≫ Home / LLM API pricing / DeepSeek V4.1 Flash

DeepSeek V4.1 Flash API pricing

Of the 20 providers checked, DeepInfra lists the lowest blended rate for DeepSeek V4.1 Flash: $0.14 input and $0.42 output per 1M tokens, on its pricing page as of 25 September 2026.

A mixture-of-experts model from DeepSeek that reads images as well as text, with a context of up to 1M tokens. The older V4 Flash and V4 Flash Vision names on DeepSeek's own API now route to it; existing integrations keep working unchanged.

Across 20 providers, the most expensive charges 4.9Γ— the cheapest on a blended basis. 1 provider is on a limited-time promotion.

Prices by provider

Per 1M tokens, on-demand, sorted cheapest first by blended cost (3:1 input to output). Off-peak and long-context rates are listed on each provider's page.

# Provider Input / 1M Cached / 1M Output / 1M Checked Notes
1 $0.14 $0.0042 $0.42 25 Sep 2026 Promotional price, 30% off list $0.20 / $0.60
2 $0.15 $0.003 $0.60 25 Sep 2026
3 $0.20 $0.006 $0.60 25 Sep 2026 Listed as deepseek/deepseek-v4-flash
4 $0.20 $0.01 $1.00 3 Oct 2026
5 €0.20 β‰ˆ $0.2273 €0.01 €1.00 β‰ˆ $1.1367 1 Oct 2026
6 €0.22 β‰ˆ $0.2501 €0.011 €1.10 β‰ˆ $1.2504 1 Oct 2026
7 $0.30 – $1.20 25 Sep 2026 International region, busy hours; idle hours are half price
8 $0.30 $0.007 $1.20 25 Sep 2026
9 $0.30 $0.03 $1.20 30 Oct 2026 Runs in a confidential computing enclave (Intel TDX, NVIDIA CC mode)
10 $0.30 $0.00 $1.20 29 Sep 2026 Listed as deepseek-v4.1-flash-fast-fp4 (MXFP4)
11 $0.30 $0.006 $1.20 25 Sep 2026 Peak rate; off-peak hours are half price
12 $0.30 $0.006 $1.20 25 Sep 2026 Standard tier
13 $0.30 $0.03 $1.20 2 Nov 2026 Shared Endpoints, billed per token
14 $0.30 $0.006 $1.20 25 Sep 2026
15 $0.30 $0.006 $1.20 25 Sep 2026
16 $0.25 – $1.75 1 Oct 2026
17 $0.50 $0.13 $1.50 15 Oct 2026 Currency shown as $ (assumed USD); VAT not stated.
18 €0.45 β‰ˆ $0.5115 – €1.75 β‰ˆ $1.9892 15 Oct 2026 Excl. VAT ("VAT may apply depending on your location"). The Norwegian site shows NOK.
19 €0.58 β‰ˆ $0.6593 €0.15 €1.73 β‰ˆ $1.9665 1 Oct 2026
20 €0.60 β‰ˆ $0.682 €0.12 €1.80 β‰ˆ $2.0461 15 Oct 2026 Paris region. Batches API -50%.

Each price was read off the provider's own pricing page on the date shown; the date links to that page. Providers that publish no per-token price for this model are not listed. EUR prices are ranked at the ECB reference rate of 24 September 2026. The same data is open under CC-BY at /api/query/prices.

Of the 8 European-headquartered providers checked, Aurora Inference lists the lowest blended rate for DeepSeek V4.1 Flash: $0.20 input and $0.60 output per 1M tokens, on its pricing page as of 25 September 2026.

European providers

Per 1M tokens, on-demand, for providers headquartered in Europe, sorted cheapest first by blended cost (3:1 input to output). See all European AI providers

# Provider Input / 1M Cached / 1M Output / 1M Checked Notes
1 $0.20 $0.006 $0.60 25 Sep 2026 Listed as deepseek/deepseek-v4-flash
2
Melious AI (DE)
€0.20 β‰ˆ $0.2273 €0.01 €1.00 β‰ˆ $1.1367 1 Oct 2026
3
GreenPT (NL)
€0.22 β‰ˆ $0.2501 €0.011 €1.10 β‰ˆ $1.2504 1 Oct 2026
4
LibertAI (FR)
$0.25 – $1.75 1 Oct 2026
5
TensorX (IE)
$0.50 $0.13 $1.50 15 Oct 2026 Currency shown as $ (assumed USD); VAT not stated.
6
WAYSCloud (NO)
€0.45 β‰ˆ $0.5115 – €1.75 β‰ˆ $1.9892 15 Oct 2026 Excl. VAT ("VAT may apply depending on your location"). The Norwegian site shows NOK.
7
HostYourAI (NL)
€0.58 β‰ˆ $0.6593 €0.15 €1.73 β‰ˆ $1.9665 1 Oct 2026
8
Scaleway (FR)
€0.60 β‰ˆ $0.682 €0.12 €1.80 β‰ˆ $2.0461 15 Oct 2026 Paris region. Batches API -50%.

Each price was read off the provider's own pricing page on the date shown; the date links to that page. Providers that publish no per-token price for this model are not listed. EUR prices are ranked at the ECB reference rate of 24 September 2026. The same data is open under CC-BY at /api/query/prices.

Compare every inference provider on free tiers, hosting and EU availability in the inference APIs table.

Is your product missing?

Add it here →