OPHIRISOpen app

lyber · Frontier

Kimi K3.1 Pro Abliterated (Lyber)

Added Nov 16, 2026

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

Kimi K3.1 Pro Abliterated served by Lyber.ai.

  • Reasoning
  • Tools
  • Structured output
Input
Text
Output
Text
Reasoning effort
low · high · max
Discovery tier
Frontier

Pricing

USD per 1M tokens
Input
$4.00
Output
$15.00
Cache read
$0.40

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
1M

Side by side

Kimi K3.1 Pro Abliterated (Lyber) compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Kimi K3.1 Pro Abliterated (Lyber)lyberThis modelAbliterated Model Large V2abliterationRemove
Providerlyberabliteration
Discovery tierFrontierFrontier
AddedNov 16, 2026Aug 31, 2026
Limits
Context window1.05MBest1M
Max output1.05MBest999.99K
Pricing, USD per 1M tokens
Input$4.00$3.00Best
Output$15.00$5.00Best
Cache read$0.40$0.30Best
Performance
Throughput72.1 tok/s132.7 tok/sBest
Time to first token61.5 s4.2 sBest
Request success (24h)74.9%99.8%Best
Capabilities
ReasoningYesYes
ToolsYesYes
Structured outputYesYes
Reasoning effortlow, high, maxlow, high, max

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Ophiris catalog.

  • Kimi K3.1 Pro Abliterated (Lyber)
  • Abliterated Model Large V2
LeaderboardKimi K3.1 Pro Abliterated (Lyber)Abliterated Model Large V2
CombinedNot in top 20#1 · 33.3%

Ranks among Ophiris catalog models on Combined leaderboards. Only top-20 placements are listed.

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
72.1 tok/s
Faster than 44% of 52 models
Time to first token
61.5 s
Quicker than 1% of 52 models
Prompt cache hits
91.0%
About $0.72 per 1M input tokens with caching
Request success (24h)
74.9%

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Developers

Use it through the API

Ophiris’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
request.sh
curl https://www.ophiris.xyz/api/v1/chat/completions \  -H "Authorization: Bearer $OPHIRIS_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "lyber/kimi-k3.1-pro-abliterated",    "reasoning_effort": "low",    "messages": [{ "role": "user", "content": "Explain this stack trace." }]  }'
client.py
import osfrom openai import OpenAI client = OpenAI(base_url="https://www.ophiris.xyz/api/v1", api_key=os.environ["OPHIRIS_API_KEY"])reply = client.chat.completions.create(    model="lyber/kimi-k3.1-pro-abliterated",    messages=[{"role": "user", "content": "Explain this stack trace."}],)print(reply.choices[0].message.content)