deepseek-v4-flash-vision-exp

deprecatedmit

DeepSeek-V4 hybrid model with both non-thinking and thinking (default) modes.

Context
1.0M
Max output
384K
Input price
$1/1M tokens
Output price
$1/1M tokens

Capabilities

vision
tool call
structured output
reasoning
json mode
streaming
fine tuning
batch

Details

Model IDdeepseek-ai/deepseek-v4-flash-vision-exp
Creator DeepSeek
Familydeepseek
Licensemit
Parameters—
Statusdeprecated
Input modalitiestext
Output modalitiestext
Architecture—
Knowledge cutoff—
Training data cutoff—
Release date—
Deprecation date—
Typechat
Reasoning tokensYes
Max input—
Open weightYes
Sourceofficial
Last updated

Pricing

Input
$1
↑355%$0.22
Output
$1
↑52%$0.66
Cache write
—
Cache read
$1
↑14186%$0.01
Batch in
—
Batch out
—
Price history · $/1M input
$0.22
$1
Sep 2Sep 26
DateInputOutputCache readChange
Sep 2, 2026$0.22$0.66$0.007—
Sep 26, 20269cb03f8$1$1$1↑355%

Input is ↑355% since Sep 2, 2026, from $0.22 to $1 per 1M tokens.

Price across providers

ProviderInputOutputSince launch
DeepInfracheapest$0.44$1.32—
Fireworks AI$1$1↑355%

Family Comparison: deepseek

ModelContextMax outPricing
deepseek-v4-flash-07311.0M—$0.14$0.28
deepseek-v4-flash1.0M384K$0.14$0.28
deepseek-v4p1-flash1.0M—$0.3$1.2
deepseek-v3p1-terminus163K—$1$1
deepseek-v4-flash-vision-exp1.0M384K$1$1
deepseek-coder-1b-base16K—$1$1
deepseek-coder-33b-instruct16K—$1$1
deepseek-coder-7b-base-v1p54K—$1$1
deepseek-coder-7b-base4K—$1$1
deepseek-coder-7b-instruct-v1p54K—$1$1
deepseek-coder-v2-instruct33K—$1$1
deepseek-coder-v2-lite-base163K—$1$1
deepseek-coder-v2-lite-instruct163K—$1$1
deepseek-prover-v2163K—$1$1
deepseek-v2-lite-chat163K—$1$1
deepseek-v2p533K—$1$1
deepseek-v3-0324163K—$1$1
deepseek-v3131K—$1$1
deepseek-v3p1163K—$1$1
deepseek-v3p2163K—$1$1
deepseek-v4-flash1.0M384K$1$1
deepseek-v4-pro1.0M384K$1$1
deepseek-v4-pro-08131.0M—$1.32$3.96
deepseek-v4-pro1.0M384K$1.74$3.48

API

GET/v1/models/fireworks/deepseek-ai/deepseek-v4-flash-vision-exp