AI Model Providers

DeepSeek

Use DeepSeek V4 Flash and V4 Pro directly from Autohand through DeepSeek's OpenAI-compatible API.

Overview

DeepSeek is a good fit for coding, reasoning, and cost-sensitive agent sessions. Autohand supports the deepseek provider with API-key authentication and model switching through /model.

Setup

  1. Create a DeepSeek API key from the DeepSeek platform.
  2. Set DEEPSEEK_API_KEY or save the key in Autohand config.
  3. Select a DeepSeek model during setup or with /model.
export DEEPSEEK_API_KEY="your-deepseek-api-key"

autohand --provider deepseek --model deepseek-v4-flash

CLI configuration

{
  "provider": "deepseek",
  "deepseek": {
    "apiKey": "${DEEPSEEK_API_KEY}",
    "baseUrl": "https://api.deepseek.com",
    "model": "deepseek-v4-flash"
  }
}
OptionDescriptionDefault
apiKeyYour DeepSeek API key-
baseUrlDeepSeek API endpointhttps://api.deepseek.com
modelDeepSeek model IDdeepseek-v4-flash

Models

ModelBest for
deepseek-v4-flashFast default model for coding and agent loops
deepseek-v4-proStronger reasoning and code review
deepseek-chatLegacy non-thinking alias
deepseek-reasonerLegacy reasoning alias

Troubleshooting

IssueFix
Invalid API keyCheck DEEPSEEK_API_KEY or deepseek.apiKey.
Model not foundUse deepseek-v4-flash or deepseek-v4-pro.
Network or proxy issuesSet deepseek.baseUrl only when routing through an approved proxy.