Skip to main content
Novita AI logo

DeepSeek V4.1 Flash API pricing on Novita AI

Every Novita AI DeepSeek V4.1 Flash rate we track, compared against 20 providers serving the same model.

Input from /1M
$0.300
Output /1M
$1.20
Input price rank
#8 of 20
Last updated
October 27, 2026

The cheapest DeepSeek V4.1 Flash input price we currently track is $0.140/1M on IteraCompute.

The cheapest DeepSeek V4.1 Flash output price is $0.550/1M on IteraCompute.

Novita AI DeepSeek V4.1 Flash rates

Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.

Novita AI DeepSeek V4.1 Flash pricing by mode
ModeInputOutput
Standard$0.300/1M$1.20/1M

About DeepSeek V4.1 Flash

Creator
DeepSeek
Modalities
text
Open weights
Yes
Full DeepSeek V4.1 Flash details and every provider →Compare API pricing for every DeepSeek model →

DeepSeek V4.1 Flash on other providers

About Novita AI

Novita AI is an inference platform serving 200+ models through a single OpenAI-compatible API, alongside serverless GPU jobs, on-demand GPU instances, and bare-metal clusters. Its catalogue is weighted toward open-weight families — Qwen, DeepSeek, GLM, Kimi, MiniMax, Llama and Gemma — with per-token billing and prompt caching on most chat models.

Frequently Asked Questions

How much does DeepSeek V4.1 Flash cost on Novita AI?

Novita AI serves DeepSeek V4.1 Flash from $0.300 per 1M input tokens, across 1 tracked pricing mode. Prices are collected daily — see the table above for current input, output, and cached-input rates.

Is Novita AI the cheapest way to run DeepSeek V4.1 Flash?

Novita AI ranks #8 of 20 providers we track serving DeepSeek V4.1 Flash on input price. The cheapest input price right now is on IteraCompute. The lowest output price is $0.550/1M on IteraCompute. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.

Does Novita AI offer batch or cached pricing for DeepSeek V4.1 Flash?

We track 1 DeepSeek V4.1 Flash offering from Novita AI. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.