Model detail

`deepseek/deepseek-v4.1-flash`

Opt-in LINE comparison pilot; fallback follows the Router's configured policy. Catalog prices are list prices, not a promise of free credits. Qwen cache rate is for implicit cache; explicit-cache creation/read is not enabled by this route.

Playground Endpoints All Models

Provider

DeepSeek

Context

128K

tokens

Max output

33K

tokens

Default endpoint

fireworks/line-evaluation

Input price

$0.2200

per 1M tokens

Output price

$0.6600

per 1M tokens

Energy estimate

75 Wh

per 1M tokens

Fallback models

OpenRouter-compatible metadata

Model ID: deepseek/deepseek-v4.1-flash
Canonical slug: deepseek/deepseek-v4.1-flash
Owned by: deepseek
API: zevrouter
Input modalities: text
Output modalities: text
Tokenizer: Other
Instruct type: chat

Pricing JSON

{
  "prompt": "0.00000022",
  "completion": "0.00000066",
  "request": "0",
  "image": "0",
  "audio": "0",
  "web_search": "0",
  "internal_reasoning": "0"
}

Parameters

Supported parameters

9 parameters

temperaturetop_pmax_tokensmax_completion_tokenstoolstool_choicestreamstream_optionsreasoning_effort

Routing

Provider endpoints

Inspect Endpoints

Endpoint	Region	Status	Latency	Carbon intensity	CFE
`fireworks/line-evaluation` fireworks evaluation	provider-managed	default	--	--	--

Fallback chain

google/gemini-3.7-flash

{
  "model": "deepseek/deepseek-v4.1-flash",
  "models": ["deepseek/deepseek-v4.1-flash", "google/gemini-3.7-flash"],
  "messages": [{ "role": "user", "content": "Hello" }]
}

API references

curl "https://router.zev.city/api/v1/models"

curl "https://router.zev.city/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints"