Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for deepseek

DeepSeek: DeepSeek V3.2

deepseek/deepseek-v3.2

Model weights
Compare

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 that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.

Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docsOpens in new tab

Modalities

In / Out Price

28% off

$0.2088 / $0.3096per 1M

Context

164K

Released

Dec 1, 2025

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), Floor (cheapest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.

Benchmark score summary for DeepSeek: DeepSeek V3.2 (Artificial Analysis and Design Arena)
SourceBenchmarkScore
Artificial AnalysisDeepSeek V3.2 (Reasoning) Coding Index44.2
Artificial AnalysisDeepSeek V3.2 (Reasoning) GPQA Diamond84.0%
Artificial AnalysisDeepSeek V3.2 (Reasoning) HLE24.6%
Artificial AnalysisDeepSeek V3.2 (Reasoning) IFBench60.7%
Artificial AnalysisDeepSeek V3.2 (Reasoning) τ²-Bench Telecom90.6%
Artificial AnalysisDeepSeek V3.2 (Reasoning) AA-LCR73.3%
Artificial AnalysisDeepSeek V3.2 (Reasoning) GDPval-AA9.0%
Artificial AnalysisDeepSeek V3.2 (Reasoning) CritPt2.9%
Artificial AnalysisDeepSeek V3.2 (Reasoning) Terminal-Bench Hard35.6%
Artificial AnalysisDeepSeek V3.2 (Reasoning) AA-Omniscience Accuracy33.0%
Artificial AnalysisDeepSeek V3.2 (Reasoning) AA-Omniscience Non-Hallucination Rate17.3%
Design ArenaDeepSeek-V3.2 Models Arena 3D Elo1161
Design ArenaDeepSeek-V3.2 Models Arena Asciiart Elo1101
Design ArenaDeepSeek-V3.2 Models Arena Code Categories Elo1179
Design ArenaDeepSeek-V3.2 Models Arena Data Visualization Elo1174
Design ArenaDeepSeek-V3.2 Models Arena Game Development Elo1155
Design ArenaDeepSeek-V3.2 Models Arena SVG Elo1056
Design ArenaDeepSeek-V3.2 Models Arena UI Component Elo1165
Design ArenaDeepSeek-V3.2 Models Arena Website Elo1187

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

Quick Start

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Model RankingsRanking

Frequently asked questions

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 that reduces training and inference cost while preserving quality in long-context scenarios.

DeepSeek V3.2 costs $0.2088/M input tokens and $0.3096/M output tokens, with separate rates for Cache Read at $0.0216/M tokens.

DeepSeek V3.2 has a 163,840 token context window.

Yes. DeepSeek V3.2 accepts tools and tool_choice for function calling on 11 of the 15 providers serving it, and requests that send tools are routed to those providers. It also supports structured outputs via a JSON schema in response_format.

DeepSeek V3.2 is served by 15 providers on OpenRouter: GMICloud, StreamLake, SiliconFlow, DeepInfra, AtlasCloud, Venice, NovitaAI, Baidu Qianfan and 7 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

DeepSeek V3.2 was released on December 1, 2025.