Models and prices / deepseek-v4.1-flash
DeepSeek V4.1 Flash 40% off
DeepSeek's latest Flash model. Fast and inexpensive, with about 1M tokens of context, tool calls and image input. A good default for coding assistants, agents and everyday chat.
OpenAI compatibleAnthropic compatible
Pricing
| Item (USD per 1M tokens) | Price |
|---|---|
| Input | $0.1791 Peak $0.0896 Off-peak |
| Cached input | $0.0036 Peak $0.0018 Off-peak |
| Output | $0.7164 Peak $0.3582 Off-peak |
- Send deepseek-v4.1-flash as the model.
- This model has peak and off-peak prices; see peak hours in your time zone below.
- Cached input is the part of a prompt served from the context cache. The struck-through price is the model maker's own price.
- Thinking is billed as output tokens. Set max_tokens to 1000 or more, or the budget may go to thinking alone.
- When you do not need reasoning, add "thinking": {"type": "disabled"} to the request, or use "reasoning_effort": "low": simple tasks get noticeably cheaper and faster.
Specs
| Context window | 1M tokens |
| Input | text, images |
| APIs | OpenAI Chat Completions, Anthropic Messages |
| Reasoning (thinking) | Yes, billed as output tokens |
Peak hours in your time zone
Models marked Peak / Off-peak cost less outside peak hours. The price is set by when the request arrives. Peak hours are 09:00–12:00 and 14:00–18:00 (UTC+8), Monday to Friday. Weekends (UTC+8) are off-peak all day. In local time this week:
| Time zone | Peak hours (all other times are off-peak) |
|---|---|
| UTC (UTC) | Mon–Fri 01:00–04:00 and 06:00–10:00 |
| London (UTC+1) | Mon–Fri 02:00–05:00 and 07:00–11:00 |
| Paris, Berlin, Amsterdam (UTC+2) | Mon–Fri 03:00–06:00 and 08:00–12:00 |
| New York, Toronto (US Eastern) (UTC-4) | Sun–Thu 21:00–24:00 Mon–Fri 02:00–06:00 |
| Los Angeles, Vancouver (US Pacific) (UTC-7) | Sun–Thu 18:00–21:00 and 23:00–03:00 next day |
| India (UTC+5:30) | Mon–Fri 06:30–09:30 and 11:30–15:30 |
| Bangkok, Jakarta, Ho Chi Minh City (UTC+7) | Mon–Fri 08:00–11:00 and 13:00–17:00 |
| Singapore, Kuala Lumpur, Manila, Hong Kong (UTC+8) | Mon–Fri 09:00–12:00 and 14:00–18:00 |
| Tokyo, Seoul (UTC+9) | Mon–Fri 10:00–13:00 and 15:00–19:00 |
| Sydney (UTC+11) | Mon–Fri 12:00–15:00 and 17:00–21:00 |
Times follow daylight saving time and are shown for the current week.
Call it with the OpenAI API
curl https://api.aifans.fan/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek-v4.1-flash", "messages": [{"role": "user", "content": "Hello"}], "max_tokens": 1000}'# pip install openai
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.aifans.fan/v1")
resp = client.chat.completions.create(
model="deepseek-v4.1-flash",
messages=[{"role": "user", "content": "Hello"}],
max_tokens=1000,
)
print(resp.choices[0].message.content)Use it in Claude Code
Put this in ~/.claude/settings.json (Windows: %USERPROFILE%\.claude\settings.json) and start Claude Code.
{
"env": {
"ANTHROPIC_BASE_URL": "https://api.aifans.fan",
"ANTHROPIC_AUTH_TOKEN": "YOUR_API_KEY",
"ANTHROPIC_MODEL": "deepseek-v4.1-flash",
"ANTHROPIC_DEFAULT_OPUS_MODEL": "deepseek-v4.1-flash",
"ANTHROPIC_DEFAULT_SONNET_MODEL": "deepseek-v4.1-flash",
"ANTHROPIC_DEFAULT_HAIKU_MODEL": "deepseek-v4.1-flash",
"CLAUDE_CODE_SUBAGENT_MODEL": "deepseek-v4.1-flash"
}
}