DeepSeek API pricing
Every DeepSeek model we track, per 1M tokens, from the official pricing page.
Quick answer: DeepSeek API prices run from $0.30 in and $1.20 out per 1M tokens (DeepSeek V4.1 Flash) up to $1.32 in and $3.96 out (DeepSeek V4 Pro). Its cheapest model is number 4 of 29 on our full list. Checked Oct 16, 2026 against the official pricing page.
| Model | Input | Cached | Output | Context |
|---|---|---|---|---|
| DeepSeek V4.1 Flashdeepseek-flashPeak rate. Off-peak is half price. | $0.30 | $0.006 | $1.20 | 1M |
| DeepSeek V4 Prodeepseek-v4-proPeak rate. Off-peak is half price. | $1.32 | $0.044 | $3.96 | 1M |
DeepSeek V4.1 Flashdeepseek-flash
1M context$0.30Input
$1.20Output
$0.006Cached
DeepSeek V4 Prodeepseek-v4-pro
1M context$1.32Input
$3.96Output
$0.044Cached
How it compares
Cheapest models from other providers, blended per 1M tokens: GPT-6 Luna (OpenAI) $0.20 · Qwen3.8 Flash (Qwen) $0.23 · Mistral Small 4 (Mistral) $0.26. See the full API price table, the best model for each task or the plan vs API calculator.
FAQ
How much does the DeepSeek API cost?
From $0.30 input and $1.20 output per 1M tokens for DeepSeek V4.1 Flash, up to $1.32 and $3.96 for DeepSeek V4 Pro.
What is the cheapest DeepSeek model?
DeepSeek V4.1 Flash, with a blended price of $0.525 per 1M tokens (3 parts input to 1 part output).
Is a subscription cheaper than the DeepSeek API?
It depends on how much you use it. Try our plan vs API calculator with your own usage.
Other providers: OpenAI · Anthropic · Google · Meta · Qwen · Mistral · xAI