DeepSeek-R1 (US) pricing, context window and limits
DeepSeek-R1 (US) costs $1.35 per million input tokens and $5.4 per million output tokens at Amazon Bedrock list price. It accepts up to 128,000 tokens of context and returns up to 32,768 tokens.
- Model id
bedrock/us.deepseek.r1-v1:0 - Snapshot
What does DeepSeek-R1 (US) cost?
| Input | $1.35 |
|---|---|
| Output | $5.4 |
| Cached input (read) | — |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can DeepSeek-R1 (US) read and write?
| Context window | 128,000 |
|---|---|
| Max output | 32,768 |
What can DeepSeek-R1 (US) do?
| Vision (image input) | No |
|---|---|
| Tool calling | No |
| Structured output | No |
| Reasoning | Yes |
| Input | text |
| Output | text |
What does a request to DeepSeek-R1 (US) cost?
| A typical request: 1,000 tokens in, 500 out | $0.004 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.019 |
| 1,000 typical requests | $4.05 |
| 1 million tokens in and 1 million out | $6.75 |
Among 191 Amazon Bedrock models with a published price, DeepSeek-R1 (US) is the 89th cheapest by input price. Its context window is the 165th largest of 191. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call DeepSeek-R1 (US) through DVARA?
Configure the bedrock provider in the DVARA LLM Gateway and send the model id bedrock/us.deepseek.r1-v1:0. DVARA, the AI governance platform, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set is counted as costing nothing. Every cost record says which price it used.
Which other Amazon Bedrock models are there?
- DeepSeek V3.2$0.62 in · $1.85 out · 164K context
- DeepSeek-V3.1$0.58 in · $1.68 out · 164K context
- DeepSeek-R1$1.35 in · $5.4 out · 128K context
- Claude Sonnet 5.5 (US)$2.2 in · $11 out · 1M context
- Llama 3.1 70B Instruct (US)$0.72 in · $0.72 out · 128K context
- Claude Sonnet 5 (US)$2.2 in · $11 out · 1M context
- Llama 3.1 8B Instruct (US)$0.22 in · $0.22 out · 128K context
- Claude Sonnet 4.6 (US)$3.3 in · $16.5 out · 1M context
- Llama 3.3 70B Instruct (US)$0.72 in · $0.72 out · 128K context
- Claude Sonnet 4.5 (US)$3.3 in · $16.5 out · 200K context
- Llama 4 Maverick 17B Instruct (US)$0.24 in · $0.97 out · 1M context
- Claude Sonnet 4 (US)$3 in · $15 out · 200K context
Which models from other providers are similar to DeepSeek-R1 (US)?
These are the closest in context window and input price, one per provider.
- Gemini 2.5 Computer Use Preview 10-2025Google Gemini · $1.25 in · $10 out · 128K context
- QVQ MaxAlibaba Qwen · $1.147 in · $4.588 out · 131K context
- GPT-5.2 ChatOpenAI · $1.75 in · $14 out · 128K context
- Magistral Medium (latest)Mistral AI · $2 in · $5 out · 128K context
- GLM-5.1Zhipu GLM · $1.4 in · $4.4 out · 200K context