Skip to main content
DeepSeek provides powerful AI models with an OpenAI-compatible API.

​
Install plugin

Install the official plugin:
Installation applies to a running Gateway automatically; otherwise it takes effect on the next startup. See Apply changes and inspect.

​
Getting started

1

Get your API key

Create an API key at platform.deepseek.com.
2

Run onboarding

Prompts for your API key and sets deepseek/deepseek-v4-pro as the default model.
3

Verify models are available

To inspect the plugin’s static catalog without a running Gateway:
Onboarding preserves your model entries and leaves generated catalog rows to discovery. With models.mode: "replace", it also writes the built-in catalog because that mode skips discovery.
For scripted or headless installations, pass all flags directly:
If Gateway runs as a daemon (launchd/systemd), make sure DEEPSEEK_API_KEY is available to that process (for example, in ~/.openclaw/.env or via env.shellEnv).

​
Built-in catalog

DeepSeek retired deepseek-chat and deepseek-reasoner on July 24, 2026 at 15:59 UTC. Those model IDs are no longer accessible. Move configured model refs to deepseek/deepseek-v4-flash or deepseek/deepseek-v4-pro.
OpenClaw’s local costs are estimates. Canonical Flash uses DeepSeek’s peak rates: 0.30permillioninputtokens,0.30 per million input tokens, 1.20 per million output tokens, and $0.006 per million cached input tokens. Published off-peak rates are half those amounts. Legacy rows retain their earlier bundled metadata. DeepSeek still accepts deepseek-v4-flash and deepseek-v4-flash-vision-exp, routes them to V4.1 Flash, and bills them at current Flash rates. Existing explicit selections remain valid in OpenClaw. DeepSeek can change rates; its Models & Pricing page is authoritative for billing. For image inputs, select deepseek/deepseek-flash. The legacy deepseek/deepseek-v4-flash-vision-exp selection also retains image support. Canonical Flash accepts PNG, JPEG, GIF, and WebP images through the same API and API key. See DeepSeek vision for image limits.
Canonical Flash and 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 require replayed assistant messages from a thinking-enabled turn to include reasoning_content on follow-up requests. OpenClaw’s DeepSeek plugin backfills that field automatically, so normal multi-turn tool use works on deepseek/deepseek-flash, deepseek/deepseek-v4-flash, deepseek/deepseek-v4-flash-vision-exp, 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 disabled (including the UI None selection), OpenClaw sends thinking: { type: "disabled" } and strips replayed reasoning_content from outgoing history, keeping the session on the non-thinking DeepSeek path. Fresh onboarding selects deepseek/deepseek-v4-pro. To select canonical Flash:

​
Live testing

To run only the DeepSeek V4 direct-model checks from the modern model live suite:
Verifies both V4 models complete and that thinking/tool follow-up turns preserve the replay payload DeepSeek requires. To check the experimental vision model with the same DEEPSEEK_API_KEY:
This runs text, generated-image recognition, and thinking replay checks against the selected model.

​
Config example

Model selection

Choosing providers, model refs, and failover behavior.

ds4 local server

Running DeepSeek V4 Flash from a local OpenAI-compatible ds4 server.

Configuration reference

Full config reference for agents, models, and providers.