Private DeepSeek V4.1 Flash API
General purpose, coding, long context. Runs on Confidential Inference: an OpenAI-compatible endpoint inside TEEs. Fully verifiable.
How much does DeepSeek V4.1 Flash cost on Confidential AI?
| Status | Input (per 1M tokens) | Input Cached (per 1M tokens) | Output (per 1M tokens) |
|---|---|---|---|
| Live | $0.30 | $0.03 | $1.20 |
Prices as of .
How do I call DeepSeek V4.1 Flash?
Point any OpenAI-compatible client at https://api.confidential.ai/v1 with your API key and the model ID deepseek-ai/DeepSeek-V4.1-Flash-1017:
curl https://api.confidential.ai/v1/chat/completions \
-H "Authorization: Bearer $CONFIDENTIAL_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek-ai/DeepSeek-V4.1-Flash-1017", "messages": [{"role": "user", "content": "Hello"}]}'Guides: OpenAI SDK, LangChain, Vercel AI SDK, LiteLLM. API keys are issued by email: get started.
Is DeepSeek V4.1 Flash private on Confidential AI?
Yes. The model runs inside trusted execution environments: Intel TDX confidential VMs with NVIDIA GPUs in confidential computing mode. Prompts and responses stay invisible to the operator, Confidential AI included. Your client can fetch and verify the attestation before it sends anything. See attestation, or verify our production cluster in your browser.
How much slower is confidential inference?
About 1 to 3% lower token throughput on NVIDIA B200s for a correctly configured stack, with negligible impact on time to first token. Method and other measurements: performance overhead.
Full pricing: pricing.