DeepSeek V3 Pricing — Token Costs & API Calculator
Official API pricing for DeepSeek V3 by DeepSeek, with context window, tokenizer details, and a plain-English cost estimate.
Pricing Details
| Attribute | Value |
|---|---|
| Provider | DeepSeek |
| Input cost (per 1M tokens) | $0.27 |
| Output cost (per 1M tokens) | $1.10 |
| Context caching | Not supported |
| Batch API discount | Not available |
| Context window | 128k tokens |
| Tokenizer | SentencePiece (Llama family) |
ⓘ Introductory pricing: Retired from DeepSeek's own API on 2026-07-24. Figures reflect third-party hosts and are not vendor-published; verify before relying on them.
Cost example
1,000 requests × 500 input tokens × 200 output tokens costs $0.36/month with DeepSeek V3 at DeepSeek's published rates.
Based on $0.27/1M input tokens and $1.1/1M output tokens.
Compare DeepSeek V3 with other models
- DeepSeek V3vsGPT-5.6 Sol
- DeepSeek V3vsGPT-5.6 Terra
- DeepSeek V3vsGPT-5.6 Luna
- DeepSeek V3vsGPT-5.5
- DeepSeek V3vsGPT-5.4
- DeepSeek V3vsGPT-5.4 mini
- DeepSeek V3vsGPT-5.4 nano
- DeepSeek V3vsGPT-4o
- DeepSeek V3vsGPT-4.1
- DeepSeek V3vso4-mini
- DeepSeek V3vsClaude Fable 5
- DeepSeek V3vsClaude Opus 5
- DeepSeek V3vsClaude Opus 4.8
- DeepSeek V3vsClaude Sonnet 4.6
- DeepSeek V3vsClaude Sonnet 5
- DeepSeek V3vsClaude Haiku 4.5
- DeepSeek V3vsGemini 3.6 Flash
- DeepSeek V3vsGemini 3.5 Flash
- DeepSeek V3vsGemini 3.5 Flash-Lite
- DeepSeek V3vsGemini 2.5 Flash
- DeepSeek V3vsGemini 2.5 Flash-Lite
- DeepSeek V3vsGemini 2.5 Pro
- DeepSeek V3vsDeepSeek V4 Pro
- DeepSeek V3vsDeepSeek V4 Flash
- DeepSeek V3vsDeepSeek R1
- DeepSeek V3vsLlama 4 Scout