Connecting

Overview

…deepseek-v4.1-flashOpenAI-compatible
Requests · 24H
0 completed · 0 failed
Success rate
0 cancelled · 0 rejected
Generation speed
output tokens per second
List value
at DeepSeek list prices
Live queue
Strict FIFO — exactly one upstream request is in flight at a time.
0 active · 0 queued
Queue is empty
New requests appear here the moment they arrive.
Model
Served through the Anthropic Messages transport, which preserves image input and cache accounting.
Active

Context

0

payload dependent

Max output

0

tokens per request

ReasoningTool callingVisionStreaming

Cache reads, cache writes and uncached input are provider-reported and disjoint; total input is their sum. OpenAI requests and responses are translated to the provider dialect at the gateway.

Tokens over time
Input split into cache reads and non-cached input, with output on top. The stack top is total tokens.
Activity
Gateway lifecycle events.
No events yet
Traffic events stream in here.
Recent requests
Latest traffic through the queue.
View log
Errors
Failed requests in the last 24 hours.
All requests