Overview
DeepSeek V4.1 Flash (the 1017 release) is DeepSeek's open-weights mixture-of-experts model, a minor update that DeepSeek says improves reasoning, coding, agentic tasks and visual benchmarks. It accepts text interleaved with images, supports tool calling and a thinking mode, and is served here with a 1M-token context window.
Strengths
- Reasoning, coding and agentic tasks in one model
- Image input alongside text
- 1M-token context window
Use cases
- Coding agents that work over large codebases or long histories
- Questions over long documents, screenshots and charts
Good to know
Text and image input only on this alias; no video or audio. Thinking is on unless turned off, and the reasoning counts against max_tokens: with a small budget the whole budget can go to reasoning, returning empty content with finish_reason "length". Turn thinking off or allow a few thousand output tokens.
API access
One OpenAI-compatible API for every model in the catalog, plus the CLI and the function SDK inside workflows. Sign up free, add a card for $5 in credits, and these requests work:
curl https://gateway.graphn.ai/v1/chat/completions \
-H "Authorization: Bearer $GRAPHN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4.1-flash",
"messages": [{"role": "user", "content": "Hello"}]
}'graphn model chat deepseek-v4.1-flash -m "What is GraphN?"
@function
async def ask(question: str) -> str:
return await chat.complete(question, model="deepseek-v4.1-flash")