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

KI
All models
Below baseline Reasoning

Mistral: Mistral Small 4

A signature model tuned for immersive RP and long-form storytelling.

Model ID mistralai/mistral-small-2603
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": "mistralai/mistral-small-2603",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'
See the full API reference
Overview

Aria Plus is a signature roleplay experience powered by Mistral Small 4. Every response feels intentional: characters stay in voice, emotional beats land naturally, and long narratives hold together from first message to last. With a 260K token context window and deep RP tuning, Aria Plus is built for immersive, sustained storytelling.

Specifications
Context / Memory ⚡ Large · 260K tokens
Cost vs baseline Below baseline
Input
0.3x
Output
0.5x
Input
2.7M
cr / M tokens
Output
10.8M
cr / M tokens

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

Model ID
mistralai/mistral-small-2603
Reasoning
Available
Status
Current
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.