Early access: features, availability, and pricing may change as Kyara Intelligence evolves.

Above baseline Reasoning Obsolete

Google: Gemini 3 Flash Preview

The ultimate SFW roleplay experience with premium-level intelligence and million-token context.

This is a legacy model, superseded by newer releases. It remains fully available to use.

Model ID google/gemini-3-flash-preview

Quick start

Drop this model into any OpenAI-compatible client by setting the base URL, your API key, and the model ID below.

curl https://api.kyara-intelligence.com/v1/chat/completions \
  -H "Authorization: Bearer $KYARA_INTELLIGENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3-flash-preview",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

See the full API reference

Overview

Iris 3 is the state-of-the-art SFW roleplay model powered by Google's Gemini 3 Flash Preview. This high-speed thinking model delivers near Pro-level reasoning with substantially lower latency than larger Gemini variants, making it perfect for immersive, dynamic roleplay sessions. Features a massive 1,048,576 token context window for epic, long-form storytelling, with configurable reasoning via thinking levels (minimal, low, medium, high) to match your RP style. Optimized for users who want strong intelligence and engaging character interactions with the safety and reliability of Google's premium technology.

Specifications

Context / Memory 🌌 Extreme · 1M tokens

Cost vs baseline Above baseline

Input

1.1x

Output

2.5x

Input

cr / M tokens

Output

54M

cr / M tokens

Multiples are relative to the catalog median; bars are scaled to the most expensive model.

Model ID

google/gemini-3-flash-preview

Reasoning

Available

Status

Obsolete

Upstream moderation

All models on Kyara Intelligence are accessed through their original API providers (Mistral, Z.AI/GLM, xAI, DeepSeek, and others). Each provider's content policies and moderation apply to all requests.

Kyara routes API calls without modifying inputs or outputs, and does not log prompt or response content. Users are responsible for complying with the relevant provider's terms of service in addition to Kyara's terms.