DeepSeek V4.1 Flash

Name: DeepSeek V4.1 Flash
Author: DeepSeek

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on..

by DeepSeek(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Reference model card from the OpenRouter listing - model deepseek/deepseek-v4.1-flash. Prices are per million tokens as listed; ratings and installs below are from this marketplace.

DeepSeek V4.1 Flash

Facts


Vendor	DeepSeek
Context window	1,048,576 tokens
Max output	384,000 tokens
Input price	$0.15 / 1M tokens
Output price	$0.60 / 1M tokens
Input	text, image
Output	text
Tool calling	yes
Structured outputs	yes
Reasoning	yes
Open weights	deepseek-ai/DeepSeek-V4.1-Flash

Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model deepseek/deepseek-v4.1-flash

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - nothing else to configure
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
# or pin it on the OpenAI-compatible endpoint: {"model": "model-deepseek-deepseek-v4-1-flash", ...}

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

model-deepseek-deepseek-v4-1-flash.ocm.jsonjson

{
  "ocm": "1",
  "id": "model-deepseek-deepseek-v4-1-flash",
  "kind": "llm",
  "name": "DeepSeek V4.1 Flash",
  "description": "DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...",
  "publisher": "DeepSeek",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "llm",
      "deepseek",
      "openrouter",
      "open-weights",
      "reasoning",
      "tool-calling",
      "image",
      "models"
    ],
    "languages": [
      "en"
    ],
    "modalities": [
      "text",
      "image"
    ],
    "supports_tools": true,
    "supports_streaming": true,
    "context_window": 1048576
  },
  "quality_prior": 0.395,
  "examples": [
    "DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on..."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "models",
      "ref": "1789021285",
      "url": "https://openrouter.ai/deepseek/deepseek-v4.1-flash",
      "key": "deepseek/deepseek-v4.1-flash",
      "catalogue": "https://openrouter.ai/api/v1"
    },
    "model": "deepseek/deepseek-v4.1-flash",
    "pricing": {
      "input_usd_per_1m": 0.15,
      "output_usd_per_1m": 0.6,
      "cache_read_usd_per_1m": 0.003
    },
    "max_output_tokens": 384000,
    "output_modalities": [
      "text"
    ],
    "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
    "reasoning": true,
    "created": 1789021285,
    "benchmarks": {
      "intelligence_index": 39.5,
      "hub_downloads": 429865,
      "hub_downloads_total": 429865,
      "hub_likes": 3135,
      "hub_trending": 1050,
      "osr_index": 42.8,
      "osr_coverage": 0.4
    }
  },
  "cost": {
    "usd_per_1k_tokens": 0.000375
  },
  "endpoints": [
    {
      "protocol": "openai",
      "url": "https://openrouter.ai/api/v1"
    }
  ]
}

Fetch it by URL: GET /api/v1/registry/model-deepseek-deepseek-v4-1-flash/manifest?version=1.0.0

About

DeepSeek V4.1 Flash

Facts

Use it

Manifest

Reviews