DeepSeek R1 API pricing
DeepSeek charges $0.55 per million input tokens and $2.19 per million output tokens for DeepSeek R1 (deepseek-r1), and $0.14 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00164.
DeepSeek R1 price per million tokens
| Token type | Standard |
|---|---|
| Input | $0.55 |
| Cached input | $0.14 |
| Output | $2.19 |
API model id: deepseek-r1. DeepSeek R1 supports a 65.5K-token context window, up to 8.19K output tokens, tool calling and reasoning.
What DeepSeek R1 costs per request
| Request | 1 request | 1,000 requests | 1M requests |
|---|---|---|---|
| Short chat message (300 in, 200 out) | $0.000603 | $0.60 | $603.00 |
| Typical request (1K in, 500 out) | $0.00164 | $1.65 | $1,645.00 |
| Long document summary (20K in, 1K out) | $0.0132 | $13.19 | $13,190.00 |
| Coding agent step (50K in, 2K out) | $0.0319 | $31.88 | $31,880.00 |
At standard rates. A token is about 4 characters of English text, so 1,000 tokens is roughly 750 words. DeepSeek counts tokens with its own tokenizer, so the same text can be a different number of tokens.
How DeepSeek R1 compares
- For a typical request, DeepSeek R1 is cheaper than 64% of the other models on apicost.app.
- GPT-5 mini from OpenAI costs $0.25 input and $2 output per million tokens, so a typical request is $0.00125: 1.3× cheaper than DeepSeek R1.
- Claude Haiku 4.5 from Anthropic costs $1 input and $5 output per million tokens, so a typical request is $0.0035: 2.1× the price of DeepSeek R1.
- Gemini 2.5 Flash from Google Gemini costs $0.3 input and $2.5 output per million tokens, so a typical request is $0.00155: about the same price as DeepSeek R1.
DeepSeek R1 price history
DeepSeek R1 has cost $0.55 per million input tokens and $2.19 per million output tokens since apicost.app started tracking prices on October 22, 2026.
Every LLM API price increase, cut, new and retired model, dated: LLM API price changes.
Models with a similar price
| Model | Provider | Input / 1M | Cached input / 1M | Output / 1M | Typical request |
|---|---|---|---|---|---|
| GPT-5 mini | OpenAI | $0.25 | $0.025 | $2 | $0.00125 |
| Mistral Large 3 | Mistral | $0.5 | $0.05 | $1.5 | $0.00125 |
| Gemini 2.5 Flash | Google Gemini | $0.3 | $0.03 | $2.5 | $0.00155 |
| Gemini 3.5 Flash Lite | Google Gemini | $0.3 | $0.03 | $2.5 | $0.00155 |
| Mistral Large 4 | Mistral | $0.7 | $0.07 | $2.1 | $0.00175 |
| Gemini 3 Flash Preview | Google Gemini | $0.5 | $0.05 | $3 | $0.002 |
| Grok Build 0.1 | xAI | $1 | $0.2 | $2 | $0.002 |
| Grok Code Fast | xAI | $1 | $0.2 | $2 | $0.002 |
Other DeepSeek models
- DeepSeek Coder $0.14 / $0.28
- DeepSeek Flash $0.3 / $1.2
- DeepSeek V3 $0.27 / $1.1
- DeepSeek V3.2 $0.28 / $0.4
- DeepSeek V4 Flash $0.3 / $1.2
- DeepSeek V4 Pro $1.32 / $3.96
Every DeepSeek model side by side, with batch, caching and long-context prices: DeepSeek API pricing. Ways to pay less: batch API, prompt caching, the cheapest models.
Questions and answers
How much does the DeepSeek R1 API cost?
DeepSeek charges $0.55 per million input tokens and $2.19 per million output tokens for DeepSeek R1 (deepseek-r1), and $0.14 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00164.
Has the DeepSeek R1 API price changed?
No. DeepSeek R1 has cost $0.55 per million input tokens and $2.19 per million output tokens since apicost.app started tracking prices on October 22, 2026.
Is there a cheaper way to use DeepSeek R1?
Prompt caching lowers the price of input that repeats across requests to $0.14 per million tokens.
What is the context window of DeepSeek R1?
DeepSeek R1 accepts up to 65,536 input tokens, roughly 49,000 words of English, and writes up to 8,192 output tokens per response. Filling the whole context window once costs $0.036 in input tokens.
Is DeepSeek R1 cheaper than GPT-5 mini?
No. GPT-5 mini from OpenAI costs $0.25 input and $2 output per million tokens, so a typical request is $0.00125: 1.3× cheaper than DeepSeek R1.