DeepSeek: DeepSeek V3
DEEPSEEK Developer Architecture Profile
Intelligence (ELO)1431Chatbot Arena Verified
Max Context Limit163,840Max Out: 16,000 tokens
Prompt CachingStandardNo Cache Discount
Standard API / 1M$1.29Blended Standard Rate
Model Capabilities & Contract SLAs
- Coding & Logic
- Fictional
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...
Granular Pricing Matrix
Input Tokens (Standard Prompt)$0.26 / 1M
Output Tokens (Completion)$1.03 / 1M
Pricing data via OpenRouter. Sync: 10/2/2026
Evaluate Competitors
VS Engine MatchupDeepSeek: DeepSeek V3 vs Mistral: Mistral Medium 3.5 (batch)VS Engine MatchupDeepSeek: DeepSeek V3 vs OpenAI: GPT Mini LatestVS Engine MatchupDeepSeek: DeepSeek V3 vs SpaceXAI: Grok 4.20 Multi-AgentVS Engine MatchupDeepSeek: DeepSeek V3 vs Qwen: Qwen3 Coder 30B A3B InstructVS Engine MatchupDeepSeek: DeepSeek V3 vs Qwen: Qwen3 235B A22BVS Engine MatchupDeepSeek: DeepSeek V3 vs OpenAI: o3