DeepSeek V3.2

DeepSeektext → textHugging Face OpenRouter

The cheapest provider for DeepSeek V3.2 is GMICloud at $0.234 per 1M tokens (blended), charging $0.209 per 1M input and $0.31 per 1M output tokens. 13 providers serve it; the most expensive charges 14× as much. Context window: 160K tokens. Prices tracked since Oct 3, 2026.

Best price

$0.234

at GMICloud

Input / output

$0.209 / $0.31

per 1M tokens

Providers

14× spread

7 days

—

best price

30 days

—

best price

Context

160K

tokens

Providers

Active offers ranked by blended price. Bars are relative to the most expensive.

Provider prices for DeepSeek: DeepSeek V3.2, USD per 1M tokens
Provider	Input	Output	Blended	vs cheapest	Context	Uptime 1d	Price since
GMICloudCheapest fp8·−28% discount	$0.209	$0.31	$0.234	best	160K	91.2%	Oct 3
AtlasCloud fp8	$0.26	$0.38	$0.29	+24%	160K	96.1%	Oct 3
DeepInfra fp4	$0.26	$0.38	$0.29	+24%	160K	99.7%	Oct 3
Venice −19% discount	$0.268	$0.39	$0.299	+28%	160K	99.6%	Oct 3
SiliconFlow fp8	$0.259	$0.42	$0.299	+28%	160K	98.2%	Oct 3
Baidu fp8	$0.28	$0.42	$0.315	+35%	128K	99.2%	Oct 3
DigitalOcean	$0.30	$0.96	$0.465	+99%	160K	98.1%	Oct 3
Alibaba fp8	$0.371	$1.11	$0.556	+137%	128K	93.0%	Oct 3
Friendli	$0.50	$1.50	$0.75	+221%	160K	99.9%	Oct 3
Google	$0.56	$1.68	$0.84	+259%	160K	99.9%	Oct 3
Phala	$1.00	$1.00	$1.00	+327%	160K	99.4%	Oct 3
Mara	$3.00	$4.50	$3.375	+1342%	32K	95.4%	Oct 3
SambaNova	$3.00	$4.50	$3.375	+1342%	32K	94.6%	Oct 3

GMICloudCheapest
$0.234
$0.209 in · $0.31 out
best
160K ctx91.2% uptimefp8·−28% discount
AtlasCloud
$0.29
$0.26 in · $0.38 out
+24%
160K ctx96.1% uptimefp8
DeepInfra
$0.29
$0.26 in · $0.38 out
+24%
160K ctx99.7% uptimefp4
Venice
$0.299
$0.268 in · $0.39 out
+28%
160K ctx99.6% uptime−19% discount
SiliconFlow
$0.299
$0.259 in · $0.42 out
+28%
160K ctx98.2% uptimefp8
Baidu
$0.315
$0.28 in · $0.42 out
+35%
128K ctx99.2% uptimefp8
DigitalOcean
$0.465
$0.30 in · $0.96 out
+99%
160K ctx98.1% uptime
Alibaba
$0.556
$0.371 in · $1.11 out
+137%
128K ctx93.0% uptimefp8
Friendli
$0.75
$0.50 in · $1.50 out
+221%
160K ctx99.9% uptime
Google
$0.84
$0.56 in · $1.68 out
+259%
160K ctx99.9% uptime
Phala
$1.00
$1.00 in · $1.00 out
+327%
160K ctx99.4% uptime
Mara
$3.375
$3.00 in · $4.50 out
+1342%
32K ctx95.4% uptime
SambaNova
$3.375
$3.00 in · $4.50 out
+1342%
32K ctx94.6% uptime

Blended = (3 × input + output) / 4.

Price history

Hover to compare providers at any point in time. Click a legend item to hide it.

USD per 1M tokens · each step is a price change

Not enough history yet

Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.

Other pricing

Cache, reasoning and per-call fees. Token rates per 1M; others per unit.

Offered by	Cache read	Cache write
GMICloud	$0.0216	—
AtlasCloud, DeepInfra	$0.13	—
Venice	$0.13	—
SiliconFlow	$0.135	—
Baidu	$0.028	—
DigitalOcean	$0.09	—
Alibaba	$0.0741	$0.463
Friendli	$0.25	—
Phala	$0.50	—

Change log

Every recorded change for this model since Oct 3, 2026.

No changes yet

Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.

About this model

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...

Released: Dec 1, 2025
First tracked: Oct 3, 2026
Canonical slug: deepseek/deepseek-v3.2-20251201
Weights: deepseek-ai/DeepSeek-V3.2