# DeepSeek Flash (V4.1) (DeepSeek) — API pricing and providers

> Budget reasoning. Model id `deepseek/deepseek-flash`. Text model by DeepSeek.

- Page: https://infro.io/models/deepseek/deepseek-flash
- Vendor: DeepSeek (https://infro.io/models/deepseek)
- Modality: Text
- Endpoint through INFRO: `POST /v1/chat/completions` at https://api.infro.io/v1
- List rate: $0.30 per 1M input tokens and $1.20 per 1M output tokens, with cached input at $0.0060 per 1M tokens
- Rates checked: 2026-10-05

Rates are DeepSeek's published list price: what the customer's own provider account bills, not an INFRO charge. INFRO is a BYOK control plane; it charges a software subscription and adds 0% to model spend.

## Providers that serve it

| Provider | Model id sent |
| --- | --- |
| Together AI | `deepseek-ai/DeepSeek-V4.1-Flash` |
| Fireworks AI | `accounts/fireworks/models/deepseek-v4p1-flash` |
| DeepSeek | `deepseek-flash` |
| OpenRouter | `deepseek/deepseek-v4.1-flash` |
| KIE | `deepseek-v4-1-flash` |

## Questions

### How much does the DeepSeek Flash (V4.1) API cost?

DeepSeek's published list rate for DeepSeek Flash (V4.1) is $0.30 per 1M input tokens and $1.20 per 1M output tokens, with cached input at $0.0060 per 1M tokens (checked 2026-10-05). The provider account you connect bills you at the rate on that account, so a negotiated rate replaces the list rate. INFRO adds 0% to model spend.

### Which providers serve DeepSeek Flash (V4.1)?

In INFRO's provider registry, DeepSeek Flash (V4.1) can be served by Together AI, Fireworks AI, DeepSeek, OpenRouter and KIE. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the DeepSeek Flash (V4.1) model ID?

Request it from INFRO as "deepseek/deepseek-flash". INFRO sends each provider its own id: Together AI "deepseek-ai/DeepSeek-V4.1-Flash", Fireworks AI "accounts/fireworks/models/deepseek-v4p1-flash", DeepSeek "deepseek-flash", OpenRouter "deepseek/deepseek-v4.1-flash", KIE "deepseek-v4-1-flash".

### How do I call DeepSeek Flash (V4.1) through an OpenAI-compatible API?

Point an OpenAI SDK, or any HTTP client, at https://api.infro.io/v1 with an INFRO gateway key and send model "deepseek/deepseek-flash" to POST /v1/chat/completions. INFRO runs the request on a provider account you connected and returns the provider's response with an estimated cost.

### Does INFRO mark up DeepSeek Flash (V4.1) usage?

No. DeepSeek or the provider you connect bills model usage to your own account. INFRO charges a software subscription for routing, failover, observability, budgets and policy, and takes 0% of model spend.