Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
DeepSeek

DeepSeek V3

Legacy$$Standard
DeepSeek#29 of 92
CompareChat

Original DeepSeek V3 — the model that put DeepSeek on the map. First iteration of the 685B MoE flagship. Superseded by V3.1 and V3.2.

▼

DeepSeek V3 by DeepSeek has a Capability Index of 78.7, making it comparable to the field average. It ranks #29 out of 92 models on the idapt capability leaderboard. DeepSeek V3 is somewhat expensive at $0.20/M tokens input and $0.80/M tokens output. The model supports a 128K 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
#29of 92
Math
#48of 70
Reasoning
#52of 78

Specifications

Vision
Audio
Reasoning
MoE
Architecture
685B
Parameters
128K
Context
16K
Max output

Performance

Providers

Misc

December 26, 2024
Released
Same family
DeepSeekDeepSeek V3.2DeepSeekDeepSeek V3.2 ExpDeepSeekDeepSeek V3 (0324)DeepSeekDeepSeek V3.1
CompareChat with DeepSeek V3

Compare with

OpenAIGPT 5.6 Solvs DeepSeek V3OpenAIGPT 5.6 Lunavs DeepSeek V3AnthropicClaude Fable 5vs DeepSeek V3AnthropicClaude Opus 4.8vs DeepSeek V3AnthropicClaude Sonnet 5vs DeepSeek V3AnthropicClaude Haiku 4.5vs DeepSeek V3GoogleGemini 3.6 Flashvs DeepSeek V3GoogleGemini 3.5 Flashvs DeepSeek V3GoogleGemini 3.5 Flash-Litevs DeepSeek V3GoogleGemma 4 31Bvs DeepSeek V3xAIGrok 4.5vs DeepSeek V3xAIGrok Build 0.1vs DeepSeek V3xAIGrok 4.1 Fastvs DeepSeek V3MetaMuse Spark 1.1vs DeepSeek V3DeepSeekDeepSeek V4 Provs DeepSeek V3DeepSeekDeepSeek V4 Flashvs DeepSeek V3MiniMaxMiniMax M3vs DeepSeek V3MoonshotAIKimi K3vs DeepSeek V3MoonshotAIKimi K2.7 Codevs DeepSeek V3Zhipu AIGLM 5.2vs DeepSeek V3QwenQwen3.7 Maxvs DeepSeek V3QwenQwen3.7 Plusvs DeepSeek V3QwenQwen3 Coder Nextvs DeepSeek V3NVIDIANemotron 3 Ultravs DeepSeek V3Mistral AIMistral Small 4vs DeepSeek V3
Frequently Asked Questions about DeepSeek V3▼

When was DeepSeek V3 released?

▼

DeepSeek V3 was released on December 26, 2024.

Who created DeepSeek V3?

▼

DeepSeek V3 was created by DeepSeek.

How capable is DeepSeek V3?

▼

DeepSeek V3 has a Capability Index of 78.7/100, making it comparable to the field average. It ranks #29 out of 92 models.

How much does DeepSeek V3 cost?

▼

DeepSeek V3 costs $0.20/M input tokens and $0.80/M output tokens.

What is DeepSeek V3 API pricing?

▼

The DeepSeek V3 API is priced at $0.20 per million input tokens and $0.80 per million output tokens. You can access DeepSeek V3 through idapt.app alongside 200+ other AI models in one workspace.

Is DeepSeek V3 a reasoning model?

▼

No, DeepSeek V3 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 support image or vision input?

▼

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

Does DeepSeek V3 support audio?

▼

No, DeepSeek V3 does not support audio input.

What is the context window of DeepSeek V3?

▼

DeepSeek V3 has a context window of 128K tokens, meaning it can process approximately 96,000 words of context at once.

Is DeepSeek V3 open source?

▼

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

Where can I use DeepSeek V3?

▼

You can chat with DeepSeek V3 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 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)