DeepSeek: DeepSeek V4.1 Flash

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.

DeepSeekDeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash

2026-09-10text+image->textreasoning: max / high / low / none

Input

$0.04

per 1M tokens

Output

$0.50

per 1M tokens

Cached input

$0.02

per 1M tokens

Context

1.0M

tokens it reads

Max output

944K

tokens it writes

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...

inspect — the catalog entry

{
  "id": "deepseek/deepseek-v4.1-flash",
  "canonical_slug": "deepseek/deepseek-v4.1-flash-20260910",
  "hugging_face_id": "deepseek-ai/DeepSeek-V4.1-Flash",
  "name": "DeepSeek: DeepSeek V4.1 Flash",
  "created": 1789021285,
  "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...",
  "context_length": 1048576,
  "architecture": {
    "modality": "text+image->text",
    "input_modalities": [
      "text",
      "image"
    ],
    "output_modalities": [
      "text"
    ],
    "tokenizer": "DeepSeek",
    "instruct_type": null
  },
  "pricing": {
    "prompt": "0.000000045",
    "completion": "0.0000005",
    "input_cache_read": "0.000000018"
  },
  "top_provider": {
    "context_length": 1048576,
    "max_completion_tokens": 943718,
    "is_moderated": false
  },
  "per_request_limits": null,
  "supported_parameters": [
    "frequency_penalty",
    "include_reasoning",
    "logit_bias",
    "logprobs",
    "max_tokens",
    "min_p",
    "parallel_tool_calls",
    "presence_penalty",
    "reasoning",
    "reasoning_effort",
    "repetition_penalty",
    "response_format",
    "seed",
    "stop",
    "structured_outputs",
    "temperature",
    "tool_choice",
    "tools",
    "top_a",
    "top_k",
    "top_logprobs",
    "top_p"
  ],
  "default_parameters": {},
  "supported_voices": null,
  "knowledge_cutoff": null,
  "expiration_date": null,
  "links": {
    "details": "/api/v1/models/deepseek/deepseek-v4.1-flash-20260910/endpoints"
  },
  "endpoints": [
    "/api/v1/chat/completions",
    "/api/v1/completions",
    "/api/v1/messages",
    "/api/v1/responses"
  ],
  "reasoning": {
    "mandatory": false,
    "default_enabled": true,
    "supported_efforts": [
      "max",
      "high",
      "low",
      "none"
    ],
    "default_effort": "high"
  },
  "benchmarks": null
}

openrouter.ai/deepseek/deepseek-v4.1-flash

References (1)

Stored model catalog — Nov 5, 2026

Via: OpenRouter
Id: openrouter/deepseek/deepseek-v4.1-flash
Model id: deepseek/deepseek-v4.1-flash
Name: DeepSeek: 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.
Family: deepseek
Canonical slug: deepseek/deepseek-v4.1-flash-20260910
Price in: 0.045
Price out: 0.5
Price cache read: 0.018
Price cache write: null
Price cache write 1h: null
Price web search: null
Price overrides: []
Context: 1048576
Max completion tokens: 943718
Modality: text+image->text
Input modalities: ["text","image"]
Output modalities: ["text"]
Tokenizer: DeepSeek
Knowledge cutoff: null
Created: 1789021285
Moderated: false
Params: ["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"]
Default parameters: {}
Tools: true
Reasoning: true
Reasoning efforts: ["max","high","low","none"]
Reasoning default effort: high
Reasoning mandatory: false
Reasoning default enabled: true
Vision: true
Expiration date: null

Page data

Open JSON

page.json

{
  "schema": "page/1",
  "id": "model:openrouter/deepseek/deepseek-v4.1-flash",
  "kind": "AIModel",
  "title": "DeepSeek: DeepSeek V4.1 Flash",
  "layout": "item",
  "status": "published",
  "summary": "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.",
  "body": [
    {
      "type": "model",
      "id": "deepseek/deepseek-v4.1-flash"
    }
  ],
  "hero": "",
  "facts": {
    "via": "OpenRouter",
    "id": "openrouter/deepseek/deepseek-v4.1-flash",
    "model_id": "deepseek/deepseek-v4.1-flash",
    "name": "DeepSeek: 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.",
    "family": "deepseek",
    "canonical_slug": "deepseek/deepseek-v4.1-flash-20260910",
    "price_in": 0.045,
    "price_out": 0.5,
    "price_cache_read": 0.018,
    "price_cache_write": null,
    "price_cache_write_1h": null,
    "price_web_search": null,
    "price_overrides": [],
    "context": 1048576,
    "max_completion_tokens": 943718,
    "modality": "text+image->text",
    "input_modalities": [
      "text",
      "image"
    ],
    "output_modalities": [
      "text"
    ],
    "tokenizer": "DeepSeek",
    "knowledge_cutoff": null,
    "created": 1789021285,
    "moderated": false,
    "params": [
      "frequency_penalty",
      "include_reasoning",
      "logit_bias",
      "logprobs",
      "max_tokens",
      "min_p",
      "parallel_tool_calls",
      "presence_penalty",
      "reasoning",
      "reasoning_effort",
      "repetition_penalty",
      "response_format",
      "seed",
      "stop",
      "structured_outputs",
      "temperature",
      "tool_choice",
      "tools",
      "top_a",
      "top_k",
      "top_logprobs",
      "top_p"
    ],
    "default_parameters": {},
    "tools": true,
    "reasoning": true,
    "reasoning_efforts": [
      "max",
      "high",
      "low",
      "none"
    ],
    "reasoning_default_effort": "high",
    "reasoning_mandatory": false,
    "reasoning_default_enabled": true,
    "vision": true,
    "expiration_date": null
  },
  "sources": [
    {
      "title": "Stored model catalog",
      "url": "https://openrouter.ai/api/v1/models",
      "date": "2026-11-05T11:17:13.538Z"
    }
  ],
  "widgets": [],
  "members": [],
  "relations": [
    {
      "ref": "provider:deepseek.com",
      "rel": "published by"
    }
  ],
  "media": [],
  "tags": [],
  "query": {},
  "created": "2026-11-05T11:17:13.538Z",
  "updated": "2026-11-05T11:17:13.538Z",
  "provenance": {
    "store": "model-catalog",
    "id": "openrouter/deepseek/deepseek-v4.1-flash",
    "key": "state/models/catalogue.json",
    "original_id": "openrouter/deepseek/deepseek-v4.1-flash",
    "source_kind": "AIModel",
    "source_provider": "OpenRouter",
    "hash": "c7be90b52f1a94b096df6aea527571a9e9c6366f48fc281dce60f7a85ec4a65d"
  },
  "version": "ea9b32a4d7374a4574d7cf0efb5415cb9eeda60fd2a6758f398c94814564c0f7"
}

the whole object this page is drawn from, as JSON · Open JSON

{
  "schema": "page/1",
  "id": "model:openrouter/deepseek/deepseek-v4.1-flash",
  "kind": "AIModel",
  "title": "DeepSeek: DeepSeek V4.1 Flash",
  "layout": "item",
  "status": "published",
  "summary": "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.",
  "body": [
    {
      "type": "model",
      "id": "deepseek/deepseek-v4.1-flash"
    }
  ],
  "hero": "",
  "facts": {
    "via": "OpenRouter",
    "id": "openrouter/deepseek/deepseek-v4.1-flash",
    "model_id": "deepseek/deepseek-v4.1-flash",
    "name": "DeepSeek: 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.",
    "family": "deepseek",
    "canonical_slug": "deepseek/deepseek-v4.1-flash-20260910",
    "price_in": 0.045,
    "price_out": 0.5,
    "price_cache_read": 0.018,
    "price_cache_write": null,
    "price_cache_write_1h": null,
    "price_web_search": null,
    "price_overrides": [],
    "context": 1048576,
    "max_completion_tokens": 943718,
    "modality": "text+image->text",
    "input_modalities": [
      "text",
      "image"
    ],
    "output_modalities": [
      "text"
    ],
    "tokenizer": "DeepSeek",
    "knowledge_cutoff": null,
    "created": 1789021285,
    "moderated": false,
    "params": [
      "frequency_penalty",
      "include_reasoning",
      "logit_bias",
      "logprobs",
      "max_tokens",
      "min_p",
      "parallel_tool_calls",
      "presence_penalty",
      "reasoning",
      "reasoning_effort",
      "repetition_penalty",
      "response_format",
      "seed",
      "stop",
      "structured_outputs",
      "temperature",
      "tool_choice",
      "tools",
      "top_a",
      "top_k",
      "top_logprobs",
      "top_p"
    ],
    "default_parameters": {},
    "tools": true,
    "reasoning": true,
    "reasoning_efforts": [
      "max",
      "high",
      "low",
      "none"
    ],
    "reasoning_default_effort": "high",
    "reasoning_mandatory": false,
    "reasoning_default_enabled": true,
    "vision": true,
    "expiration_date": null
  },
  "sources": [
    {
      "title": "Stored model catalog",
      "url": "https://openrouter.ai/api/v1/models",
      "date": "2026-11-05T11:17:13.538Z"
    }
  ],
  "widgets": [],
  "members": [],
  "relations": [
    {
      "ref": "provider:deepseek.com",
      "rel": "published by"
    }
  ],
  "media": [],
  "tags": [],
  "query": {},
  "created": "2026-11-05T11:17:13.538Z",
  "updated": "2026-11-05T11:17:13.538Z",
  "provenance": {
    "store": "model-catalog",
    "id": "openrouter/deepseek/deepseek-v4.1-flash",
    "key": "state/models/catalogue.json",
    "original_id": "openrouter/deepseek/deepseek-v4.1-flash",
    "source_kind": "AIModel",
    "source_provider": "OpenRouter",
    "hash": "c7be90b52f1a94b096df6aea527571a9e9c6366f48fc281dce60f7a85ec4a65d"
  },
  "version": "ea9b32a4d7374a4574d7cf0efb5415cb9eeda60fd2a6758f398c94814564c0f7"
}

Connected subjects

DeepSeek