Continue logo

Run Continue on DeepSeek V4 Pro

by ContinueEditorcontinue.dev

Continue is an open-source AI code assistant that lives inside VS Code and JetBrains, giving you chat, inline edits, autocomplete and custom assistants against whichever models you configure. Add an Opper entry to ~/.continue/config.yaml with the openai provider and our base URL, and every role you assign it runs on any of 700+ models, with a choice of EU or US inference on one key.

RunContinue logoContinueonin

Connect Continue to DeepSeek V4 Pro

Set up with agents

Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.

Get your API key

Where you can run it

DeepSeek V4 Pro runs on the routes below. Route only to EU providers when your data has to stay in Europe. One route also sells flex and priority processing: the same model at another price, picked per request with service_tier. How service tiers work.

ProviderRegionZero data retentionTrainingInputOutputCache read
EUNo$2.00$4.00$0.50Not offered on this routeNot offered on this route
USNo$1.30$2.60$0.10
USNo$0.87$1.74$0.17Not offered on this routeNot offered on this route
USNo$1.48$3.40Input priceNot offered on this routeNot offered on this route
USNo$1.60$3.20$0.14Not offered on this routeNot offered on this route
MultiNo$1.80$3.60$0.15Not offered on this routeNot offered on this route
MultiNo$1.74$3.48$0.14Not offered on this routeNot offered on this route
Multi—$1.69$3.38$0.14Not offered on this routeNot offered on this route
MultiNo$1.32$3.96$0.04Not offered on this routeNot offered on this route
MultiNo$1.74$3.48$0.14Not offered on this routeNot offered on this route
MultiNo$1.74$3.48$0.14Not offered on this routeNot offered on this route

The model

Run Continue on other models

Step-by-step setup for running Continue on each of these models through Opper.

More apps on Opper

Run Continue on DeepSeek V4 Pro

One key, 700+ models, a choice of region, and zero data retention. Switch the model behind your app without changing your workflow.

Get startedView Documentation