Skip to content

DeepSeek: DeepSeek V4.1 Flash (batch)

DeepSeekNew
deepseek/deepseek-v4.1-flash:batch

About this model

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...

Make a request

OpenAI-compatible: set the base URL and your Promptix API key, keep your existing SDK.

curl https://promptix.tn/api/v1/chat/completions \  -H "Authorization: Bearer $PROMPTIX_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "deepseek/deepseek-v4.1-flash:batch",    "messages": [      {"role": "user", "content": "Hello! What can you do?"}    ]  }'

Pricing

In TND per 1M tokens. VAT and the platform fee are added at top-up.

Input tokens

0.434 TND

per 1M tokens

Output tokens

1.301 TND

per 1M tokens

1,000 requests with 1K input and 500 output tokens cost about 1.084 TND.

Specifications

Provider
DeepSeek
Context window
1,048,576 tokens
Input modality
Text
Added
Sep 10, 2026
Supported parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effort