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 V4 Pro 0813

deepseek/deepseek-v4-pro-0813

Model weights
Compare

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Modalities
In / Out Price
$0.2565 / $8per 1M
Context
1.0M
Released
Aug 12, 2026
Compare
ProvidersPricingPerformanceUptimeAppsActivityDocumentationFAQExplore

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.

DeepSeek: DeepSeek Pro versions

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

Documentation

Guides, cookbooks, blog posts, and tools for building with DeepSeek: DeepSeek V4 Pro 0813 on OpenRouter.

  • Does DeepSeek V4 Have Vision?Blog post
  • Why Use OpenRouter for DeepSeekBlog post
  • DeepSeek V4 Is Earning Agentic Token ShareBlog post

Explore more models

AI Model RankingsRanking
Latency / throughput
$0.4500$0.800$0.06501.01s98 tps
100.00%
$0.4500$0.800$0.06500.94s104 tps
100.00%
$0.2850$4.300$0.28400.46s154 tps
100.00%
$0.3700$2.930$0.08801.01s38 tps
100.00%
$1.3100$3.960$0.04400.67s124 tps
99.73%
$1.3200$3.960$0.13000.88s90 tps
99.91%
$1.0800$3.800$0.18001.55s77 tps
98.95%
$1.1220$3.366$0.11221.48s55 tps
99.54%
50% off
$1.32$0.6600$3.96$1.980$0.044$0.02202.52s44 tps
100.00%
$0.2565$8.000$0.26001.05s109 tps
98.72%
$1.3200$3.960$0.04401.17s45 tps
100.00%
$1.3200$3.960$0.04402.95s43 tps
100.00%
$1.3200$3.960$0.04401.60s37 tps
99.76%
$1.4500$4.360$0.15003.57s43 tps
100.00%
$1.3200$3.960$0.04201.12s41 tps
100.00%
$1.3200$3.960$0.04401.09s30 tps
99.53%
$1.3200$3.960$0.13202.18s51 tps
100.00%
$1.3200$3.960$0.13201.00s53 tps
99.77%
$1.6500$4.950$0.16501.44s59 tps
100.00%
25% off
$1.32$0.9900$3.96$2.970$0.044$0.03302.72s37 tps
99.96%
$1.3000$2.600$0.10001.13s58 tps
99.57%
20% off
$1.32$1.0560$3.96$3.168$0.044$0.03522.20s28 tps
100.00%
$1.3200$3.960$0.13201.07s35 tps
100.00%
$1.3200$3.960$0.04401.02s22 tps
100.00%
Throughput
154tok/s

P50, best across providers

Latency
0.46s

P50, best provider

AutoExacto benchmarks
GPQA DiamondTAU-BenchBaseten91.6%--StreamLake92.0%79.0%Alibaba Cloud Int. (US)91.3%79.1%Phala92.0%78.4%NovitaAI91.1%79.1%Alibaba Cloud Int.91.8%77.2%
+20 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.
99.80%

Availability over the last 3 days

Last 72 hours
Availability 99.80%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.79%
Without Routing
97.04%

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://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
546Btokens
2.
Favicon for https://www.isekai.world/
ISEKAI ZERO
AI adventures. Travel with your favorite characters
136Btokens
3.
Favicon for https://strix.ai/
Strix
new
134Btokens
4.
Favicon for https://github.com/cowboyinc/marshal-harness
marshal-harness
new
92.5Btokens
5.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
90.5Btokens

Frequently asked questions

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

The DeepSeek V4 Pro 0813 documentation on OpenRouter includes the Does DeepSeek V4 Have Vision? blog post, the Why Use OpenRouter for DeepSeek blog post, and the DeepSeek V4 Is Earning Agentic Token Share blog post. The quickstart covers API keys and your first request, and the API reference lists every parameter.

DeepSeek V4 Pro 0813 costs $0.2565/M input tokens and $8.00/M output tokens, with separate rates for Cache Read at $0.26/M tokens.

DeepSeek V4 Pro 0813 has a 1,048,576 token context window. It supports up to 393,216 completion tokens.

Yes. DeepSeek V4 Pro 0813 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

DeepSeek V4 Pro 0813 is served by 22 providers on OpenRouter: Relace, Wafer, Ionstream, Sail Research, StreamLake, NovitaAI, GMICloud, DekaLLM and 14 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 V4 Pro 0813 was released on August 12, 2026.