deepseek-v3.2-30%

deepseek-v3.2

DeepSeek model with remarkable quality-per-dollar for chat and RAG.

CONTEXT

160K

RELEASED

Sep 2025

INPUT /MTOK

$0.196$0.28

OUTPUT /MTOK

$0.28$0.4

Connect

Call deepseek-v3.2 through the gateway. Native is the model's own wire protocol; Compatible endpoints are translated by the gateway.

POST /v1/responsesNative

curl https://apiarc.ai/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $APIARC_API_KEY" \
  -d '{
    "model": "deepseek-v3.2",
    "input": "Hello"
  }'

Providers

Routes offering deepseek-v3.2 through the gateway, with list pricing.

Provider	Input /M	Output /M	Cache read /M	Latency (30d avg)
DeepSeek-30%	$0.196$0.28	$0.28$0.4	—	—