Grok - Askr

Grok is xAI’s family of models: conversational, quick, and tuned for a more direct style. A good pick for chat-first products and up-to-the-minute topics.

Best for

Conversational assistants with a distinctive voice.
Current-events and real-time-leaning questions.
Fast, general-purpose chat.


Modality	Chat & code (text in, text out)
Example model id	`grok-4`
Endpoint	`POST /chat/completions`

Example

curl https://api.heyaskr.ai/chat/completions \
  -H "Authorization: Bearer ASKR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4",
    "messages": [
      {"role": "user", "content": "Give me a punchy tagline for a coffee brand."}
    ]
  }'

from openai import OpenAI
client = OpenAI(base_url="https://api.heyaskr.ai", api_key="ASKR_API_KEY")

resp = client.chat.completions.create(
    model="grok-4",
    messages=[
        {"role": "user", "content": "Give me a punchy tagline for a coffee brand."},
    ],
)
print(resp.choices[0].message.content)

Pricing

Priced per token, input and output separately. As a rough guide, expect around $3 per 1M input tokens and $15 per 1M output tokens for the flagship model.

Image
Grok on Askr: model card and pricing

The model id and prices above are examples. Confirm the exact id and current price against the live /v1/models list before you rely on them.

⌘I