DeepSeek V4.1 Flash API pricing on Lyceum
Every Lyceum DeepSeek V4.1 Flash rate we track, compared against 21 providers serving the same model.
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.
Lyceum DeepSeek V4.1 Flash rates
Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.
| Mode | Input | Output |
|---|---|---|
| Standard | $0.500/1M | $1.50/1M |
About DeepSeek V4.1 Flash
- Creator
- DeepSeek
- Modalities
- text
- Open weights
- Yes
DeepSeek V4.1 Flash on other providers
- IteraCompute$0.140/1M
- OpenRelay$0.150/1M
- GMI Cloud$0.180/1M
- Deep Infra$0.200/1M
- IO.NET$0.253/1M
- Heabsy$0.280/1M
- Crusoe$0.290/1M
- Baseten$0.300/1M
- DeepSeek$0.300/1M
- DigitalOcean$0.300/1M
- Empirio Labs$0.300/1M
- Fireworks AI$0.300/1M
- Geodd$0.300/1M
- Mistral AI$0.300/1M
- Novita AI$0.300/1M
- PopNow$0.300/1M
- Prime Intellect$0.300/1M
- Together AI$0.300/1M
- HiAPI$0.440/1M
- Scaleway$0.670/1M
About Lyceum
Lyceum offers serverless inference, dedicated endpoints, GPU VMs, and large-scale clusters for AI workloads. The platform is designed to facilitate the deployment and management of AI solutions without the complexity of traditional infrastructure.
Frequently Asked Questions
How much does DeepSeek V4.1 Flash cost on Lyceum?
Lyceum serves DeepSeek V4.1 Flash from $0.500 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 Lyceum the cheapest way to run DeepSeek V4.1 Flash?
Lyceum ranks #20 of 21 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 Lyceum offer batch or cached pricing for DeepSeek V4.1 Flash?
We track 1 DeepSeek V4.1 Flash offering from Lyceum. 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.