DeepSeek V4 Flash pricing & specs

DeepSeek · released 2026-04-24 · ● verified 2026-10-11

input / 1M$0.09via DeepInfra
output / 1M$0.18via DeepInfra
context1.05M
max output16.4K

// price history ($/1M tokens)

$0.207
input $/1Moutput $/1M2026-04-24 → 2026-10-11

// cheaper or similar alternatives

modelinoutctxvs DeepSeek V4 Flash
Qwen3.7 Flash$0.03$0.131M−51.1%
Qwen Turbo$0.05$0.201M−22.2%
DeepSeek V4 Flash 0731$0.06$0.181.05M−20%
Qwen Flash$0.05$0.401M+22.2%
Qwen3.5 Flash$0.10$0.401M+55.6%
DeepSeek V4 Flash vs DeepSeek V4 Flash 0731 →

// price by host

hostin $/1Mout $/1M
DeepInfra$0.09$0.18
NVIDIA$0.14$0.28
Azure$0.19$0.51

// faq

How much does DeepSeek V4 Flash cost?

DeepSeek V4 Flash costs $0.09 per million input tokens and $0.18 per million output tokens (cheapest tracked host: DeepInfra). At 50M input and 10M output tokens per month that is about $6.30.

What is the context window of DeepSeek V4 Flash?

1.05M tokens, with up to 16.4K output tokens per request.

Does DeepSeek V4 Flash support prompt caching?

Yes. Cached input tokens cost $0.018 per million.

What are cheaper alternatives to DeepSeek V4 Flash?

Qwen3.7 Flash ($0.03 in / $0.13 out), Qwen Turbo ($0.05 in / $0.20 out), DeepSeek V4 Flash 0731 ($0.06 in / $0.18 out) offer the same input types and capabilities for less.

Is DeepSeek V4 Flash open weights?

Yes. It is available from 3 tracked hosts; the cheapest is DeepInfra at $0.09 input and $0.18 output per million tokens.

// spec sheet

input / 1M
$0.09
output / 1M
$0.18
cache read / 1M
$0.018
blended (3:1)
$0.1125
context
1.05M
max output
16.4K
input types
text
reasoning
yes
tool calling
yes
structured output
yes
open weights
yes
knowledge cutoff
2025-05
price source
DeepInfra

report a data error

// cost calculator

modelin $/1Mout $/1M= monthly
Qwen3.7 Flash$0.03$0.13$2.80
Qwen Turbo$0.05$0.20$4.50
DeepSeek V4 Flash 0731$0.06$0.18$4.80
DeepSeek V4 Flash$0.09$0.18$6.30

Base-tier list prices. Long-context tiers, caching and batch discounts are not included.