DeepSeek V4 Flash API pricing on Novita AI
Every Novita AI DeepSeek V4 Flash rate we track, compared against 20 providers serving the same model.
The cheapest DeepSeek V4 Flash input price we currently track is $0.050/1M on OpenRouter.
Novita AI DeepSeek V4 Flash rates
Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.
| Mode | Input | Output |
|---|---|---|
| Standard | $0.440/1M | $1.32/1M |
About DeepSeek V4 Flash
- Creator
- DeepSeek
- Context
- 1.0M
- Modalities
- text
- Open weights
- Yes
DeepSeek V4 Flash on other providers
- OpenRouter$0.050/1M
- Deep Infra$0.060/1M
- GMI Cloud$0.091/1M
- Baseten$0.130/1M
- Crusoe$0.140/1M
- DigitalOcean$0.140/1M
- Geodd$0.140/1M
- HiAPI$0.140/1M
- Together AI$0.140/1M
- Velokey$0.140/1M
- IO.NET$0.168/1M
- OpenRelay$0.220/1M
- Lyceum$0.250/1M
- Heabsy$0.280/1M
- Empirio Labs$0.424/1M
- Prime Intellect$0.440/1M
- Scaleway$0.448/1M
- EcoHash$0.490/1M
- VoltageGPU$0.810/1M
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 Flash cost on Novita AI?
Novita AI serves DeepSeek V4 Flash from $0.440 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 Flash?
Novita AI ranks #16 of 20 providers we track serving DeepSeek V4 Flash. The cheapest input price right now is on OpenRouter. Price is only one factor — throughput, latency, and context limits differ between providers.
Does Novita AI offer batch or cached pricing for DeepSeek V4 Flash?
We track 1 DeepSeek V4 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.