DeepSeek

DeepSeek-V4 Flash

The fast, low-cost V4 tier for high-volume tasks, available across inference gateways.

ActiveAvailable from 18 providers
Tool callingCan invoke external tools and APIs (function calling) mid-response.Structured outputCan return JSON or schema-constrained responses instead of free text.ReasoningUses extended thinking / chain-of-thought for harder multi-step problems.Effort controlLets you dial thinking depth (low / medium / high) to trade cost for quality.Fine-tuningSupports training a custom variant on your own data.

Source: DeepSeek API models, DeepSeek models

Price per 1M tokens
$0.14 in / $0.28 out
Context window131,072
Max output32,768
Cache read$0.028 / M
Batch discount-50%
ModalitiesText → Text
Priced across18 providers

Pricing

Every billing leg from the live catalog, in USD per 1M tokens.

Billing legRateBatch
Input$0.14 / M$0.07 / M
Output$0.28 / M$0.14 / M
Cache read$0.028 / Mn/a

Cost calculator

Billing-grade math over the rate card above, including the thinking tokens most estimates miss.

Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.

Estimated monthly cost
$44.80
at current list prices
Fresh input$28.00
Cached input$0.00
Output incl. thinking$16.80
Track this automatically →

Compare providers

The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.

PlatformInput / MOutput / MCache read / MBatchAccess
Fireworks AI
$0.14$0.28$0.028✓Direct
DeepInfraLowest
$0.09$0.18$0.018—via OpenRouter
GMICloud
$0.098$0.196$0.02—via OpenRouter
Baidu
$0.0983$0.1966$0.0197—via OpenRouter
DigitalOcean
$0.112$0.224$0.028—via OpenRouter
StreamLake
$0.1288$0.2576$0.02576—via OpenRouter
Alibaba
$0.134$0.268$0.0268—via OpenRouter
SiliconFlow
$0.13$0.28$0.028—via OpenRouter
Venice
$0.138$0.275$0.028—via OpenRouter
Morph
$0.139$0.278——via OpenRouter
Akashml
$0.14$0.28——via OpenRouter
AtlasCloud
$0.14$0.28$0.028—via OpenRouter
Fireworks AI
$0.14$0.28$0.028—via OpenRouter
Novita
$0.14$0.28$0.028—via OpenRouter
Parasail
$0.14$0.28$0.07—via OpenRouter
Wandb
$0.14$0.28$0.07—via OpenRouter
Azure AI Foundry
$0.19$0.51$0.028—Direct
Azure AI Foundry · Data zone
$0.21$0.56$0.031—Direct

Price history

Has this model gotten cheaper or more expensive?

EffectiveInput / OutputStatus
May 21, 2026 – July 10, 2026$0.14 / $0.28past
July 10, 2026$0.14 / $0.28current

More from DeepSeek

Other models from the same provider.

DeepSeek-V4 Pro
deepseek/deepseek-v4-pro
$1.74 / $3.48 in / out per 1M
DeepSeek-V3.2
deepseek/deepseek-v3.2
$0.2288 / $0.3432 in / out per 1M
DeepSeek-V3.1
deepseek/deepseek-v3.1
$0.21 / $0.79 in / out per 1M
DeepSeek-V3
deepseek/deepseek-v3
$0.2002 / $0.8001 in / out per 1M
DeepSeek-R1
deepseek/deepseek-r1
$0.5 / $2.15 in / out per 1M

Stop estimating. Track it.

SuperPenguin meters every DeepSeek-V4 Flash call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.

Get started free

Rates are generated from SuperPenguin's live pricing catalog.