DeepSeek R1 (0528) pricing
$$ Standard$0.50/M input · $2.15/M output. List prices from provider data; in idapt, chat is metered per token with transparent, usage-based pricing at the prices shown in the app.
Full rate table
| Rate | Price | Unit |
|---|---|---|
| Input | 0.5 | /M tokens |
| Output | 2.1500000000000004 | /M tokens |
| Cache read | 0.35 | /M tokens |
What typical work costs
| Workload | Tokens | List price |
|---|---|---|
| Quick question | 1K tokens in, 500 out | $0.0016 |
| Long-document summary | 60K tokens in, 2K out | $0.03 |
| Agent working session | 400K tokens in, 40K out across a day | $0.29 |
Price your own workload
- Per call
- $0.0016
- Per month
- $0.16
Compare up to four models at once in the cost calculator.
Frequently asked
What does DeepSeek R1 (0528) cost per 1M tokens?
DeepSeek R1 (0528) lists at $0.50 per 1M input tokens and $2.15 per 1M output tokens.
Does DeepSeek R1 (0528) discount cached input tokens?
Yes. Cached input tokens are billed at $0.35 per 1M, versus $0.50 for fresh input. Prompts that repeat a long prefix (a system prompt, attached files) benefit the most.
What does a typical chat message with DeepSeek R1 (0528) cost?
A message with about 1,000 input tokens and a 500-token reply costs roughly $0.0016 at list price. Long documents and long replies scale that linearly with token counts.
Is DeepSeek R1 (0528) cheaper than DeepSeek R1 Distill Llama 70B?
DeepSeek R1 Distill Llama 70B has the lower blended price at a 3:1 input:output mix. DeepSeek R1 (0528): $0.50 in / $2.15 out per 1M. DeepSeek R1 Distill Llama 70B: $0.80 in / $0.80 out per 1M.
How does idapt bill DeepSeek R1 (0528)?
Chat with DeepSeek R1 (0528) in idapt is metered per token with transparent, usage-based pricing at the prices shown in the app. Subscriptions include a weekly usage allowance before any balance is touched.
Part of the DeepSeek R1 (0528) model page · cheapest models board · price changes