DeepSeek V3.2 Speciale

Name: DeepSeek V3.2 Speciale
Author: DeepSeek

Released

2025-04-10

Last refreshed

2026-06-15

Status

Researched 133d ago

Open weightsCommercial use: permittedCodingRAGLong contextClassificationJSON / Tool use

DeepSeek releases · 7 in the last 12 monthsChangelog →

Specifications

Family: DeepSeek
Released: 2025-04-10
Context: 164k
Parameters: 685B total, 37B active (MoE)
Architecture: Decoder Only
Specialization: general
Openness: Open weights
License: DeepSeek LicenseCommercial use: permitted
Weights: Unknown
Code: Unknown

Created by

DeepSeek

Advancing artificial general intelligence (AGI).

Hangzhou, Zhejiang, China

Founded 2023

Website

Pricing

Output / 1M

$0.420

Input / 1M

$0.280

Cheapest of 3 routes · DeepSeek Platform

Providers(3)

DeepSeek Platform OpenRouter Microsoft Foundry

View 3 provider routes

Links

Website

About

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

Provider price ladder

Compare all 3

Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Route
DeepSeek Platform	$0.280	$0.420	Serverless
OpenRouter	$0.400	$1.20	Serverless
Microsoft Foundry	-	-	ServerlessPartial

Available via routers & gateways(8)

LiteLLM

Gateway

Open-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.

Free OSSMicrosoft FoundryDeepSeek Platform

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughDeepSeek Platform

Portkey

Gateway

Production AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.

SubscriptionMicrosoft Foundry

Azure AI Foundry Model Router

Router

Microsoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.

PassthroughMicrosoft Foundry

Helicone

Gateway

Observability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.

SubscriptionMicrosoft Foundry

Kong AI Gateway

Gateway

Multi-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.

SubscriptionMicrosoft Foundry

Capabilities

Structured Outputs

Benchmark peer barsfor Coding

SWE-bench ProRank 44 of 46

80.3

79.2

69.2

67.7

DeepSeek V3.2 Specialecurrent

40.1

Benchmark scores(1)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.