DeepSeek V3 0324

Chat

Built by DeepSeek · China · deepseek.com

DeepSeek chat model.

How to use

model: "deepseek/deepseek-v3-0324"

Cap quality here and save

Hard questions go to this model, easy ones drop to something cheaper. Set a savings target (0–0.8) and the router tunes itself until realized savings converge on it.

{
  "model": "celon/auto",
  "celon": {
    "anchor": "deepseek/deepseek-v3-0324",
    "savings_target": 0.4
  }
}

Naming a model directly gets you that model — savings controls don't apply.

Context

164K

Max output

—

Input $/1M

$0.24

Output $/1M

$0.90

Features

Tool callingJSON

Serving providers

DeepInfraNovita

Providers

Price, latency, and uptime per provider serving this model. Celon routes each request to the fastest and cheapest of them. Click a row for regions and data policies.

Loading provider metrics…

Performance

Benchmark quality scores, and measured speed per provider.

Quality

Epoch Capabilities IndexComposite over 50+ benchmarks

137.0

GPQA DiamondPhD-level science questions

67.6%

AIMECompetition mathematics

37.8%

SciCodeScientific code generation

35.8%

At each model's best reasoning effort. Benchmarks it wasn't run on are omitted.

Speed

Loading provider metrics…