> ## Documentation Index
> Fetch the complete documentation index at: https://docs.hostlinku.com/llms.txt
> Use this file to discover all available pages before exploring further.

# DeepSeek-V4.1-Flash Turbo

> DeepSeek-V4.1-Flash is a multimodal mixture-of-experts model built on an asymmetric Causal Encoder–Decoder architecture, with native visual understanding. It...

## Overview

DeepSeek-V4.1-Flash is a multimodal mixture-of-experts model built on an asymmetric Causal Encoder–Decoder architecture, with native visual understanding. It supports a 1M-token context window, up to 384K output tokens, thinking and non-thinking modes, tool calls, and structured JSON output. Available on the Hostlinku Dedicated channel with a higher throughput lane.

| Property | Value |
| - | - |
| Provider | DeepSeek |
| Slug | `deepseek-v4-1-flash-turbo` |
| Context | 1,000,000 tokens |
| Max output | 384,000 tokens |
| Input | text, image |
| Output | text |
| Release | 2026-09-13 |
| Tags | fast, budget, dedicated |

## Capabilities

* `text`
* `tool-calling`
* `function-calling`
* `structured-outputs`
* `json-mode`
* `streaming`
* `reasoning`
* `code-generation`
* `long-context`
* `multilingual`
* `vision`
* `image-input`
* `multimodal`

## Pricing

| Item | Price |
| - | - |
| Input (prompt) | - |
| Output (completion) | - |
| Cache read | - |
| Cache write | - |

Prices are customer prices per **1M tokens** for a Hostlinku API key, with 1 kredit = \$1. Actual cost per request follows the API key's Service Mode and may change; check [Console](https://console.hostlinku.com/models) or `GET /v1/models` for current values.

## Supported endpoints

| Endpoint | Format | Support |
| - | - | - |
| `POST /v1/chat/completions` | OpenAI Chat Completions | available |
| `POST /v1/messages` | Anthropic Messages | adapted (bridge) |
| `POST /v1/responses` | OpenAI Responses | adapted (bridge) |

Endpoint and model availability follow the catalog and the API key's Service Mode. If a model is unavailable for that mode, the request may be rejected with `400 MODEL_NOT_IN_SERVICE_MODE`.

## Example request

```bash theme={null}
curl https://api.hostlinku.com/v1/chat/completions \
  -H "Authorization: Bearer sk-isi-api-key-kamu" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-1-flash-turbo",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'
```

## Related models

* [DeepSeek V4 Flash](https://docs.hostlinku.com/en/models/deepseek-v4-flash.md)
* [DeepSeek V4 Pro](https://docs.hostlinku.com/en/models/deepseek-v4-pro.md)
* [DeepSeek-V4.1-Flash](https://docs.hostlinku.com/en/models/deepseek-v4-1-flash.md)
* [DeepSeek-V4.1-Flash Hyper](https://docs.hostlinku.com/en/models/deepseek-v4-1-flash-hyper.md)
* [DeepSeek-V4.1-Flash Hyper Chat](https://docs.hostlinku.com/en/models/deepseek-v4-1-flash-hyper-chat.md)

[← Back to the model catalog](https://docs.hostlinku.com/en/models.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.