DeepSeek model
R1 API cost calculator
R1 costs $0.70 per 1M input tokens and $2.50 per 1M output tokens on the DeepSeek API, with a 64K-token context window. A typical request (2K input, 500 output tokens) costs $0.0027 — about $79.50/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on R1
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.0011 | $1.10 |
| RAG query with context | 4,000 / 500 | $0.0040 | $4.05 |
| Document summarization | 20,000 / 1,000 | $0.02 | $16.50 |
| Agent coding session | 100,000 / 5,000 | $0.08 | $82.50 |
R1 vs other DeepSeek models
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| R1 | $0.70 | $2.50 | 64K |
| DeepSeek V4 Flash Vision Exp | $0.22 | $0.66 | 1.0M |
| DeepSeek V4 Pro 0813 | $1.19 | $3.56 | 1.0M |
| DeepSeek V4 Flash 0731 | $0.08 | $0.18 | 1.3M |
| DeepSeek V4 Pro 0423 | $1.60 | $3.20 | 1.0M |
Frequently asked questions
How much does R1 cost per 1M tokens?
According to current pricing data, R1 costs $0.70 per 1M input tokens and $2.50 per 1M output tokens. Processing 1M tokens each way costs $3.20.
What does a typical API request to R1 cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.0027. At 1,000 requests per day that is $2.65 daily, or about $79.50 per month.
What is R1's context window?
R1 supports a 64K-token context window (64,000 tokens).
Does R1 support prompt caching?
No cache-read pricing is published for R1, so every input token is billed at the full $0.70 per 1M rate.
What is a cheaper alternative to R1?
Ling-2.6-flash from Inclusionai is currently the cheapest comparable option at $0.01 per 1M input tokens versus $0.70 for R1 — roughly 70x cheaper on input.
Prices may differ from DeepSeek's official pricing page for batch, tiered, or fine-tuned usage. Compare all current prices on the live model pricing dashboard, see R1 vs Ling-2.6-flash pricing, or run R1 head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.