xAI

Grok-4.7

xAI's latest flagship with a 500K context window, stronger performance on long coding tasks, self-verification, and knowledge work

Category Text Model ID grok-4.7

Context Length500K tokens

Model TypeLarge Language Model (LLM)

MultimodalText and image input; text output

Pricing & Specs

💰 Pricing

Input$2 / M tokens

Output$6 / M tokens

Cache Hit$0.5 / M tokens

⚙️ Specs

Context Length500K tokens

Model TypeLarge Language Model (LLM)

MultimodalText and image input; text output

Output LengthNo separate text output limit

Special CapabilitiesFunction calling, Web / X search, code execution

ReasoningLow, medium, high (default), or xhigh

Long-context Pricing (≥200K)Input $4; cached input $1; output $12 / M tokens for the full request

Web Search$5 / 1K tool calls

Release DateSeptember 21, 2026

Knowledge CutoffMay 2026

API Examples

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.xairouter.com/v1",
    api_key="your-api-key"
)

response = client.chat.completions.create(
    model="grok-4.7",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)

print(response.choices[0].message.content)

cURL

curl https://api.xairouter.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "grok-4.7",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Model highlights

Grok 4.7 uses a larger base model trained for longer coding, agentic, and knowledge-work tasks. It improves self-verification, long-context management, and document and presentation creation. See the official announcement.

API usage

Use model ID grok-4.7 with the Responses API or Chat Completions.
The Responses API automatically returns reasoning.encrypted_content, even without an explicit include. When managing conversation history yourself, pass reasoning items unchanged in the next request's input.
Once the prompt reaches 200K tokens, long-context pricing applies to the entire request. The API examples and base prices on this page use the standard model.

Grok 4.7 Fast is available only in Cursor and Grok Build, with no public xAI API access.

References: Model overview, model pricing.

← Back to Models