deepseek-ai/DeepSeek-V4-Flash

Input / M tokens

$0.17

Output / M tokens

$0.35

Cache read

$0.035

Context

1048K

Sample code and API for DeepSeek V4 Flash

fetch("https://cloud-api.near.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR-NEAR-AI-CLOUD-API-KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "deepseek-ai/DeepSeek-V4-Flash",
    "messages": [
      {
        "role": "user",
        "content": "What is the meaning of life?"
      }
    ]
  })
})

You can also use NEAR AI Cloud with OpenAI's client API:

import OpenAI from "openai"

const openai = new OpenAI({
  baseURL: "https://cloud-api.near.ai/v1",
  apiKey: "<YOUR-NEAR-AI-CLOUD-API-KEY>",
})

async function main() {
  const completion = await openai.chat.completions.create({
    messages: [{ "role": "user", "content": "What is the meaning of life?" }],
    model: "deepseek-ai/DeepSeek-V4-Flash",
  })

  console.log(completion.choices[0])
}
main()

Verify DeepSeek V4 Flash

This model is hosted in a GPU TEE. TEE enables strong privacy with end-to-end encryption for data in transmission and in use. TEE protects the entire lifecycle of the model inference and gives you a proof of the execution. It allows you to verify that the given a model and an input, it produces a specific output both onchain and offchain.

Check out the docs for more details.

Get the attestation report.

curl 'https://cloud-api.near.ai/v1/attestation/report?model=deepseek-ai/DeepSeek-V4-Flash' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer <NEAR_AI_CLOUD_API_KEY>'

Retrieve the response signature using the chat completion ID. Signatures are available for 5 minutes.

CHAT_ID=chatcmpl-4af9...
curl 'https://cloud-api.near.ai/v1/signature/${CHAT_ID}?model=deepseek-ai/DeepSeek-V4-Flash&signing_algo=ecdsa' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer <NEAR_AI_CLOUD_API_KEY>'