.5 Flash-Litevs DeepSeek V3 (0324)GoogleGemma 4 31Bvs DeepSeek V3 (0324)xAIGrok 4.5vs DeepSeek V3 (0324)xAIGrok Build 0.1vs DeepSeek V3 (0324)xAIGrok 4.1 Fastvs DeepSeek V3 (0324)MetaMuse Spark 1.1vs DeepSeek V3 (0324)DeepSeekDeepSeek V4 Provs DeepSeek V3 (0324)DeepSeekDeepSeek V4 Flashvs DeepSeek V3 (0324)MiniMaxMiniMax M3vs DeepSeek V3 (0324)MoonshotAIKimi K3vs DeepSeek V3 (0324)MoonshotAIKimi K2.7 Codevs DeepSeek V3 (0324)Zhipu AIGLM 5.2vs DeepSeek V3 (0324)QwenQwen3.7 Maxvs DeepSeek V3 (0324)QwenQwen3.7 Plusvs DeepSeek V3 (0324)QwenQwen3 Coder Nextvs DeepSeek V3 (0324)NVIDIANemotron 3 Ultravs DeepSeek V3 (0324)Mistral AIMistral Small 4vs DeepSeek V3 (0324)
Frequently Asked Questions about DeepSeek V3 (0324)▼

When was DeepSeek V3 (0324) released?

▼

DeepSeek V3 (0324) was released on March 24, 2025.

Who created DeepSeek V3 (0324)?

▼

DeepSeek V3 (0324) was created by DeepSeek.

How capable is DeepSeek V3 (0324)?

▼

DeepSeek V3 (0324) has a Capability Index of 70.0/100, making it comparable to the field average. It ranks #57 out of 92 models.

How much does DeepSeek V3 (0324) cost?

▼

DeepSeek V3 (0324) costs $0.27/M input tokens and $1.12/M output tokens.

What is DeepSeek V3 (0324) API pricing?

▼

The DeepSeek V3 (0324) API is priced at $0.27 per million input tokens and $1.12 per million output tokens. You can access DeepSeek V3 (0324) through idapt.app alongside 200+ other AI models in one workspace.

Is DeepSeek V3 (0324) a reasoning model?

▼

No, DeepSeek V3 (0324) is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.

Does DeepSeek V3 (0324) support image or vision input?

▼

No, DeepSeek V3 (0324) does not currently support image or vision input. It is a text-only model.

Does DeepSeek V3 (0324) support audio?

▼

No, DeepSeek V3 (0324) does not support audio input.

What is the context window of DeepSeek V3 (0324)?

▼

DeepSeek V3 (0324) has a context window of 164K tokens, meaning it can process approximately 122,880 words of context at once.

Is DeepSeek V3 (0324) open source?

▼

DeepSeek V3 (0324) is a proprietary model developed by DeepSeek. The model weights and training data are not publicly available.

Where can I use DeepSeek V3 (0324)?

▼

You can chat with DeepSeek V3 (0324) 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 V3 (0324) 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)