All models
Grok

Grok 4.7

x-ai/grok-4.7

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks and verifying its own work. Note: prompts longer than 200K tokens are billed by the provider at double the listed rate.

Pricing

Input$1.60per 1M tokens
Output$4.80per 1M tokens
Cached input$0.4per 1M tokens read from cache

Specifications

Context window500Ktokens
Max output66Ktokens
ProviderGrok
CapabilitiesVision · Reasoning · Function calling
Input typestext, image

Use Grok 4.7

Point your existing OpenAI SDK at xKiro and pass x-ai/grok-4.7 as the model. Nothing else in your code changes.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.xkiro.com/v1",
    api_key="YOUR_XKIRO_KEY",
)

response = client.chat.completions.create(
    model="x-ai/grok-4.7",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

max_tokens · temperature · top_p · stop · frequency_penalty · presence_penalty · seed · stream · tools · tool_choice · response_format · structured_outputs · reasoning · include_reasoning

Related models

Call Grok 4.7 through the same endpoints you already use.

Get an API key