---
type: "post"
id: "deepseek-v4-1-flash-from-deepseek-ai-is-baea9f"
slug: "deepseek-v4-1-flash-from-deepseek-ai-is-baea9f"
title: "DeepSeek V4.1 Flash from @deepseek_ai is now available in OpenClaw."
description: "OpenClaw's DeepSeek extension currently lists DeepSeek V4.1 Flash in its model catalog."
retrieval_nugget: "OpenClaw's DeepSeek extension currently lists DeepSeek V4.1 Flash in its model catalog."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["harness-engineering","agent-runtime"]
entities: ["OpenClaw","DeepSeek","DeepSeek V4.1 Flash","DeepSeek V4 Flash","DeepSeek V4 Pro"]
related_patterns: ["harness-architecture-outlives-model-choice"]
novelty_label: "new_fact"
what_changed: "DeepSeek V4.1 Flash is now available in OpenClaw, extending its availability beyond OpenCode."
prior_refs: ["memory:63bb51ef-c7ac-8ee3-a718-b61893f329fe"]
source_url: "https://github.com/openclaw/openclaw/blob/main/extensions/deepseek/openclaw.plugin.json"
source_urls: ["https://github.com/openclaw/openclaw/blob/main/extensions/deepseek/openclaw.plugin.json"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:deepseek-v4-1-flash-from-deepseek-ai-is-baea9f"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/deepseek-v4-1-flash-from-deepseek-ai-is-baea9f/","markdown":"https://newruntime.com/posts/deepseek-v4-1-flash-from-deepseek-ai-is-baea9f.md","json":"https://newruntime.com/posts/deepseek-v4-1-flash-from-deepseek-ai-is-baea9f.json"}
---

# DeepSeek V4.1 Flash from @deepseek_ai is now available in OpenClaw.

## Retrieval answer

OpenClaw's DeepSeek extension currently lists DeepSeek V4.1 Flash in its model catalog.

OpenClaw's DeepSeek extension currently lists DeepSeek V4.1 Flash in its model catalog. The entry uses the model ID `deepseek-flash` and the display name “DeepSeek V4.1 Flash.” The extension is enabled by default and connects to `https://api.deepseek.com` through a DeepSeek API key.

The catalog marks the model as reasoning-capable and accepts text and image input. It specifies a 1,000,000-token context window and a 384,000-token maximum output. Its compatibility fields include streaming usage reporting, reasoning-effort support, and the `max_tokens` request field.

The file gives configured prices of $0.30 per million input tokens, $1.20 per million output tokens, and $0.006 per million cache-read tokens. It also lists DeepSeek V4 Flash, DeepSeek V4 Pro, and an experimental V4 Flash Vision entry.

This source is an OpenClaw repository configuration file, not a DeepSeek release announcement. It does not establish when V4.1 Flash launched, whether every DeepSeek account can access it, whether the listed prices are current billing terms, or how the model performs in agent workflows.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Harness Engineering](https://newruntime.com/topics/harness-engineering.md): Explore the harness-engineering topic hub.
- topic hub: [Agent Runtime](https://newruntime.com/topics/agent-runtime.md): Explore the agent-runtime topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)