DeepSeek V3.2 Speciale
DeepSeek V3.2 Speciale is worth evaluating for coding, rag, and long context when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, rag, and long context
- Workloads that can use a 164k context window
- Buyers comparing 3 tracked provider routes
Do not use it for
- Vision or document-understanding workloads
- 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
Cheapest of 3 routes · DeepSeek Platform
About
DeepSeek: DeepSeek V3.2 Speciale available via OpenRouter. Pricing: $0.4/1M input, $1.2/1M output.
DeepSeek V3.2 Speciale is an open-weight model in the DeepSeek family. The structured metadata tracks a 164k-token context window and structured outputs. This page tracks provider routes through DeepSeek Platform, OpenRouter, and Microsoft Foundry, with the cheapest tracked route listed at $0.28 input and $0.42 output per 1M tokens. Headline tracked benchmarks include SWE-bench Pro 40.1.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ C1 relevant benchmark in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Long context
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare all 3Compare 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
GatewayOpen-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.
OpenRouter
HybridUnified 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.
Portkey
GatewayProduction 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.
Azure AI Foundry Model Router
RouterMicrosoft 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.
Helicone
GatewayObservability-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.
Kong AI Gateway
GatewayMulti-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.
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(1)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| SWE-bench Pro | 40.1 | — | https://labs.scale.com/leaderboard/swe_bench_pro_public |
Migration checks
No linked migration route is available for this model yet.
Frequently asked questions
What is the context window of DeepSeek V3.2 Speciale?
DeepSeek V3.2 Speciale has a context window of 164k tokens.
How much does DeepSeek V3.2 Speciale cost?
DeepSeek V3.2 Speciale pricing ranges from $0.28/1M to $0.4/1M input tokens depending on the provider.
When was DeepSeek V3.2 Speciale released?
DeepSeek V3.2 Speciale was released on 2025-04-10.
Which providers offer DeepSeek V3.2 Speciale?
DeepSeek V3.2 Speciale is available from 3 providers: DeepSeek Platform, OpenRouter, Microsoft Foundry.
What benchmarks has DeepSeek V3.2 Speciale been tested on?
DeepSeek V3.2 Speciale has been evaluated on 1 benchmark, including SWE-bench Pro.
Cheapest of 3 routes · DeepSeek Platform