DeepSeek V4.1 Flash 1017

Incognito

deepseek/deepseek-v4.1-flash-1017

October 17, 2026 snapshot of DeepSeek V4.1 Flash, a reasoning and coding model with image understanding. Served through OpenRouter using zero data retention inference endpoints.

Input / 1M tokens: $0.3
Output / 1M tokens: $1.2
Cache read / 1M tokens: $0.006
Context window: 1048K tokens

Privacy & execution

This Incognito model runs on a partner provider’s infrastructure. NEAR AI routes requests using shared provider credentials, so your NEAR AI account credentials are not forwarded.

Your prompts are processed by the provider under its terms and privacy policy. HTTPS protects data in transit. Model TEE attestation and client-to-model end-to-end encryption are not provided for this model. Where available, Gateway signatures verify the request and response handled by the Gateway.

Verification documentation

Make your first request

Call /v1/chat/completions over HTTPS.

Get an API key and set the NEARAI_API_KEY environment variable.

curl --fail-with-body "https://cloud-api.near.ai/v1/chat/completions" \
  -H "Authorization: Bearer $NEARAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek/deepseek-v4.1-flash-1017",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

This HTTP example uses HTTPS. Use the SDK below to verify Gateway attestation and response signatures.

Build and Verify with the SDK

Let the inference client verify the Gateway and its response signatures.

Verification guide

Setup

npm install @nearai/inference-sdk openai

Example

import OpenAI from "openai";
import { InferenceClient } from "@nearai/inference-sdk/node";

const apiKey = process.env.NEARAI_API_KEY;
if (!apiKey) throw new Error("Set NEARAI_API_KEY first.");

// Verify the Gateway. Incognito models do not support model attestation or field E2EE.
const inferenceClient = new InferenceClient({
  apiKey,
  baseUrl: "https://cloud-api.near.ai/v1",
  e2ee: false,
});

const openai = new OpenAI({
  apiKey,
  baseURL: inferenceClient.getBaseUrl(),
  fetch: inferenceClient.fetch,
});

const completion = await openai.chat.completions.create({
  model: "deepseek/deepseek-v4.1-flash-1017",
  messages: [{ role: "user", content: "Hello!" }],
});

// Verify the exact request/response bytes before displaying the answer.
const verified = await inferenceClient.verifyResponse(completion.id);
console.log(completion.choices[0]?.message.content ?? "");
console.log("Verified signer:", verified.signatureKind);

JavaScript SDK guide