Skip to content
Dashboard

DeepSeek V3.2

DeepSeek V3.2 is the extended reasoning variant of DeepSeek-V3.2. Available on AI Gateway since December 1, 2025, it generates up to 65.5K tokens of chain-of-thought reasoning for complex analytical, scientific, and multi-step problem-solving tasks. Your use subject to DeepSeek's Terms & Privacy Policies.

Implicit CachingReasoningTool Use
import { streamText } from 'ai'
const result = streamText({
model: 'deepseek/deepseek-v3.2-thinking',
prompt: 'Why is the sky blue?'
})
Read docs

More models by DeepSeek

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Release Date
1M
0.9s
144tps
$0.09/M
$0.18/M
Read:$0.0/M
Write:
alibaba logo
baseten logo
deepinfra logo
+3
07/31/2026
1M
3.1s
164tps
$0.09/M
$0.18/M
Read:$0.0/M
Write:
alibaba logo
azure logo
baseten logo
+5
04/23/2026
1M
0.5s
155tps
$1.74/M$0.43/M
$3.48/M$0.87/M
Read:$0.0/M
Write:
alibaba logo
azure logo
baseten logo
+5
04/23/2026
164K
0.8s
92tps
$0.28/M
$0.42/M
Read:$0.03/M
Write:
bedrock logo
deepinfra logo
deepseek logo
+1
12/01/2025
131K
2.7s
30tps
$0.27/M
$1/M
Read:$0.14/M
Write:
novita logo
09/22/2025
164K
1.1s
39tps
$0.25/M
$0.95/M
Read:$0.13/M
Write:
deepinfra logo
novita logo
sambanova logo
08/21/2025