Models & APIs / DigitalOcean Inference API pricing Verified 14 Nov 2026, 12:00 UTC Source docs.digitalocean.com/products/inference/details/pricing

DigitalOcean Inference API pricing

by DigitalOceanper 1M tokens
$0.20 / 1M outputMinistral 3 14B Instruct (DigitalOcean) · the cheapest model

DigitalOcean Inference API costs $0.10–$3.00 per 1M input tokens and $0.20–$15.00 per 1M output tokens. Output tokens cost several times more than input, so long answers drive the bill.

Cheapest output$0.20Ministral 3 14B Instruct (DigitalOcean) · per 1M
Top model$15.00Kimi K3 (DigitalOcean) · per 1M output

Every model, per 1M tokens

USD list price, before batch or volume discounts
ModelInputOutputCached inputContext
gpt-oss-120b (DigitalOcean)$0.10$0.70——
Trinity Large (DigitalOcean)$0.25$0.90$0.06—
DeepSeek V4.1 Flash 1017 (DigitalOcean)$0.30$1.20$0.006—
DeepSeek V4.1 Flash (DigitalOcean)$0.30$1.20$0.006—
DeepSeek V4 Pro 0813 (DigitalOcean)$1.32$3.96$0.044—
DeepSeek V4 Flash 0731 (DigitalOcean)$0.14$0.28$0.028—
DeepSeek V4 Pro (DigitalOcean)$1.74$3.48$0.348—
DeepSeek V3.2 (DigitalOcean)$0.50$1.60$0.15—
MiniMax M3.1-Flash (DigitalOcean)$0.15$0.60$0.015—
MiniMax M2.5 (DigitalOcean)$0.30$1.20$0.06—
Kimi K3.1 Pro (DigitalOcean)$2.00$10.00$0.20—
Kimi K3 (DigitalOcean)$3.00$15.00$0.30—
Kimi K2.6 (DigitalOcean)$0.95$4.00$0.19—
Ministral 3 14B Instruct (DigitalOcean)$0.20$0.20$0.04—
NVIDIA Nemotron 3.5 Super VL (DigitalOcean)$0.30$0.65$0.06—
Reflection AI Beam (DigitalOcean)$0.40$1.20$0.04—
MiMo V2.5 Pro (DigitalOcean)$0.80$3.00$0.16—
GLM-5.3 (DigitalOcean)$1.40$4.40$0.26—
GLM-5.3 Flash (DigitalOcean)$0.15$0.50$0.03—
GLM-5.2 (DigitalOcean)$1.40$4.40$0.21—
Bill estimate

What will you pay?

$18.00
per month on Kimi K3 (DigitalOcean)

Other model APIs

Compare all models →
Prices from docs.digitalocean.com/products/inference/details/pricing How we collect prices Some links are affiliate links; they never change the prices or the order shown. Disclosure