AI TOOLS RADAR
All models / DEEPSEEK
deepseek logo
deepseek

DeepSeek: DeepSeek V4.1 Flash 1017

Source description (English)

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
1,048,576 tokens
Maximum output
393,216 tokens
Architecture
text+image->text
Tokenizer
DeepSeek
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.15
per 1M tokens
Output
$0.6
per 1M tokens
Cache read
$0.003
per 1M tokens
API

Model configuration

Reasoning

Reasoning required
No
Default parameters
high
Capabilities
max, high, low, none
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-v4.1-flash-1017","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimage
Output
text
Reasoning

Yes · max · high · low · none

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

34 providers

Checked: October 26, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

OpenInference

fp4
Context
1.0M
Maximum output
944K
Input
$0.02
Output
$1
Cache read
$0.015
Cache write
Not provided

Relace

Not provided
Context
1.0M
Maximum output
944K
Input
$0.07
Output
$0.5
Cache read
$0.008
Cache write
Not provided

Morph

fp8
Context
1.0M
Maximum output
944K
Input
$0.073
Output
$0.6
Cache read
$0.01
Cache write
Not provided

DeepInfra

fp8
Context
1.0M
Maximum output
131K
Input
$0.0784
Output
$0.2352
Cache read
$0.002352
Cache write
Not provided

InferenceNet

fp8
Context
1.0M
Maximum output
393K
Input
$0.08
Output
$0.5
Cache read
$0.008
Cache write
Not provided

InferenceNet

fp8
Context
1.0M
Maximum output
393K
Input
$0.08
Output
$0.5
Cache read
$0.008
Cache write
Not provided

Reka

Not provided
Context
1.0M
Maximum output
393K
Input
$0.08
Output
$0.8
Cache read
$0.08
Cache write
Not provided

DeepInfra

fp8
Context
1.0M
Maximum output
131K
Input
$0.098
Output
$0.294
Cache read
$0.00294
Cache write
Not provided

Cloudflare

Not provided
Context
1.0M
Maximum output
944K
Input
$0.1
Output
$0.6
Cache read
$0.003
Cache write
Not provided

Sail Research

fp4
Context
1.0M
Maximum output
384K
Input
$0.101
Output
$0.15
Cache read
$0.006735
Cache write
Not provided

Sail Research

fp4
Context
1.0M
Maximum output
384K
Input
$0.101
Output
$0.15
Cache read
$0.006735
Cache write
Not provided

Wafer

mxfp4
Context
1.0M
Maximum output
944K
Input
$0.13
Output
$0.5
Cache read
$0.008
Cache write
Not provided

Decart

fp4
Context
1.0M
Maximum output
262K
Input
$0.1365
Output
$0.546
Cache read
$0.00273
Cache write
Not provided

DeepInfra

fp8
Context
1.0M
Maximum output
131K
Input
$0.147
Output
$0.441
Cache read
$0.00441
Cache write
Not provided

Makora

fp8
Context
1.0M
Maximum output
944K
Input
$0.15
Output
$1.2
Cache read
$0.006
Cache write
Not provided

GMICloud

fp8
Context
1.0M
Maximum output
944K
Input
$0.18
Output
$0.72
Cache read
$0.0036
Cache write
Not provided

AtlasCloud

fp8
Context
1.0M
Maximum output
393K
Input
$0.195
Output
$0.78
Cache read
$0.0039
Cache write
Not provided

Fireworks

Not provided
Context
1.0M
Maximum output
944K
Input
$0.21
Output
$0.84
Cache read
$0.0042
Cache write
Not provided

Ionstream

Not provided
Context
1.0M
Maximum output
944K
Input
$0.22
Output
$0.6
Cache read
$0.019
Cache write
Not provided

DigitalOcean

Not provided
Context
1.0M
Maximum output
944K
Input
$0.225
Output
$0.9
Cache read
$0.006
Cache write
Not provided

Novita

fp8
Context
1.0M
Maximum output
393K
Input
$0.24
Output
$0.96
Cache read
$0.0048
Cache write
Not provided

Modal

Not provided
Context
1.0M
Maximum output
944K
Input
$0.25
Output
$1
Cache read
$0.005
Cache write
Not provided

Baidu

fp8
Context
1.0M
Maximum output
393K
Input
$0.28
Output
$1.13
Cache read
$0.006
Cache write
Not provided

Crusoe

fp8
Context
1.0M
Maximum output
944K
Input
$0.29
Output
$1.2
Cache read
$0.007
Cache write
Not provided

Nebius

fp8
Context
1.0M
Maximum output
944K
Input
$0.3
Output
$1.2
Cache read
$0.006
Cache write
Not provided

Phala

Not provided
Context
1.0M
Maximum output
393K
Input
$0.3
Output
$1.2
Cache read
$0.006
Cache write
Not provided

SiliconFlow

fp8
Context
1.0M
Maximum output
393K
Input
$0.3
Output
$1.2
Cache read
$0.006
Cache write
Not provided

Together

Not provided
Context
1.0M
Maximum output
944K
Input
$0.3
Output
$1.2
Cache read
$0.006
Cache write
Not provided

Fireworks

Not provided
Context
1.0M
Maximum output
944K
Input
$0.3
Output
$1.2
Cache read
$0.006
Cache write
Not provided

PrimeIntellect

Not provided
Context
1.0M
Maximum output
131K
Input
$0.3
Output
$1.2
Cache read
$0.006
Cache write
Not provided

BaseTen

Not provided
Context
1.0M
Maximum output
262K
Input
$0.3
Output
$1.2
Cache read
$0.007
Cache write
Not provided

Parasail

fp8
Context
1.0M
Maximum output
944K
Input
$0.3
Output
$1.2
Cache read
$0.006
Cache write
Not provided

DeepSeek

Not provided
Context
1.0M
Maximum output
393K
Input
$0.3
Output
$1.2
Cache read
$0.006
Cache write
Not provided

Alibaba

Not provided
Context
1M
Maximum output
393K
Input
$0.33
Output
$1.32
Cache read
$0.033
Cache write
Not provided
deepseek

4 models

All models
deepseek logodeepseek

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. It activates 8B parameters on input and 16B on...

Context
1.0M
Input
text · image
Output
text
Input: $0.02Output: $1per 1M tokens
View model details →
deepseek logodeepseek

DeepSeek: DeepSeek V4.1 Flash (batch)

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
1.0M
Input
text · image
Output
text
Input: $0.05Output: $0.15per 1M tokens
View model details →
deepseek logodeepseek

DeepSeek: DeepSeek V4 Flash Vision Exp

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

Context
1.0M
Input
text · image
Output
text
Input: $0.2156Output: $0.6468per 1M tokens
View model details →
deepseek logodeepseek

DeepSeek: DeepSeek V4 Pro 0813

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Context
1.0M
Input
text
Output
text
Input: $0.66Output: $1.98per 1M tokens
View model details →