DeepSeek logo

DeepSeek V4 Flash Vision Exp

Deprecated
Pricing & Specs API
Free REST API for prices, specs and benchmarks
DeepSeek V4 Flash Vision Exp is DeepSeek's language model with a 1.0M context window and up to 944K output tokens, available from 5 providers, starting at $0.216 / 1M input and $0.647 / 1M output. An experimental vision-enabled large language model that adds image understanding to the lightweight DeepSeek V4 Flash variant, with reasoning and tool-use capabilities.
Specifications
Canonical IDdeepseek-v4-flash-vision-exp
TypeLanguage
StatusDeprecated
CreatorDeepSeekDeepSeek
Providers
Context Window1.0M tokens
Max Output944K tokens
Input ModalitiesImageText
Output ModalitiesText
Reasoning Effortsdefault
Parameters305B
HuggingFace Likes560
HuggingFace Downloads (30d)54,571
HuggingFace Downloads (all-time)54,571
Release Date · 2 months ago
Deprecation Date

Capabilities

Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities7/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill✓

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandardFast
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
DeepSeek logo
DeepSeek
deepseek-v4-flash-vision-exp
$0.3$1.20$0.006———
Fireworks AI logo
Fireworks AI
fireworks_ai/deepseek-v4-flash-vision-exp
$0.22$0.66$0.007$0.275$0.825$0.00875
Novita logo
Novita
novita/deepseek/deepseek-v4-flash-vision-exp
$0.44$1.32$0.028———
OpenRouter logo
OpenRouter
deepseek/deepseek-v4-flash-vision-exp
$0.216$0.647$0.00686———
Vercel AI Gateway logo
Vercel AI Gateway
deepseek/deepseek-v4-flash-vision-exp
$0.216$0.647$0.0068———

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host DeepSeek V4 Flash Vision Exp, ranked by cheapest on-demand price. The model needs about 731 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
g7e.48xlargeAWS8× RTX PRO Server 6000768 GB$33.14/hr
g4-standard-384GCP8× nvidia-rtx-pro-6000768 GB$36.00/hr
Standard_ND96isr_MI300X_v5Azure8× AMD Instinct MI300X1536 GB$48.00/hr
7 more instances can run DeepSeek V4 Flash Vision Exp
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
DeepSeek V4 Flash 0731 P————Available
DeepSeek V4.731 Flash US————Available
DeepSeek V4 420 Flash————Available
DeepSeek V4.4.1 Flash————Available
DeepSeek V4.1 Flash Fast1.0M$0.010$1.20Available
DeepSeek V4.1 Flash Expires Exp1.0M$0.010$0.600Deprecating
DeepSeek V4.1 Flash Beta1.0M——Available
DeepSeek V4.1 Flash DST————Available
DeepSeek V4.1 Flash P————Available
DeepSeek V4.1 Flash US—1.0M$0.450$1.80Available
DeepSeek V4 Flash Vision Exp1.0M$0.216$0.647Current

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
DeepSeek V4 ProPro1.0M$0.660$1.98
DeepSeek V4 Pro 0813 PPro————
DeepSeek V4 ProPro————
DeepSeek V4 ProPro1.0M$0.250$0.870
DeepSeek V4 Pro 813Pro—1.0M$1.32$3.96
DeepSeek V4 Pro USPro————

Model IDs

accounts/fireworks/models/deepseek-v4-flash-vision-exp
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
deepseek-v4-flash-vision-exp
deepseek/deepseek-v4-flash-vision-exp
fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-vision-exp
fireworks_ai/deepseek-v4-flash-vision-exp
novita/deepseek/deepseek-v4-flash-vision-exp
openrouter/deepseek/deepseek-v4-flash-vision-exp
openrouter/deepseek/deepseek-v4-flash-vision-exp:batch