FindCostShortlistChangesModels
← All tracked models

DeepSeek

DeepSeek V4 Flash 0423 API prices by provider

deepseek/deepseek-v4-flash

15 inference providers serve this exact model through OpenRouter. Input and output rates are paired per endpoint; route tags may identify a region or sub-endpoint whose eligibility is not yet verified.

Active endpoints
11 / 15
Lowest at 1M in + 1M out
$0.2478
AtlasCloud · standard tier
Context up to
1.05M
Latest price change
None yet
Rates unchanged since first record 2026-09-29
DeepSeek V4 Flash 0423 endpoint prices per million tokens
Provider · routeTierInput / 1MOutput / 1MCache readCache writeContextTools1M + 1MStatusPrice since

StreamLake

streamlake/fp8 · fp8

Promo$0.0749$0.1498$0.015—1.02MYes$0.2247ActiveSince

AtlasCloud

atlas-cloud/fp4 · fp4

Standard$0.0826$0.1652$0.0165—1.05MYes$0.2478ActiveSince

DeepInfra

deepinfra/fp8 · fp8

Standard$0.09$0.18$0.018—1.05MYes$0.27ActiveSince

GMICloud

gmicloud/fp8 · fp8

Promo$0.091$0.182$0.0182—1.05MYes$0.273ActiveSince

DigitalOcean

digitalocean · unknown

Standard$0.098$0.196$0.0196—1.05MYes$0.294ActiveSince

SiliconFlow

siliconflow/fp8 · fp8

Standard$0.13$0.28$0.028—1.05MYes$0.41ActiveSince

Novita

novita/fp8 · fp8

Standard$0.14$0.28$0.028—1.05MYes$0.42ActiveSince

Parasail

parasail/fp8 · fp8

Standard$0.14$0.28$0.07—1.05MYes$0.42ActiveSince

Mancer 2

mancer/fp8 · fp8

Standard$0.19$0.50——1.05MYes$0.69ActiveSince

OpenInference

open-inference/fp8 · fp8

Standard$0.012$1.25$0.01—1.05MYes$1.262ActiveSince

Relace

relace/fp4 · fp4

Standard$0.03$1.28$0.03—1.05MYes$1.31ActiveSince

Baidu

baidu/fp8 · fp8

Promo$0.0763$0.1526$0.0153—1.05MYes$0.2289UnavailableSince

Venice

venice · unknown

Promo$0.0966$0.1925$0.0196—1MYes$0.2891UnavailableSince

Alibaba

alibaba/fp8 · fp8

Standard$0.134$0.268$0.0268—1MYes$0.402UnavailableSince

Azure

azure/us · unknown

Standard$0.21$0.56$0.031—1.05MYes$0.77UnavailableSince

“—” means no rate is published for that endpoint; it is excluded from estimates, not counted as zero. “Since” is the first record with no rate change observed; “Changed” is the latest observed rate or billing change. Per-request fees: not published for any endpoint here. Status is the upstream operational flag, not a measured uptime.