TEXT → TEXT · DeepSeek

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window.

Censorship unknown

PRICE0.0018 creditsper 1k tokens

AVG TIME~20sestimate

OUTPUTtextsync

Open in playground

Inputs

promptrequired · text

textoptional · Context — artifact id or https URL

imageoptional · Image — artifact id or https URL

Monthly estimate

1k tokenss per month

1,000 × 0.0018 credits1.80 credits

curl https://platform.4i.app/api/v1/run \
  -H "Authorization: Bearer $FOURI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "deepseek/deepseek-v4-1-flash",
    "input": {
      "prompt": "Ask for some text, or about an attached image…"
    }
  }'

Every output has an artifact_id. Pass it as input to any compatible service.

Get your API key →