DeepSeek V4.1 Flash 1017

DeepSeek
deepseek-v4-1-flash-1017
Released Oct 17, 2026
Chat
Providers
8
Context
1.0M
Input
$0.07/M
Output
$0.29/M
BAA-eligible on 3 of 8 providersPHI requires a signed BAA from Concentrate and HIPAA-enabled organization.

The 2026-10-17 update to DeepSeek V4.1 Flash: stronger reasoning, coding, agentic and vision results with shorter outputs and faster task completion than the previous version. 1M context window, image input, tool calling and thinking mode.

Fireworks AI

fireworks/deepseek-v4-1-flash-1017QuantUnspecified
Input
$0.30/M
Output
$1.20/M
Context
1.0M
Max out
131K
Cache read
$0.01/M
Cache write
$0.30/M
Thinking out
$1.20/M
Flex

Novita

novita/deepseek-v4-1-flash-1017Quantfp8
Input
$0.30/M
Output
$1.20/M
Context
1.0M
Max out
393K
Cache read
$0.01/M
Cache write
$0.30/M
Thinking out
$1.20/M
FlexPriority / Fast

Azure Fireworks

azure-fw/deepseek-v4-1-flash-1017QuantUnspecified
Input
$0.38/M
Output
$1.50/M
Context
1.0M
Max out
131K
Cache read
$0.01/M
Cache write
$0.38/M
Thinking out
$1.50/M
FlexPriority / Fast

Relace

relace/deepseek-v4-1-flash-1017QuantUnspecified
Input
$0.07/M
Output
$0.50/M
Context
1.0M
Max out
1.0M
Cache read
$0.01/M
Cache write
$0.07/M
Thinking out
$0.50/M
FlexPriority / Fast

RunAnywhere

runanywhere/deepseek-v4-1-flash-1017Quantfp8
Input
$0.28/M
Output
$1.14/M
Context
1.0M
Max out
66K
Cache read
$0.01/M
Cache write
$0.28/M
Thinking out
$1.14/M
FlexPriority / Fast

Baseten

baseten/deepseek-v4-1-flash-1017QuantUnspecified
Input
$0.30/M
Output
$1.20/M
Context
1.0M
Max out
262K
Cache read
$0.01/M
Cache write
$0.30/M
Thinking out
$1.20/M
FlexPriority / Fast

DeepInfra

deepinfra/deepseek-v4-1-flash-1017Quantfp8
Input
$0.10/M
Output
$0.29/M
Context
1.0M
Max out
131K
Cache read
$0.00/M
Cache write
$0.10/M
Thinking out
$0.29/M

DeepSeek

deepseek/deepseek-v4-1-flash-1017QuantUnspecified
Input
$0.15/M
Output
$0.60/M
Context
1.0M
Max out
393K
Cache read
$0.00/M
Cache write
$0.15/M
Thinking out
$0.60/M
FlexPriority / Fast