Models

Open models, self-hosted by our GPU partner with zero data retention.

Get started Read the docs

3 models · from $0.08 per 1M input tokens · up to 1M context

Base URL https://lutheosfifi.fun/v1

DeepSeek V4.1 Flash 1017 Abliterated
DeepSeek Available
- Refusals removed
- FP8
- Text
- 128K max output
- Zero data retention
- 20% off
deepseek-v4.1-flash-abliterated
Input / 1M
~~was $0.10~~, now $0.08

Cached input / 1M
~~was $0.02~~, now $0.016

Output / 1M
~~was $0.40~~, now $0.32

Context
1M

Max output
128K

Try in chat
DeepSeek V4.1 Flash 1017
DeepSeek Available
- Refusals kept
- FP8
- Text
- 128K max output
- Zero data retention
deepseek-v4.1-flash
Input / 1M
$0.08

Cached input / 1M
$0.01

Output / 1M
$0.32

Context
1M

Max output
128K

Try in chat
GLM 5.3 Flash
Z.ai Available
- Refusals kept
- FP8
- Text
- Zero data retention
glm-5.3-flash
Input / 1M
$0.08

Cached input / 1M
$0.034

Output / 1M
$0.42

Context
—

Max output
—

Try in chat

Billed per token from your balance. No monthly fee, and a request that fails before its reply starts is not billed. Quickstart Pricing