Guide
OpenClaw + DeepSeek V4: Use DeepSeek V4 Pro and V4 Flash with OpenClaw
DeepSeek's fourth-generation models are live on OpenClaw. 1M context window, strong reasoning, and ultra-low pricing — pick Pro for frontier quality or Flash for the lowest cost per token.
What Is DeepSeek V4?
DeepSeek is a Chinese AI lab known for open, cost-efficient frontier models. DeepSeek V4 is the fourth-generation family and ships in two flavors: V4 Pro for frontier reasoning and coding quality, and V4 Flash for the lowest cost per token with near-Pro intelligence on most tasks. Both support a 1M token context window.
Compared to the prior V3.2 release, V4 trades a larger context window (128K → 1M), better coding and agentic tool use, and a cleaner Pro/Flash split so you can match the model to the workload instead of paying Pro prices for Flash-sized work.
DeepSeek V4 Pro vs V4 Flash
| Model | Context | Input (per 1M) | Output (per 1M) | Best for |
|---|---|---|---|---|
| DeepSeek V4 Pro | 1M tokens | $1.74 | $3.48 | Frontier reasoning, complex coding, long-document analysis |
| DeepSeek V4 Flash | 1M tokens | $0.14 | $0.28 | High-volume chat, agent tool loops, day-to-day coding |
V4 Flash is the budget workhorse — roughly 10–20× cheaper than Claude Sonnet or GPT-5.2 on input tokens, so your AI credits go a long way. V4 Pro is still cheaper than most frontier models, but you get a noticeable quality lift on hard reasoning, multi-file refactors, and nuanced instruction-following.
How to Deploy DeepSeek V4 with OpenClaw Launch
The fastest path is through OpenClaw Launch — no API key needed, everything routes through the included AI credits via OpenRouter.
- Go to openclawlaunch.com and open the configurator.
- In the model dropdown, pick DeepSeek V4 Flash for the cheapest per-token cost, or DeepSeek V4 Pro for frontier quality.
- Pick your chat platform (Telegram, Discord, WhatsApp, WeChat, or browser gateway).
- Click Deploy. Your DeepSeek V4 agent is live in about 10 seconds.
/model chat command — no redeploy needed. A common pattern is Flash for everyday chat and Pro for hard coding sessions.Self-Hosted Configuration
If you run OpenClaw on your own server, configure OpenRouter as a provider in your openclaw.json and point the default agent at either V4 Pro or V4 Flash:
{
"models": {
"providers": {
"openrouter": {
"apiKey": "sk-or-..."
}
}
},
"agents": {
"defaults": {
"model": {
"primary": "openrouter/deepseek/deepseek-v4-flash"
}
}
}
}Swap deepseek-v4-flash for deepseek-v4-pro to route to the Pro variant instead. Grab an OpenRouter key at openrouter.ai/keys.
Which DeepSeek V4 Model Should You Pick?
A simple heuristic:
- Pick V4 Flash if you run high-volume chat, agent tool loops, or general coding. It's the best cost-per-quality ratio in the DeepSeek lineup and works great as the default model for Telegram and Discord bots.
- Pick V4 Pro if you need frontier-class reasoning — complex multi-file refactors, architecture discussions, long-document analysis across that full 1M context, or tasks where Flash occasionally slips on nuance.
- Run both if you want — one instance per role, or swap at runtime with
/model.
DeepSeek V4 vs Other Frontier Models
| Model | Input (per 1M) | Output (per 1M) | Context | Notes |
|---|---|---|---|---|
| DeepSeek V4 Flash | $0.14 | $0.28 | 1M | Cheapest frontier-adjacent model in the lineup |
| DeepSeek V4 Pro | $1.74 | $3.48 | 1M | Frontier reasoning, strong coding |
| Claude Sonnet 4.6 | $3.00 | $15.00 | 200K | Best nuanced reasoning and creative writing |
| GPT-5.4 | $2.50 | $15.00 | 1M+ | Strong general-purpose model with vision |
| Gemini 3.1 Pro | $2.00 | $12.00 | 1M | Multimodal with video input |
DeepSeek V4 Flash is a standout on pure cost-efficiency, and V4 Pro closes most of the gap to Claude Sonnet / GPT-5.4 at roughly half the price on input tokens.
BYOK with DeepSeek V4
If you already have an OpenRouter account or a direct DeepSeek API key, you can bring it to OpenClaw Launch via BYOK. In the configurator, select BYOK and paste your OpenRouter key — all requests route through your key and your own billing.
What's Next?
- Add skills to your agent — 3,200+ skills for search, coding, automation, and more
- Compare all models — See how V4 Pro and V4 Flash stack up against Claude, GPT, Gemini, and others
- See pricing — Deploy with AI credits included, starting at $3/month
- Set up Telegram — Connect your DeepSeek V4 agent to Telegram