DeepSeek V3.2 Speciale

Pricing & Specs API

Free REST API for prices, specs and benchmarks

SpecificationsAPIGET/api/v1/models/deepseek-v3-2-speciale
Canonical ID	deepseek-v3-2-speciale
Type	Language
Status	Active
Creator	DeepSeek
Providers	Azure AI Foundry
Context Window	164K tokens
Input Modalities	Text
Output Modalities	Text
Reasoning Efforts	default
Parameters	685B
HuggingFace Likes	703
HuggingFace Downloads (30d)	12,474
HuggingFace Downloads (all-time)	252,919
Release Date	2025-12-01 · 11 months ago

BenchmarksAPIGET/api/v1/models/deepseek-v3-2-speciale/benchmarks
Intelligence Index	14.5 #232
Math Index	96.7 #5
MMLU-Pro	0.9 #20
GPQA	0.9 #74
HLE	0.3 #97
LiveCodeBench	0.9 #4
IFBench	0.6 #104
Time to First Token	0.00s #122
SciCode	0.4 #111
AIME 2025	1.0 #5
LCR	0.7 #146
TerminalBench Hard	0.3 #70
TAU2	0.0 #405
Output TPS	0.0 #366

CapabilitiesAPIGET/api/v1/models/deepseek-v3-2-speciale

Pricing by ProviderAPIGET/api/v1/models/deepseek-v3-2-speciale/pricing

• Table
• Chart

Provider	Standard
	Input $ / 1M	Output $ / 1M
Azure AI Foundry azure_ai/deepseek-v3.2-speciale	$0.58	$1.68

Cost CalculatorAPIGET/api/v1/models/deepseek-v3-2-speciale/pricing/calculate?input_tokens=1000000&output_tokens=500000

Cheapest Instances to Run ItAPIGET/api/v1/models/deepseek-v3-2-speciale/instances

Cloud GPU instances that can host DeepSeek V3.2 Speciale, ranked by cheapest on-demand price. The model needs about 1645 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

Instance	Cloud	GPU	VRAM	Price	Cheapest region
p6-b300.48xlarge	AWS	8× B300	2149 GB	$142.42/hr	us-east-1

VersionsAPIGET/api/v1/models?family=deepseek-v3

Model IDsAPIGET/api/v1/models/deepseek-v3-2-speciale