Early access: features, availability, and pricing may change as Kyara Intelligence evolves.
All models
Above baseline Reasoning

xAI: Grok 4.7

xAI's Grok 4.7 flagship for long-running coding and agentic tasks, with 500K context.

Model ID x-ai/grok-4.7
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": "x-ai/grok-4.7",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'
See the full API reference
Overview

Grok 4.7 succeeds Grok 4.6 as xAI's flagship model for coding, agentic tasks, and knowledge work, and is particularly strong at long-running software engineering and verifying its own work. Its 500K token context window and up to 450K tokens of output leave room for large inputs and long generations. Configurable reasoning effort and text, image, and file input let it scale from quick answers to deep analysis.

Specifications
Context window
500K tokens Huge
Cost vs catalog median
Input
4x
Output
4x
Input 28.8M credits / M tokens
Output 86.4M credits / M tokens

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

Reasoning
Available
Status
Current
Moderation

Kyara Intelligence does not add a moderation layer. Moderating what goes in and out of your integration is up to you as the developer.

Kyara routes API calls without modifying inputs or outputs, and does not log prompt or response content. You are responsible for how your app uses the models and for complying with Kyara's terms.