Skip to content

DeepSeek V3.1

DeepSeek V3.1 is DeepSeek's August 21, 2025 model update introducing hybrid inference with selectable thinking and non-thinking modes in one endpoint. It strengthens tool use and multi-step agent capabilities over DeepSeek-V3.

ReasoningTool Use
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'deepseek/deepseek-v3.1',
prompt: 'Why is the sky blue?'
})

More models by DeepSeek

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Per Query
Capabilities
Providers
ZDR
No Training
Release Date
1M
0.6s
102tps
$0.14/M$0.28/M
Read:$0.0/M
Write:
deepinfra logo
deepseek logo
novita logo
04/23/2026
1M
0.9s
62tps
$0.43/M$0.87/M
Read:$0.0/M
Write:
deepinfra logo
deepseek logo
fireworks logo
+1
04/23/2026
164K
0.8s
83tps
$0.28/M$0.42/M
Read:$0.03/M
Write:
bedrock logo
deepinfra logo
deepseek logo
+2
12/01/2025
164K
0.3s
100tps
$0.28/M$0.42/M
Read:$0.03/M
Write:
bedrock logo
deepinfra logo
deepseek logo
+2
12/01/2025
131K
1.8s
29tps
$0.27/M$1.00/M
Read:$0.14/M
Write:
novita logo
09/22/2025
164K
0.9s
111tps
$0.77/M$0.77/M
Read:$0.14/M
Write:
baseten logo
novita logo
12/26/2024