Skip to content
Alpha
  • Models
  • Rankings
  • Ori

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • EU routing
  • 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
  • AI Site Map

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
ProvidersPricingPerformanceUptimeAppsActivityFAQExplore

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), or Floor (cheapest).

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.

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.

API

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.

Not currently available through EU in-region routing. In-region routing docs

Explore more models

AI Model RankingsRanking
Latency / throughput
$0.3000$0.9600$0.09000.94s55 tps
99.71%
$0.2600$0.3800$0.13002.99s16 tps
99.59%
19% off
$0.33$0.2683$0.48$0.3902$0.16$0.13013.80s17 tps
99.74%
$0.2590$0.8000$0.14002.31s13 tps
100.00%
$1.0000$1.0000$0.50001.77s22 tps
100.00%
28% off
$0.29$0.2088$0.43$0.3096$0.03$0.02161.64s48 tps
100.00%
$0.2600$0.3800$0.13003.22s22 tps
99.82%
$3.0000$4.5000--4.89s48 tps
92.31%
$0.2800$0.4200$0.0280----
100.00%
$3.0000$4.5000------
0.00%
$0.5600$1.6800------
0.00%
Throughput
55tok/s

P50, best across providers

Latency
0.94s

P50, best provider

AutoExacto benchmarks
GPQA DiamondTAU-BenchDigitalOcean83.0%--Baidu Qianfan81.9%--Venice82.1%75.0%Alibaba83.0%73.3%SiliconFlow81.6%74.6%
+9 more providers
Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.39%

Availability over the last 3 days

Last 72 hours
Availability 99.39%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
98.82%
Without Routing
92.23%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

1.
Favicon for https://janitorai.com/
Janitor AI
Janitor AI is a chatbot platform where users create and chat with custom AI characters for interactive roleplay, storytelling, and immersive fiction.
197Btokens
2.
Favicon for https://chatboxai.app/
Chatbox AI
On-device AI copilot
103Btokens
3.
Favicon for https://lorebary.com/
Sophia's LoreBary
Organize and enhance your roleplay creations.
22.4Btokens
4.
Favicon for https://sillytavern.app/
SillyTavern
SillyTavern is the LLM frontend for power users, a chat interface that connects to any model and gives deep control through character creation, roleplay, and prompt customization.
17.4Btokens
5.
Favicon for https://github.com/SkyrimNet-GamePlugin
SkyrimNet
new
13.4Btokens

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 7 of the 11 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 11 providers on OpenRouter: GMICloud, SiliconFlow, DeepInfra, AtlasCloud, Venice, Baidu Qianfan, DigitalOcean, Google Vertex and 3 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.