DeepSeek Provider Setup

DeepSeek offers powerful AI models through an API that works with OpenAI's format.

Property	Value
Provider	`deepseek`
Auth	`DEEPSEEK_API_KEY`
API	OpenAI-compatible
Base URL	`https://api.deepseek.com`

Install plugin

Install the official plugin, then restart Gateway:

openclaw plugins install @openclaw/deepseek-provider
openclaw gateway restart

Getting started

Get your API key

Generate an API key at platform.deepseek.com.

Run onboarding

openclaw onboard --auth-choice deepseek-api-key

Prompts you for your API key and sets deepseek/deepseek-v4-flash as the default model.

Verify models are available

openclaw models list --provider deepseek

To view the plugin's static catalog without a running Gateway:

openclaw models list --all --provider deepseek

Non-interactive setup

For scripted or headless setups, provide all flags directly:

openclaw onboard --non-interactive \
  --mode local \
  --auth-choice deepseek-api-key \
  --deepseek-api-key "$DEEPSEEK_API_KEY" \
  --skip-health \
  --accept-risk

Warning

If Gateway runs as a daemon (launchd/systemd), confirm that DEEPSEEK_API_KEY is accessible to that process (for example, in ~/.openclaw/.env or through env.shellEnv).

Built-in catalog

Model ref	Name	Input	Context	Max output	Notes
`deepseek/deepseek-v4-flash`	DeepSeek V4 Flash	text	1,000,000	384,000	Default model; V4 thinking-capable surface
`deepseek/deepseek-v4-pro`	DeepSeek V4 Pro	text	1,000,000	384,000	V4 thinking-capable surface
`deepseek/deepseek-chat`	DeepSeek Chat	text	1,000,000	384,000	Deprecated V4 Flash non-thinking compatibility name
`deepseek/deepseek-reasoner`	DeepSeek Reasoner	text	1,000,000	384,000	Deprecated V4 Flash thinking compatibility name

Warning

DeepSeek will remove deepseek-chat and deepseek-reasoner on July 24, 2026 at 15:59 UTC. They currently route to DeepSeek V4 Flash in non-thinking and thinking mode, respectively. Move configured model refs to deepseek/deepseek-v4-flash or deepseek/deepseek-v4-pro before the cutoff.

OpenClaw's local cost estimates follow DeepSeek's published cache-hit, cache-miss, and output rates. DeepSeek can adjust those rates; its Models & Pricing page is authoritative for billing.

Tip

V4 models support DeepSeek's thinking control. OpenClaw also replays DeepSeek reasoning_content on follow-up turns so thinking sessions with tool calls can continue. Use /think xhigh or /think max with DeepSeek V4 models to request DeepSeek's maximum reasoning_effort; both map to "max".

Thinking and tools

DeepSeek V4 thinking sessions need replayed assistant messages from a thinking-enabled turn to include reasoning_content on follow-up requests. OpenClaw's DeepSeek plugin fills that field in automatically, so normal multi-turn tool use works on deepseek/deepseek-v4-flash and deepseek/deepseek-v4-pro even when history came from another OpenAI-compatible provider (no native reasoning_content) or from a plain assistant message. No /new required after switching providers mid-session.

When thinking is off (including the UI None selection), OpenClaw sends thinking: { type: "disabled" } and removes replayed reasoning_content from outgoing history, keeping the session on the non-thinking DeepSeek path.

Use deepseek/deepseek-v4-flash for the default fast path. Use deepseek/deepseek-v4-pro for the stronger model when you can accept higher cost or latency.

Live testing

To run only the DeepSeek V4 direct-model checks from the modern model live suite:

OPENCLAW_LIVE_PROVIDERS=deepseek \
OPENCLAW_LIVE_MODELS="deepseek/deepseek-v4-flash,deepseek/deepseek-v4-pro" \
pnpm test:live src/agents/models.profiles.live.test.ts

Verifies both V4 models complete and that thinking/tool follow-up turns preserve the replay payload DeepSeek requires.

Config example

{
  env: { DEEPSEEK_API_KEY: "sk-..." },
  agents: {
    defaults: {
      model: { primary: "deepseek/deepseek-v4-flash" },
    },
  },
}

Model selection, Choosing providers, model refs, and failover behavior.
Configuration reference, Full config reference for agents, models, and providers.