DeepSeek Harness logo

Run DeepSeek Harness on Llama 3.3 70B

by DeepSeekCoding agent

DeepSeek Harness (dsh) is DeepSeek's open-source agent harness, released under MIT and built so that everything is a plugin, from the model adapter and the tool registry to the agent loop itself. Start it with npx @deepseek-ai/dsh web and it opens a local web UI where the agent reads and edits your workspace, runs commands, and keeps a plan, with a headless profile for one-shot jobs from the terminal. On Opper it runs on any of 700+ models rather than DeepSeek's own alone: add Opper as a custom provider and you get one key, automatic fallbacks, and a choice of region.

RunDeepSeek Harness logoDeepSeek Harnessonin

Connect DeepSeek Harness to Llama 3.3 70B

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

Llama 3.3 70B runs on the routes below. Route only to EU providers when your data has to stay in Europe.

ProviderRegionZero data retentionTrainingInputOutputCache read
EUNo$1.23$1.23Input price
EUNo$1.01$1.01Input price
USNo$0.67$1.34Input price
USNo$0.14$0.40Input price

The model

by Meta

Llama 3.3 70B Instruct: refined 70B model with improved multilingual performance, structured output, and tool calling for reasoning workloads.

Available on

Pricing from$0.14/ 1M input$0.40/ 1M output131Kcontext

Privacy

ZDR
Training
No
Region
EU + US

Run DeepSeek Harness on other models

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

More apps on Opper

Run DeepSeek Harness on Llama 3.3 70B

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