Context
164K
Max output
164K
Serving providers
1
Cheapest input
$0.62 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Amazon BedrockCheapest$0.62$1.851
ComponentUnitStandardBatchCached
Text input/1M tok$0.6200
Text output/1M tok$1.85

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.500$1.00$1.50$2.00Feb 13Jun 22$1.85$0.620

Cost calculator

estimate your monthly spend on this model
$272
estimated / month

Model IDs

copy the exact identifier for your platform
bedrock/us-east-1/deepseek.v3.2

Frequently asked questions

V3 2 pricing, context and availability

How much does V3 2 cost?

V3 2 costs $0.62 per 1M input tokens and $1.85 per 1M output tokens at its cheapest provider via Amazon Bedrock.

What is the context window of V3 2?

V3 2 accepts up to 164K tokens of context and can return up to 164K output tokens.

What can V3 2 do?

V3 2 supports tool use and reasoning.

Other DeepSeek models

compare pricing across the DeepSeek lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI