ModelWatch
← Catalog

DeepSeek V3.1

Open-weights model with a hybrid thinking mode. Very low cost for its coding ability.

open-weightslow-costcodingreasoning
Input price
$0.25 / 1M tokens
Output price
$0.95 / 1M tokens
Context window
164K tokens
Max output
147K tokens
Output speed
113 tokens/s
Time to first token
2.69s
Inputs
text
Open weights
Yes
OpenRouter id
deepseek/deepseek-chat-v3.1
Provider API id
deepseek-chat
Listed
Aug 21, 2025

Benchmarks

Intelligence Index
n/a
Engineering Index
n/a

Speed and benchmarks for “DeepSeek V3.1 (Reasoning)” from Artificial Analysis. Prices, context window and listing date are live from OpenRouter.

Compare with others