# DeepSeek: deepseek-flash — API on ChinaAPI

> DeepSeek V4.1 Flash, served through ChinaAPI's existing deepseek-flash model ID. Released on 2026-09-10, it is a native image-and-text 552B Mixture-of-Experts model with 8B parameters active during input prefill and 16B during output decoding, a 1M context window, and up to 384K output. It supports thinking and non-thinking modes, tool calling, JSON output, Responses API, and Anthropic-compatible access.

- Canonical page: https://chinaapi.ai/models/deepseek-flash/
- Model ID: `deepseek-flash`
- Context window: 1M
- Modalities: Text, image input
- Pricing: $0.3/M input, $1.2/M output tokens (USD)
- Endpoint: OpenAI-compatible `POST https://api.chinaapi.ai/v1/chat/completions`
- Price note: DeepSeek charges peak rates on Beijing-time weekdays from 09:00–12:00 and 14:00–18:00. All other times are off-peak at exactly half price, including cache reads. The headline prices show the higher peak tier; all tiers are listed below. Live gateway billing remains authoritative.
- Pricing basis: Token-model rates are synchronized from the gateway and may follow providers' official China list prices where configured. Live pricing is authoritative.
- Access: no mainland-China account or phone number required; $2 free trial credit
- Sign up: https://dash.chinaapi.ai/register?lang=en&utm_source=chinaapi&utm_medium=model-md&utm_campaign=deepseek-flash

## Quickstart

```
curl -X POST https://api.chinaapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $CHINAAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-flash",
    "messages": [
      {"role": "user", "content": "Summarize the main tradeoffs for this API workload."}
    ]
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["CHINAAPI_API_KEY"],
    base_url="https://api.chinaapi.ai/v1",
)

response = client.chat.completions.create(
    model="deepseek-flash",
    messages=[
        {"role": "user", "content": "Summarize the main tradeoffs for this API workload."}
    ],
)
print(response.choices[0].message.content)
```

## FAQ

**How do I use deepseek-flash?**
Use deepseek-flash through ChinaAPI with an API key and the OpenAI-compatible endpoint shown on this page.

**How much does deepseek-flash cost?**
deepseek-flash is $0.3/M input, $1.2/M output tokens, paid in USD. The live pricing page is authoritative. Token-model rates are synchronized from the gateway and may follow providers' official China list prices where configured. Live pricing is authoritative.

**Does deepseek-flash need a Chinese account?**
No. ChinaAPI provides access without a mainland-China account or phone number and includes a $2 free trial. Check live pricing for the displayed USD rate.

---
Markdown twin of https://chinaapi.ai/models/deepseek-flash/ — generated by scripts/gen_model_pages.py. Full catalog: https://chinaapi.ai/llms-full.txt