Start free trial

DeepSeek: DeepSeek V4 Flash Vision Exp

deepseek/deepseek-v4-flash-vision-exp
CompareAPITry this model

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents

Modalities
In / out per 1M$0.22 / $0.65
Context1M
ReleasedAug 21, 2026

Providers

3 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
DeepInfraus · fp8$0.22$0.65$0.011.27s88 tps100%
GMICloudfp8$0.44$1.32$0.012.81s43 tps100%
SiliconFlowfp8$0.44$1.32$0.031.95s101 tps100%

Market-wide measurements, refreshed every 15 minutes. They describe who serves DeepSeek V4 Flash Vision Exp in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what DeepSeek V4 Flash Vision Exp costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.22
per 1M tokens
Output
$0.65
per 1M tokens
Cache read
$0.01
per 1M cached tokens
Included in every pass
DeepSeek V4 Flash Vision Exp is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s2.5s5.0s7.5s10.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
DeepInfra (us) SiliconFlow GMICloud
0 tok/s100 tok/s200 tok/s300 tok/s400 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
DeepInfra (us) SiliconFlow GMICloud

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.8%
Oct 16, 12:00 PMNow
Availability over the last 24 hoursAvailability 99.8%
100% 98% 97% 95%
Oct 18, 12:10 PMNow

Apps

Tools that most often run DeepSeek V4 Flash Vision Exp, by tokens this week.

Hermes AgentPersonal Agent · 35.7% of tokens26.1BDeepSeek Harness29.9% of tokens21.8BpiCli Agent · 12.8% of tokens9.3BDigen AICli Agent · 11.9% of tokens8.7BClaude CodeCli Agent · 9.7% of tokens7.1B

Activity

484.7B tokens processed market-wide in the last month.

010.0B20.0B30.0B40.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens

FAQ

Which model id do I use for DeepSeek V4 Flash Vision Exp?
deepseek/deepseek-v4-flash-vision-exp. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does DeepSeek V4 Flash Vision Exp hold?
1,048,576 tokens per request, of which up to 262,144 can be the response.
What can it accept and return?
Input: text, image. Output: text.
What does DeepSeek V4 Flash Vision Exp cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.22 per 1M input tokens and $0.65 per 1M output tokens.
Who built DeepSeek V4 Flash Vision Exp?
DeepSeek, in the DeepSeek family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion