Open models DeepSeek DeepSeek V4.1 Flash

DeepSeek V4.1 Flash

Available

deepseek-ai/DeepSeek-V4.1-Flash

Get API key Chat Completions API reference

Pricing

Pay per token

Input / million

USD0.14

Cached input / million

USD0.03

Output / million

USD0.58

Cache hit rate

97.8%last 24 hours

Access

Provider: DeepSeek
API compatibility: Chat-compatible, POST /v1/chat/completions
Messages compatibility: Messages-compatible, POST /v1/messages
Accepted input: Text
Availability: Available
Data retention: Read the policy

Capacity

Context window: 1,048,576 tokens
Maximum generated output: 32,768 tokens

Capabilities

Tool calling: Supported
JSON mode: Supported
Streaming: Supported

View full spec

Model ID: deepseek-v4-1-flash
API model ID: deepseek-ai/DeepSeek-V4.1-Flash
Kind: Chat
Prompt caching: Supported
Reasoning effort: none, low, high, xhigh, max

Code examples

# Set RUNINFRA_GATEWAY_KEY to your API key before running this example.
curl -X POST "https://api.runinfra.ai/v1/chat/completions" \
  -H "Authorization: Bearer $RUNINFRA_GATEWAY_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4-1-flash","messages":[{"role":"user","content":"Hello"}],"max_tokens":16384}'

Trust and provenance

RightNow AI is a YC-backed GPU research lab.