DeepSeek V3.2 pricing, context window and limits
DeepSeek V3.2 costs $0.62 per million input tokens and $1.85 per million output tokens at Amazon Bedrock list price. It accepts up to 163,840 tokens of context and returns up to 81,920 tokens.
- Model id
bedrock/deepseek.v3.2 - Snapshot
What does DeepSeek V3.2 cost?
| Input | $0.62 |
|---|---|
| Output | $1.85 |
| Cached input (read) | — |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can DeepSeek V3.2 read and write?
| Context window | 163,840 |
|---|---|
| Max output | 81,920 |
What can DeepSeek V3.2 do?
| Vision (image input) | No |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | Yes |
| Input | text |
| Output | text |
What does a request to DeepSeek V3.2 cost?
| A typical request: 1,000 tokens in, 500 out | $0.0015 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.008 |
| 1,000 typical requests | $1.55 |
| 1 million tokens in and 1 million out | $2.47 |
Among 199 Amazon Bedrock models with a published price, DeepSeek V3.2 is the 77th cheapest by input price. Its context window is the 160th largest of 199. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call DeepSeek V3.2 through DVARA?
Configure the bedrock provider in the DVARA LLM Gateway and send the model id bedrock/deepseek.v3.2. DVARA, the AI gateway, 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 gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Amazon Bedrock models are there?
- DeepSeek-V3.1$0.58 in · $1.68 out · 164K context
- DeepSeek-R1$1.35 in · $5.4 out · 128K context
- DeepSeek-R1 (US)$1.35 in · $5.4 out · 128K context
- Nova 2 Lite (EU)$0.374 in · $3.157 out · 1M context
- Nova Lite (EU)$0.069 in · $0.276 out · 300K context
- Nova Lite (CA)$0.064 in · $0.256 out · 300K context
- Nova Micro (EU)$0.04 in · $0.16 out · 128K context
- Claude Sonnet 5 (AU)$2.2 in · $11 out · 1M context
- Nova Pro (EU)$0.92 in · $3.68 out · 300K context
- AU Anthropic Claude Sonnet 4.6$3.3 in · $16.5 out · 1M context
- Claude Fable 5 (EU)$11 in · $55 out · 1M context
- Claude Sonnet 4.5 (AU)$3.3 in · $16.5 out · 200K context
Which models from other providers are similar to DeepSeek V3.2?
These are the closest in context window and input price, one per provider.
- GLM-4.5Zhipu GLM · $0.6 in · $2.2 out · 131K context
- Qwen3.6 27BGroq · $0.6 in · $3 out · 131K context
- Qwen2.5 72B InstructAlibaba Qwen · $0.574 in · $1.721 out · 131K context
- Gemini 3.1 Flash Live PreviewGoogle Gemini · $0.75 in · $4.5 out · 131K context
- Mistral Medium 3Mistral AI · $0.4 in · $2 out · 131K context