DeepSeek V3 API pricing on Deep Infra
Every Deep Infra DeepSeek V3 rate we track, compared against 4 providers serving the same model.
The cheapest DeepSeek V3 input price we currently track is $0.240/1M on Liquid Inference.
Deep Infra also has the cheapest DeepSeek V3 output price.
Deep Infra DeepSeek V3 rates
Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.
| Mode | Input | Output |
|---|---|---|
| Standard | $0.320/1M | $0.890/1M |
About DeepSeek V3
- Creator
- DeepSeek
- Context
- 64K
- Modalities
- text
- Knowledge cutoff
- Jun 2024
- Tool calling
- Yes
- Open weights
- Yes
DeepSeek V3 on other providers
About Deep Infra
Deep Infra is an AI inference cloud that provides serverless APIs for 100+ models and dedicated GPU rentals. Features OpenAI-compatible endpoints, custom model deployments, and infrastructure optimized for scale.
Frequently Asked Questions
How much does DeepSeek V3 cost on Deep Infra?
Deep Infra serves DeepSeek V3 from $0.320 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 Deep Infra the cheapest way to run DeepSeek V3?
Deep Infra ranks #3 of 4 providers we track serving DeepSeek V3 on input price. The cheapest input price right now is on Liquid Inference. Deep Infra also has the lowest DeepSeek V3 output price. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.
Does Deep Infra offer batch or cached pricing for DeepSeek V3?
We track 1 DeepSeek V3 offering from Deep Infra. 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.