# DeepSeek-V4.1-Flash API on ScaledThought

> DeepSeek-V4.1-Flash, the open-weight model from DeepSeek, is live on ScaledThought's OpenAI-compatible API in the US region as deepseek-v4-1-flash, at $0.22 per 1M input tokens and $0.66 per 1M output tokens (last read 2026-11-08 19:53 UTC).

## Price

USD per 1M tokens, US region, read from the US region's API at 2026-11-08 19:53 UTC (re-read at most every 5 minutes). Every live model's price: https://scaledthought.com/pricing

- Input: $0.22
- Cached input: $0.007
- Output: $0.66

## Specs

- Model id: deepseek-v4-1-flash
- Publisher: DeepSeek
- Weights released: Sep 10, 2026
- Parameters: 552B total, 16B active
- Architecture: MoE
- Context: 1M tokens (1,000,000)
- Region: US
- Licence: MIT
- Weights: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash

Licence text: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash. You must follow it when you use the model through ScaledThought.

## Set up

Tell your agent: "Set me up on ScaledThought to use deepseek-v4-1-flash: scaledthought.com/go/org-models". Full setup protocol: https://scaledthought.com/go/org-models

## Call it

Base URL `https://api.us.scaledthought.com/v1` (OpenAI-compatible). After setup, `./.env` holds `ST_API_KEY` and `ST_BASE_URL`.

### Python

```
import os
from openai import OpenAI

client = OpenAI(base_url=os.environ["ST_BASE_URL"], api_key=os.environ["ST_API_KEY"])
resp = client.chat.completions.create(
    model="deepseek-v4-1-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
```

### TypeScript

```
import OpenAI from "openai";

const client = new OpenAI({ baseURL: process.env.ST_BASE_URL, apiKey: process.env.ST_API_KEY });
const resp = await client.chat.completions.create({
  model: "deepseek-v4-1-flash",
  messages: [{ role: "user", content: "Hello" }],
});
```

### curl

```
curl "$ST_BASE_URL/chat/completions" \
  -H "Authorization: Bearer $ST_API_KEY" \
  -H "content-type: application/json" \
  -d '{"model":"deepseek-v4-1-flash","messages":[{"role":"user","content":"Hello"}]}'
```

### CLI

```
npx -y scaledthought@0.6 chat -m deepseek-v4-1-flash "Hello"
```

## Other live models

- MiMo-V2.6-Flash (`mimo-v2-6-flash`): https://scaledthought.com/models/mimo-v2-6-flash