One chat reply3,000 tokens in, 500 outDeepSeek V4 Flash costs 1.3× as much as DeepSeek V4.1 Flash
$0.0015
$0.002
Summarise a 100-page report50,000 tokens in, 1,500 out, one requestDeepSeek V4 Flash costs 1.4× as much as DeepSeek V4.1 Flash
$0.02
$0.02
1,000 classification calls500 tokens in, 20 out, per call
$0.17
$0.25
Coding-agent session2M tokens in across ~60 turns, 60,000 out, no cache
$0.67
$0.96
At listed rates. Token counts are typical sizes, not measurements.
DeepSeek V4.1 Flash pricing notes
The listed price is DeepSeek's peak rate. DeepSeek's own API charges half outside 01:00-04:00 and 06:00-10:00 UTC on weekdays; other serving providers bill the peak rate.
Cache hits bill $0.006 per 1M on some serving providers and $0.03 per 1M on others.
DeepSeek V4 Flash pricing notes
The listed rate is DeepSeek's peak-hour price from its 2026-08-16 revision. It applies at all hours here, although DeepSeek's own off-peak rate was half.
DeepSeek retired the model on its own API on 2026-09-10, and that route now serves V4.1 Flash. This page is for the V4 Flash open weights served by third-party hosts.
DeepSeek V4.1 Flash is DeepSeek's open-weight mixture-of-experts model that reads text and images with a 1M-token context. It replaced V4 Flash behind DeepSeek's own deepseek-flash route and costs less than V4 Flash here.
Pick it if
you want the cheapest DeepSeek model here, and the only one with image input
you need long replies: DeepSeek's API allows up to 384K output tokens
you want MIT-licensed weights you can self-host
Skip it if
you need video or audio input; it takes text and images only
The smaller DeepSeek V4 model: an open-weights mixture-of-experts with 284B total and 13B active parameters that takes text only. On its own API, DeepSeek has replaced it with V4.1 Flash, which costs less and adds image input.
Pick it if
you want MIT-licensed open weights from DeepSeek's cheaper V4 tier
you need a 1M-token context with cached input at $0.014 per 1M
you want a choice of non-think, Think High or Think Max reasoning
Skip it if
you need image input; V4.1 Flash accepts images
the cheaper V4.1 Flash sibling covers your workload
FAQ
Which is cheaper, DeepSeek V4.1 Flash or DeepSeek V4 Flash?
DeepSeek V4.1 Flash lists lower input and output prices. On a coding-agent session (2M tokens in, 60,000 out) DeepSeek V4.1 Flash costs $0.67 and DeepSeek V4 Flash $0.96.
Which one accepts images?
DeepSeek V4.1 Flash supports vision; DeepSeek V4 Flash does not.
Can I switch between DeepSeek V4.1 Flash and DeepSeek V4 Flash mid-task?
Yes. In an Octomind session, /model octohub:deepseek-v4.1-flash and /model octohub:deepseek-v4-flash switch models without losing the conversation, so you can draft on one and review on the other.
Try either model
Switch between models inside the same Octomind session.