Model detail

deepseek-v4.1-flash-1017

1,048,576 token context · 310 ms first-token latency

Price breakdown

Model pricing
Model Context Input Output Cached input Latency
deepseek-v4.1-flash-1017 1,048,576 tokens $0.345 $1.38 $0.172 310 ms

Try this model

curl https://inference-api.example.com/v1/chat/completions \
  -H "Authorization: Bearer $INFRA_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"model":"deepseek-v4.1-flash-1017","messages":[{"role":"user","content":"Hello"}]}'