LLM ReferenceLLM Reference
Microsoft Foundry

DeepSeek V3.2 Speciale on Microsoft Foundry

DeepSeek · DeepSeek

ServerlessOpen Source

Why use DeepSeek V3.2 Speciale on Microsoft Foundry?

Microsoft Foundry offers DeepSeek V3.2 Speciale with competitive pricing. Microsoft Foundry is a unified Azure platform-as-a-service offering for enterprise AI operations, model builders, and application development.

Compare DeepSeek V3.2 Speciale across 3 providers to find the best fit for your use case
Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: deepseek-v3.2-speciale
Model ID
deepseek-v3.2-speciale

Request example

Curated snippets for this provider are not sourced yet. Use Microsoft Foundry documentation with model ID deepseek-v3.2-speciale.

Gotchas

No curated gotchas have been sourced for this exact provider/model route yet.

Compare DeepSeek V3.2 Speciale Across Providers

ProviderInput (per 1M)Output (per 1M)
DeepSeek Platform$0.28$0.42
OpenRouter$0.40$1.20
Microsoft Foundry

Capabilities

Structured Outputs

About DeepSeek V3.2 Speciale

DeepSeek: DeepSeek V3.2 Speciale available via OpenRouter. Pricing: $0.4/1M input, $1.2/1M output.

FAQ

What is the context window for DeepSeek V3.2 Speciale on Microsoft Foundry?

DeepSeek V3.2 Speciale supports a 128,000 token context window on Microsoft Foundry.

How does Microsoft Foundry compare to other DeepSeek V3.2 Speciale providers?

DeepSeek V3.2 Speciale is available from 3 providers. The cheapest input pricing is $0.28/1M tokens from DeepSeek Platform.

What API model ID do I use for DeepSeek V3.2 Speciale on Microsoft Foundry?

Use the model ID deepseek-v3.2-speciale when calling Microsoft Foundry's API.

Who created DeepSeek V3.2 Speciale?

DeepSeek V3.2 Speciale was created by DeepSeek as part of the DeepSeek model family.

Is DeepSeek V3.2 Speciale open source?

DeepSeek V3.2 Speciale is open source according to the seed data.

Get Started

Model Specs

Released2025-04-10
Context164K
ArchitectureDecoder Only