MODELS / DEEPSEEK

DeepSeek V4.1 Flash Fast

Speed-optimized deployment of DeepSeek V4.1 Flash using tensor parallelism and DSpark speculative decoding for faster token output and lower latency.

TEXTREASONINGIMPLICIT-CACHINGREASONINGSTRUCTURED-OUTPUTTOOL-USEVISION
1.0M
CONTEXT WINDOW
1M
MAX OUTPUT TOKENS
$0.3
INPUT PRICE / 1M TOKENS
$1.20
OUTPUT PRICE / 1M TOKENS
QUICKSTART

Call it in one request.

OpenAI-compatible: change the base URL, and the setup is complete.

curl https://enterprise.blackbox.ai/v1/chat/completions \
  -H "Authorization: Bearer $BLACKBOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "blackboxai/deepseek/deepseek-v4.1-flash-fast",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
SPECIFICATIONS

The full spec sheet.

Context, pricing, modalities, routing, and deployment: everything DeepSeek V4.1 Flash Fast supports, in one table.

MODEL ID
blackboxai/deepseek/deepseek-v4.1-flash-fast
DEVELOPED BY
DeepSeek
MODEL TYPE
Text
RELEASED
Sep 29, 2026
CONTEXT WINDOW
1.0M
MAX OUTPUT TOKENS
1M
INPUT MODALITIES
text, image
OUTPUT MODALITIES
text
INPUT PRICE
$0.3 / 1M tokens
OUTPUT PRICE
$1.20 / 1M tokens
CACHE READ
$0.006 / 1M tokens
REASONING
Supported
DATA RETENTION
Standard retention
DEDICATED DEPLOYMENT
Enterprise · single-tenant
SUPPORTED PARAMETERS
max_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs