How much does DeepSeek V3.2 cost per million tokens?

DeepSeek V3.2 costs $0.28 per million input tokens and $0.42 per million output tokens at list price, and $0.028 per million cached input tokens.

What is the context window of DeepSeek V3.2?

DeepSeek V3.2 accepts up to 163,840 tokens of context and returns up to 65,536 output tokens.

How much do 1,000 chat messages cost with DeepSeek V3.2?

About $0.49, assuming 1,000 input + 500 output tokens per message.

Is there a cheaper alternative to DeepSeek V3.2?

In the same price range, OpenAI GPT-6 Luna Pro ($0.1 / $0.5), OpenAI GPT-6 Luna ($0.1 / $0.5), Qwen Qwen3.8 Omni Flash ($0.15 / $0.47) cost less per token. Quality differs: test on your own prompts.

Where can I buy DeepSeek API credits for less?

Discount credit books resell OpenRouter usage below face value within their depth, OpenRouter adds a 5.5% card fee, and DeepSeek sells its own credits at face value. The live table on this page ranks them for $100 of usage.

DeepSeek · live price

DeepSeek V3.2 API pricing

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

Small and cheap (under $1 per 1M)Tool callingReasoning

Input: $0.28; per 1M tokens
Output: $0.42; per 1M tokens
Cached input: $0.028; per 1M tokens
Context: 164K; 66K max output

List price from OpenRouter, which passes DeepSeek's price through without markup. Refreshed hourly. Released December 1, 2025. Model id deepseek/deepseek-v3.2.

What DeepSeek V3.2 costs in practice

At list price, before any batch or caching discount.

1,000 chat messages

$0.49

1,000 input + 500 output tokens each

1,000 RAG questions

$2.45

8,000 input + 500 output tokens each

100 coding-agent steps

$0.92

30,000 input + 2,000 output tokens each, no caching

DeepSeek V3.2 price history

No price change since we started tracking on 2026-10-01. We record prices daily; changes will show here.

DeepSeek V3.2 price by host

GMICloud serves it below list price right now. Route to it to pay less on every token.

GMICloud$0.209 in · $0.31 out · 164K ctx · 90.0% uptime 24h
DeepInfra$0.26 in · $0.38 out · 164K ctx · 99.3% uptime 24h
AtlasCloud$0.26 in · $0.38 out · 164K ctx · 94.6% uptime 24h
Venice$0.268 in · $0.39 out · 160K ctx · 99.7% uptime 24h
SiliconFlow$0.259 in · $0.42 out · 164K ctx · 95.0% uptime 24h
Baidu$0.28 in · $0.42 out · 131K ctx · 99.6% uptime 24h
DigitalOcean$0.3 in · $0.96 out · 164K ctx · 98.2% uptime 24h
Alibaba$0.37 in · $1.11 out · 131K ctx · 93.9% uptime 24h
Friendli$0.5 in · $1.50 out · 164K ctx · 100.0% uptime 24h
Phala$1 in · $1 out · 164K ctx · 99.4% uptime 24h
Google$0.56 in · $1.68 out · 164K ctx · 99.1% uptime 24h
Mara$3 in · $4.50 out · 33K ctx · 78.2% uptime 24h
SambaNova$3 in · $4.50 out · 33K ctx · 95.3% uptime 24h

Where to buy DeepSeek credits for less

DeepSeek V3.2 costs the same per token everywhere it's sold through OpenRouter. What changes is the price of the credits. Live quotes for $100 of usage:

#	Where you buy	You payYou pay for $100.00 of usage	vs list price	Price source
1	OrbioCardCheapest right now Credits from a discount book, plus a 5% platform fee and card processing, both included in the quote.	$85.10 incl. $2.60 card processing	-14.9%	live quote
2	smaaartCard Credits from a discount book, plus a 5% platform fee on face value. Card processing and taxes shown at checkout.	$95.00 + card processing and tax at checkout (not in this number)	-5.0%	live quote
3	Direct from the labCard Prepaid credits at face value (OpenAI, Anthropic, Google…). Taxes may apply.	$100.00 no top-up fee	list price	face value
4	OpenRouterCrypto 5% on crypto purchases. No markup on model prices.	$105.00 fees included	+5.0%	published fee
5	OpenRouterCard 5.5% on card purchases, $0.80 minimum. No markup on model prices.	$105.50 fees included	+5.5%	published fee

Disclosure: this site is run by the team behind smaaart, one of the options compared. Tables are ranked by price only, from live quotes and published fees, including when smaaart isn't first. How we compare

DeepSeek V3.2 cost calculator

Enter your monthly tokens to price your own usage.

Model$0.28 in / $0.42 out per 1M tokens · list price, liveInput tokens / month (millions)Output tokens / month (millions)

Usage at list price$18.20/ month(quotes below are for $18.00: purchases run from $5.00 to $10,000.00)

Cheaper alternatives to DeepSeek V3.2

Other labs' models in the same price range or the one below, cheaper per token.

Model	Input / 1M	Output / 1M	Blended 3:1	Context
OpenAI: GPT-6 Luna Pro	$0.1	$0.5	$0.2	1.1M
OpenAI: GPT-6 Luna	$0.1	$0.5	$0.2	1.1M
Qwen: Qwen3.8 Omni Flash	$0.15	$0.47	$0.23	1M
Qwen: Qwen3.8 Flash	$0.15	$0.47	$0.23	1M
Z.ai: GLM 5.3 Flash	$0.15	$0.5	$0.237	1.0M
Qwen: Qwen3.7 Flash	$0.03	$0.13	$0.055	1M

Other DeepSeek models

Model	Input / 1M	Output / 1M	Blended 3:1	Context
DeepSeek V3.2 Exp	$0.27	$0.41	$0.305	164K
DeepSeek V3.1 Terminus	$0.3	$1	$0.475	164K
DeepSeek V3.1	$0.25	$0.95	$0.425	164K
DeepSeek V4 Flash 0423	$0.042	$0.084	$0.052	1.0M
DeepSeek V4 Pro 0423	$0.209	$0.418	$0.261	1.0M
R1 0528	$0.5	$2.15	$0.913	164K

All DeepSeek API prices