Plain-text specification

DeepSeek V4.1 Flash API

DeepSeek V4.1 Flash is a large language model by DeepSeek, available on the Venice API as deepseek-v4-1-flash. It runs privately, with zero data retention.DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.

DeepSeek V4.1 Flash API pricing

Model ID	Variant	Privacy	Price
`deepseek-v4-1-flash`	Standard	Private	$0.38 input /$ 1.50 output per 1M tokens

DeepSeek V4.1 Flash specifications

Spec	Value
Provider	DeepSeek
Released	Sep 10, 2026
Privacy	Private
Open weights	Yes
Context window	1M tokens
Max output	128K tokens
Reasoning effort	none, low, high, max
Served precision	FP8

How to use the DeepSeek V4.1 Flash API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "deepseek-v4-1-flash" and your API key.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-1-flash",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
    "reasoning_effort": "high"
  }'

DeepSeek V4.1 Flash API FAQ

How much does the DeepSeek V4.1 Flash API cost?

0.38 per 1M input tokens and

1.50 per 1M output tokens, with cached input at $0.0075 per 1M. Prices are in USD and can be paid in DIEM at parity.

What is the DeepSeek V4.1 Flash model ID?

Use deepseek-v4-1-flash as the model parameter.

Is the DeepSeek V4.1 Flash API private?

DeepSeek V4.1 Flash is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.

What is the context window of DeepSeek V4.1 Flash?

1M tokens of context, with up to 128K output tokens per response.

What does DeepSeek V4.1 Flash support?

DeepSeek V4.1 Flash supports function calling, structured outputs, reasoning, image input, web search and prompt caching. Reasoning effort is adjustable with reasoning_effort: none, low, high and max (default high).

Which endpoint does the DeepSeek V4.1 Flash API use?

Call POST /chat/completions. /responses (Alpha) is also supported.

Related models

DeepSeek V4 Flash 0731 API: $0.17 input /$ 0.35 output per 1M tokens
DeepSeek V4 Flash 0423 API: $0.14 input /$ 0.28 output per 1M tokens
GPT-5.6 Luna API: $0.25 input /$ 1.50 output per 1M tokens
GPT-5.6 Luna Pro API: $0.25 input /$ 1.50 output per 1M tokens
MiniMax M2.7 API: $0.38 input /$ 1.50 output per 1M tokens
MiMo-V2.5 API: $0.40 input /$ 2.00 output per 1M tokens