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

# DeepSeek

> Every DeepSeek model Verlon supports — the V4 family on DeepSeek’s own API — with quickstart, thinking, time-of-use pricing, and SDK compatibility.

DeepSeek's V4 family, on DeepSeek's own API, is routable through Verlon in whichever SDK you already use. No DeepSeek-specific SDK required. (The same open weights are also served by [Fireworks](https://docs.verlon.ai/provider-compatibility/fireworks.md) under `accounts/fireworks/models/...` ids.)

## Chat models

| Model ID | Type | Context |
| - | - | - |
| `deepseek-flash` | chat | 1049K |
| `deepseek-v4-flash` | chat | 1000K |
| `deepseek-v4-flash-vision-exp` | chat | 1000K |
| `deepseek-v4-pro` | chat | 1049K |

> [!NOTE]
>
> This table is auto-generated from the Verlon model registry on every sync —
> see the [live registry](https://docs.verlon.ai/provider-compatibility/models.md#live-registry) for
> pricing, capabilities, and deprecation dates.

## Quickstart

```typescript theme={null}
import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: 'https://api.verlon.ai/v1',
  apiKey: process.env.VERLON_API_KEY,
});

const response = await openai.chat.completions.create({
  model: 'deepseek-v4-flash',
  messages: [{ role: 'user', content: 'Hello!' }],
});

console.log(response.choices[0].message.content);
```

Already using DeepSeek's API? DeepSeek serves OpenAI Chat Completions, OpenAI Responses and Anthropic Messages, and Verlon mirrors all three: swap the base URL on the SDK you have.

## Thinking

The V4 models think by default. `reasoning_effort` (`low`, `medium`, `high`) passes through; `reasoning_effort: "none"` turns thinking off. Thinking tokens are billed as output.

Two requests DeepSeek refuses in thinking mode are served with thinking off for that request, and the response says so:

* **A forced tool choice** (`tool_choice` naming a tool, or `required`): DeepSeek honours it only with thinking off (`x-verlon-emulated: tool_choice`).
* **A tool loop whose history lacks the model's own reasoning** — a client on another SDK, or one that kept only the answer: DeepSeek requires the reasoning passed back in thinking mode, so that turn runs without it (`x-verlon-dropped: thinking`).

## Pricing by the clock

DeepSeek prices on the clock: peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday, and every other hour is off-peak at half the peak rate — all US and European business hours and every weekend. The registry's standard rates are the off-peak card, with the peak card under its tier pricing. Verlon prices each request by the window in force when the response completed.

## What's supported

> [accordion] Streaming
>
> Full support for `stream: true` in every supported SDK.

> [accordion] Tool / function calling
>
> Supported, with forced tool choice served as described under
> [Thinking](#thinking).

> [accordion] Structured output
>
> `json_object` works on chat completions. A strict `json_schema` is enforced
> only on DeepSeek's Responses API, so Verlon sends those requests there
> (`x-verlon-translated: chat->responses`) and the answer fits your schema.

> [accordion] Prompt caching
>
> DeepSeek caches prompt prefixes automatically; cached input tokens are
> billed at its cache rate and reported in every response's usage.

> [accordion] Usage + cost tracking
>
> Every response includes token usage plus Verlon's `cost` field, at the
> peak or off-peak rate in force.

### Not available

* **PDF input.** DeepSeek accepts no documents; route PDFs to a model that reads them.
* **Image, video, audio generation, embeddings.** Route those to another provider and keep chat on DeepSeek — that mix is what gates are for.

## Related

* [Any SDK, any model](https://docs.verlon.ai/provider-compatibility/translation.md) — what the gateway translates, serves itself, or drops, and the headers that say so.
* [Fireworks](https://docs.verlon.ai/provider-compatibility/fireworks.md) — the same open weights on a serverless channel.


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