Abliterated Model Router now live! Try it today free.

MoonshotAI: Kimi K3.1 Pro Abliterated

moonshotai/kimi-k3.1-pro-abliterated
1 providerText inputImage inputTool callingAbliterated
Input / output price$4 / $15 per 1M
Context1M tokens
Max output65.5K tokens
ReleasedNov 9, 2026

Providers

Available providers, with each one's token pricing and limits for this model.

ProviderZDRZero data retention (ZDR): the provider keeps no prompt or output after serving the request.ContextMax outputInput /MCache /MOutput /MLatencyTime to first token (median): how long after the request reaches the provider until the first output token streams back, measured on live streamed requests.SpeedModalitiesStatus
Lyber1M65.5K$4$0.40$153.4s73 tok/sText, Image → TextAvailableAvailableLast 5 min: 0%Last 30 min: 0%Last day: 66.31%

Capabilities

ModalitiesText, Image → Text
Reasoning effortmax, high, low, none
AbliterationAbliterated weights
max_tokensreasoningreasoning_effortresponse_formatseedstoptemperaturetool_choicetoolstop_pweb_search_options

API quickstart

Use the official OpenAI client with the AllModels OpenAI-compatible endpoint.

Client
Language

Response with the OpenAI SDK

Use the model ID above with the AllModels OpenAI-compatible Responses API.

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseURL: "https://api.allmodels.io/oai",
});

const response = await client.responses.create({
  model: "moonshotai/kimi-k3.1-pro-abliterated",
  input: "Hello!",
});

console.log(response.output_text);