Use DeepSeek with Codex

Configure Codex CLI against a DeepSeek OpenAI-compatible endpoint. Source-level recipe — AgentRunDB runs pending.

● Backed by 0 AgentRunDB runs

Goal: Run Codex CLI with DeepSeek as the backend model.

agent: codex
model: deepseek
Tested versions: Codex 0.x · deepseek-chat

Working Configuration

# ~/.codex/config.toml
model = "deepseek-chat"
model_provider = "deepseek"

[model_providers.deepseek]
name = "deepseek"
base_url = "https://api.deepseek.com/v1"
wire_api = "chat"

Steps

Get a DeepSeek API key
Add the provider block above to your Codex config
codex and verify the model connects

Status: configuration from official docs — AgentRunDB verification runs are queued. This page will update with real data.