Skip to main content
DeepSeekOct 23, 2026New

DeepSeek V4.1 Flash 1017 Ultrafast

deepseek-v4-1-flash-1017-ultrafastPrivateOpen weights

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.

$1.50/$6.00
per 1M in / out
1M
context window
128K
max output
How it comparesamong 143 text models
GPQA Diamondhigher than 64%88.9%
Blended pricecheaper than 39%$2.63
Context windowlarger than 42%1M
Max outputlarger than 78%128K

Further right is better. Hover a dot for its model.

Time to first token— 
Output speed— 
Uptime— 

Last 24 hours of Venice traffic.How it’s measured

Capabilities

What the model takes in, returns and supports through the API.

InTextImage
OutText

Not supportedvideo input, audio input, X search and log probabilities

Benchmarks

GPQA Diamond
88.9%47th of 139 · 13 score higher for less, including Gemini 3.8 Flash, Gemini 3.7 Flash and Pareto

Specs

Model ID
deepseek-v4-1-flash-1017-ultrafast
Endpoint
POST /api/v1/chat/completions
Context window
1,000,000 tokens
Max output
131,072 tokens
Reasoning
none · low · high · max · default high
Precision
FP8
Privacy
Private
Added
Oct 23, 2026

Compare

ModelInputOutputGPQA DiamondContextMax outputFirst tokenSpeed
DeepSeek V4.1 Flash 1017 Ultrafast$1.50$6.0088.9%1M128K——
Muse Spark Open$1.56$5.3171.7%1M128K——
GLM 5.3 E2EE$1.75$5.5075.3%1M32K——
GLM 5.3$1.75$5.5079.8%1M128K——
Qwen 4 Max$1.50$4.5094.4%1M384K——

Pricing

Billed per token in USD. Reasoning tokens bill as output.

Input$1.50per 1M tokens
Cached input$0.0398% off input
Output$6.00per 1M tokens

Estimate a workload

$0.006per request
$60.00for 10,000 requests

Blended price against similar models

DeepSeek V4.1 Flash 1017 Ultrafast$2.63
GLM 5.3$2.69

Per 1M tokens at three input tokens for each output token.

Quickstart

OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice 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-1017-ultrafast",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
"reasoning_effort": "high"
}'
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modeldeepseek-v4-1-flash-1017-ultrafastRequired
messagestext · image_urlContent parts the model reads
max_completion_tokensUp to 131,072Counts reasoning tokens
reasoning_effortnone | low | high | maxDefault high
toolsFunction definitionsWith tool_choice
response_format{ type: "json_schema" }Output that matches a schema
streamtrue | falseServer-sent events
venice_parameters.enable_web_searchauto | on | offWeb results and citations