Abliteration: Abliterated Large Flash
abliterated-model-large-flash
Abliterated Large Flash is an uncensored reasoning model based on DeepSeek V4.1-Flash-1017. It accepts text and images and returns text, with tool calling, JSON mode, JSON Schema output, and automatic prompt caching. Its shared input/output context is 1,048,576 tokens, with up to 262,144 output tokens when space permits. Reasoning defaults to high and can be turned off or set to low, high, or max. Supports up to four images across the request history.
模态
文本 + 图片 → 文本
输入 / 输出价
$1.30 / $2.60 每 1M
上下文
1.05M · 最长输出 262K
能力
价格
按实际 token 计费,从余额中扣除。人民币按 1 美元 ≈ 7.2 元折算,仅供参考。
| 计费项 | 美元 / 1M token | 人民币参考 |
|---|---|---|
| 输入 | $1.30 | ¥9.36 |
| 输出 | $2.60 | ¥18.72 |
| 缓存命中(输入) | $0.130 | ¥0.94 |
试算
拖动滑块估算这个模型的花费。
- 单次
- $0.00598
- 每天
- $2.99
- 每月(30 天)
- $89.70≈ ¥646
Abliterated Large Flash:输入 $1.3/M · 输出 $2.6/M · 缓存命中 $0.13/M
curl https://api.geniusrelaygpt.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "abliterated-model-large-flash", "max_tokens": 800,
"messages": [{"role": "user", "content": "…"}]}'接入代码
兼容 OpenAI 接口。把 Base URL 换成 https://api.geniusrelaygpt.com/v1,模型名填 abliterated-model-large-flash。
curl https://api.geniusrelaygpt.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "abliterated-model-large-flash",
"stream": true,
"messages": [{"role": "user", "content": "你好"}]
}'支持的参数
常用 OpenAI 参数都可以直接传。
temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed常见问题
- Abliterated Large Flash 怎么计费?
- 输入 $1.30、输出 $2.60 每百万 token,命中缓存的输入按 $0.130 计。每次请求的扣费都能在控制台使用日志里查到。
- 上下文有多长?
- 1.05M token。长对话每一轮都会按全部输入 token 计费,注意控制历史长度。
- 支持流式输出吗?
- 支持。请求里加
"stream": true,返回 SSE,格式与 OpenAI 一致。