MODELS / DEEPSEEK

DeepSeek V3.1

DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens. Additionally, DeepSeek-V3.1 is trained using the UE8M0 FP8 scale data format to ensure compatibility with microscaling data formats.

TEXTREASONINGIMPLICIT-CACHINGREASONINGTOOL-USE
163.8K
CONTEXT WINDOW
128K
MAX OUTPUT TOKENS
$0.25 / 1M tokens
INPUT PRICE
$0.95 / 1M tokens
OUTPUT PRICE
QUICKSTART

Call it in one request.

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

SHELL
curl https://enterprise.blackbox.ai/v1/chat/completions \
  -H "Authorization: Bearer $BLACKBOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "blackboxai/deepseek/deepseek-v3.1",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
INPUT: textOUTPUT: textRELEASED: 2025-08-21
RELATED MODELS

Also worth a look.

DEEPSEEK

DeepSeek V3 0324

163.8K context · $0.27 / 1M tokens input · $1.12 / 1M tokens output

DEEPSEEK

DeepSeek V3.1 Terminus

131.1K context · $0.27 / 1M tokens input · $1 / 1M tokens output

DEEPSEEK

DeepSeek V3.2

128K context · $0.28 / 1M tokens input · $0.42 / 1M tokens output