Skip to content

DeepSeek · Chat

DeepSeek V3

DeepSeek 🇨🇳ChatDeepSeek familyOpen weights. One of its sources says the weights are publicly available.

Newer version: DeepSeek V3.1. We compared release dates and version names in our catalogue.

From Aiml API's listing:
DeepSeek-V3 is an advanced LLM with efficient architecture and high performance across various natural language tasks.
llminfo IQ
116.3
Market median price
$0.4375 blended / 1M
Max context
164K
Listings
9

Evidence and sources

🤗 deepseek-ai/DeepSeek-V3-0324llminfo IQ 116.3, ranked among chat models. From 9 benchmarks. A fair amount of data behind it.How llminfo IQ is computedPoor value (46.7). Costs more per task than its benchmark results predict. From 4 benchmarks with measured task costs. A fair amount of data behind it.How Value for money worksReleased 26 Dec 2024 Training-data cutoff, as its sources state it Maker HQ: CN (according to DeepSeek's own website)
All rankings: #167 on OpenRouter today #176 on OpenRouter this week #181 on OpenRouter this monthSources: GenAI Prices data, Models.dev data, AI/ML API data, OpenRouter data docs, llminfo researchPrimary data from GenAI Prices from Models.dev: name, weights availability from AI/ML API: primary mode, description from OpenRouter: knowledge cutoff from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 4 of the 9 peers that say either way have open weights.

Trade-offs

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 8 maker's prices; 2 market median prices.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

Function callingStructured output

Listings

 Flowdotdeepseek/deepseek-chat-v3-0324 · 0324Source: FlowDot data164K$0.20$0.77——
 Kilodeepseek/deepseek-chat-v3-0324 · 0324Sources: Kilo AI Gateway data, Models.dev data164K$0.25$1.00——
 Nous Portaldeepseek/deepseek-chat-v3-0324 · 0324Source: Nous Portal Inference Gateway data164K$0.25$1.00——
 OpenRouterdeepseek/deepseek-chat-v3-0324 · 0324Sources: GenAI Prices data, Models.dev data, OpenRouter data docs164K$0.25$1.00——
 OpenRouterInference by SiliconFlowdeepseek/deepseek-chat-v3-0324 · fp8, 0324 · fp8Source: OpenRouter data docs164K$0.25$1.00232,203.5ms
 Aimlapideepseek/deepseek-chat-v3-0324 · 0324Source: Models.dev data128K$0.3068cache read $0.1481$1.2061——

3 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Science

GPQA Diamond6 results
Source: OpenRouter benchmark exports
deepseek-chat-v3-0324 · 90-day results
Across 5 providers lowest 8.8% median 52.1% highest 67.7%OpenRouter's automatic routing 46%
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
  • SiliconFlow
  • Crusoe
  • GMICloud
  • DeepInfra
  • OpenRouter's automatic routing
  • Novita

Coding

Agentic

Reasoning

Data credits: EvalPlus Leaderboard and EvalPerf (evalplus.github.io), Apache-2.0; EvalPerf win-rate fractions converted to percentages (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence)

Also known as: deepseek-chat-v3-0324, deepseek/deepseek-chat-v3-0324, deepseek/deepseek-chat-v3-0324:free

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works