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

# DeepSeek V4 Flash

> Latency-optimised V4 — DeepSeek Pro quality on bounded prompts at sub-second TTFB.

**Vendor:** DeepSeek
**Model ID:** `deepseek-v4-flash`
**Capability:** 64K context · tool use · streaming · structured output
**Pricing:** per-token, flash tier ([live rate](https://bytespike.ai/pricing#text))

DeepSeek V4 Flash takes the V4 base and tunes for latency. Same
strong code generation on bounded prompts, half the wait of V4 Pro
on short inputs. Right pick for inline code suggestions, lint-style
fixes, and any agent step where one or two seconds matters.

## Request

```bash theme={null}
curl https://llm.bytespike.ai/v1/chat/completions \
  -H "Authorization: Bearer $BYTESPIKE_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Add type hints to this Python function."}]
  }'
```

### Body parameters

| Field             | Type    | Required | Default   | Notes                       |
| ----------------- | ------- | -------- | --------- | --------------------------- |
| `model`           | string  | yes      | —         | `deepseek-v4-flash`         |
| `messages`        | array   | yes      | —         | —                           |
| `max_tokens`      | integer | no       | model max | Max: 8192.                  |
| `tools`           | array   | no       | —         | Function calling supported. |
| `response_format` | object  | no       | —         | JSON / structured output.   |
| `stream`          | boolean | no       | false     | SSE streaming.              |

## Response

```json theme={null}
{
  "id": "chatcmpl-…",
  "object": "chat.completion",
  "model": "deepseek-v4-flash",
  "choices": [{"index": 0, "message": {"role": "assistant", "content": "..."}, "finish_reason": "stop"}],
  "usage": {"prompt_tokens": 64, "completion_tokens": 142, "total_tokens": 206}
}
```

## Code examples

<CodeGroup>
  ```bash cURL theme={null}
  curl https://llm.bytespike.ai/v1/chat/completions \
    -H "Authorization: Bearer $BYTESPIKE_API_KEY" \
    -H "content-type: application/json" \
    -d '{"model": "deepseek-v4-flash", "messages": [{"role": "user", "content": "Add type hints."}]}'
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(base_url="https://llm.bytespike.ai/v1", api_key="$BYTESPIKE_API_KEY")
  resp = client.chat.completions.create(
      model="deepseek-v4-flash",
      messages=[{"role": "user", "content": "Add type hints to this Python function."}],
  )
  print(resp.choices[0].message.content)
  ```

  ```javascript Node theme={null}
  import OpenAI from "openai"

  const client = new OpenAI({
    baseURL: "https://llm.bytespike.ai/v1",
    apiKey: process.env.BYTESPIKE_API_KEY,
  })
  const resp = await client.chat.completions.create({
    model: "deepseek-v4-flash",
    messages: [
      { role: "user", content: "Add type hints to this Python function." },
    ],
  })
  console.log(resp.choices[0].message.content)
  ```
</CodeGroup>

## Streaming + caching

`"stream": true` for SSE. Automatic prompt caching.

## Errors

| Code                        | Trigger  | Billed?         |
| --------------------------- | -------- | --------------- |
| 400 / 401 / 402 / 422 / 429 | Standard | No              |
| 5xx                         | Upstream | No (auto-retry) |

## When to use

* Inline code suggestions, lint-style fixes, IDE-integrated agents.
* Latency-bound code routing.
* For full V4 Pro quality on hard problems, see [DeepSeek V4 Pro](/api-reference/text/deepseek-v4-pro).

## Limits

| Limit                   | Value       |
| ----------------------- | ----------- |
| Context window          | 64K tokens  |
| Max output              | 8192 tokens |
| Supports tool use       | Yes         |
| Supports vision         | No          |
| Supports streaming      | Yes         |
| Supports prompt caching | Automatic   |