LLM API PricesUpdated 2026-09-17 06:21:06 UTC

Home / DeepSeek / DeepSeek V4.1 Flash

DeepSeek V4.1 Flash API price

deepseek-v4.1-flash

The cheapest DeepSeek V4.1 Flash API is $0.12/M input at InferX (inference host) - all 7 providers compared below, per 1M tokens.

SmallDeepSeek1.0M context7 sellers
Input $0.12 per 1M tokens · InferX (inference host)
up to $0.30
Output $0.48 per 1M tokens · InferX (inference host)
up to $1.20

Where to buy it

Cheapest DeepSeek V4.1 Flash API providers compared - 7 sellers, from $0.12/M.

Cost calculator
ProviderInput $/MOutput $/MCached inTPSYour cost
InferX (inference host)60% off0.120cheapest0.4800.0024-
Nahcrof (inference host)stale, Q8_00.1000.5000.003092
Cheaper Inference (discount marketplace)60% off0.1210.4830.0024-
OpenRouter (aggregator)stale0.1500.6000.0030-
OrcaRouter (aggregator)0.1500.600--
Together AI (inference host)0.3001.200.0060-
TokenRouter (aggregator)0.3001.200.0060-

3.0× between the cheapest and the dearest of 7 sellers.

Against its tier

#9 of 18 small · cheaper than 53%

Details

Context window
1.0M1,048,576 tokens
Developer
DeepSeek
Intelligence
39.5Reasoning, Max Effort
Sellers
73.0× spread
Cached input
$0.0024where the source publishes one
Cheapest at
InferX (inference host)
Combined
$0.60in + out per 1M
Last checked
2026-09-17
Throughput
92 tok/sas published by Nahcrof (inference host)

More from DeepSeek

Other small-tier models

← All DeepSeek models