DeepSeek V4 Pro
lx1-deepseek-v4-proCodingLive in the catalogThe top of the V4 line: a 1.6-trillion-parameter mixture-of-experts with 49 billion active per token, post-trained specifically for agentic work — long tool chains, multi-step automation, changes that span a whole repository. It reasons before it answers, and it will stream that reasoning to you if you ask to see it. Latency varies more here than elsewhere in this tier, so spend it where the quality of the plan decides the outcome rather than where the stopwatch does.
- 01Post-trained for agentic coding and long tool chains
- 02Streams its reasoning, so you can watch it work
- 031M-token context for repository- and corpus-scale tasks
Strict, schema-faithful tool calls, enforced by the engine on every request — safe to build an agent loop on.
Thinks before it answers. Budget max_tokens generously — hidden reasoning counts against it.
Text-only.
One endpoint. Served by our engine.
DeepSeek V4 Pro is served through the Layer X1 engine — zero-downtime serving is the design target, not a status-page apology. You request it by name; everything else is our problem.
curl https://api.layerx1.com/v1/messages \
-H "x-api-key: lx1_your_key" \
-H "content-type: application/json" \
-d '{
"model": "lx1-deepseek-v4-pro",
"max_tokens": 1024,
"messages": [{ "role": "user", "content": "Hello" }]
}'OpenAI-style clients work too — send the same model name to /v1/chat/completions with a Bearer key. See the docs for both dialects.
Your agent stays the same.
Its inference gets better.
Start free · no card · Starter from $5/mo