# DeepSeek models — API pricing and providers

> 3 DeepSeek models with DeepSeek's list rates (checked 2026-10-05). Page: https://infro.io/models/deepseek

| Model | Id | Modality | List rate | Providers |
| --- | --- | --- | --- | --- |
| [DeepSeek Flash (V4.1)](https://infro.io/models/deepseek/deepseek-flash) | `deepseek/deepseek-flash` | Text | $0.30 per 1M input tokens and $1.20 per 1M output tokens, with cached input at $0.0060 per 1M tokens | 5 |
| [DeepSeek V4 Pro](https://infro.io/models/deepseek/deepseek-v4-pro) | `deepseek/deepseek-v4-pro` | Text | $1.32 per 1M input tokens and $3.96 per 1M output tokens, with cached input at $0.044 per 1M tokens | 3 |
| [DeepSeek V4 Flash](https://infro.io/models/deepseek/deepseek-v4-flash) | `deepseek/deepseek-v4-flash` | Text | $0.30 per 1M input tokens and $1.20 per 1M output tokens, with cached input at $0.0060 per 1M tokens | 3 |

## Questions

### Which DeepSeek models does this reference list?

3 DeepSeek models: 3 text. Each has its own page with DeepSeek's list rate and the providers that serve it.

### Which providers serve DeepSeek models?

Together AI, Fireworks AI, DeepSeek, OpenRouter, KIE and LaoZhang API. You connect your own account with any of them; INFRO routes between the ones you connect.

### What is the lowest DeepSeek input rate listed?

DeepSeek Flash (V4.1), at $0.30 per 1M input tokens and $1.20 per 1M output tokens, with cached input at $0.0060 per 1M tokens on DeepSeek's list (checked 2026-10-05).

### Does INFRO add a markup to DeepSeek model usage?

No. Your DeepSeek or provider account bills usage directly; INFRO charges a software subscription and takes 0% of model spend.