Models
/
near/deepseek-v3.1
near/deepseek-v3.1

NEAR
•
128K
24H
7D
30D
90D
All
TOTAL REQUESTS
106
AVG LATENCY
0ms
AVG TOKENS
0
SUCCESS RATE
100%
TOTAL SPEND
$0.1998
CONTEXT WINDOW
128K
A versatile open-weight DeepSeek model that can switch between fast direct outputs and deeper reasoning/agentic modes, aiming to balance conversational quality with structured problem solving.
(5 total)
Status
Tokens
Character chat and creation
8.56M
3.43M
codex
Character chat and creation
3.15M
weareo.fun
Character chat and creation
2.92M
Character chat and creation
535K
Recent activity on
near/deepseek-v3.1
Total usage per day
Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.
are optional.
Setting them allows your app to appear on the OLLM leaderboards.
# Create clientfrom openai import OpenAIclient = OpenAI(base_url="https://api.ollm.com/v1",api_key="your-api-key")response = client.chat.completions.create(model="near/deepseek-v3.1 ",messages=[{"role": "user", "content": "Why is the sky blue?"}])