Skip to content

DeepSeek V3 0324

DeepSeekOpen weightsNon-reasoningVerifiedReleased Mar 24, 2025Input: text
Compare with Grok 4.1 FastSource scores ↗OpenRouter ↗
Overall score
36.5
Rank 154 of 222 · 20.0–52.9
Context window
128K
128,000 tokens
Price per 1M tokens
$0.29 in · $1.14 out
Source: OpenRouter
Blended price
$0.50
3:1 input:output tokens
Output speed
—
Not measured yet

Category scores

Scores per capability area with the model's rank among ranked models in that category.

  1. 1Multilingual#1555.5
  2. 2Reasoning53.0
  3. 3Instruction following#10047.7
  4. 4Knowledge47.0
Higher is better. #N is the model's rank in that category, where it is eligible to be ranked.

Benchmark results (1)

As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.

Multilingual

MMLU-ProX70.5#14 of 16

Pricing by source

USD per 1M tokens.

SourceInputOutputCached in
List price (OpenRouter)$0.29$1.14—
OpenRouter deepseek/deepseek-chat-v3-0324$0.29$1.14$0.11

MIT-licensed weights for the March 2025 checkpoint are available for self-hosting. We haven't confirmed a current official API price for this checkpoint. The deepseek-chat alias has since moved to newer releases.

Arena ratings

Human-preference ratings from LMArena. Best-rated variant shown.

Text1375#179 · 45K votes

Open weights

From the Hugging Face repository.

Parameters
685B
Licence
mit
Downloads (30 days)
1M

Speed

Measured by us through OpenRouter (median of trials).

Not measured yet.

Related models

Same family

Similar score