Grok 4.20 Beta Latest Non Reasoning
xai/grok-4.20-beta-latest-non-reasoningGrok 4.20 Beta Latest Non Reasoning (xai/grok-4.20-beta-latest-non-reasoning) is an AI model from xAI with a 1,000,000-token context window and 1,000,000 max output tokens, priced at $1.25/1M input and $2.50/1M output tokens. Available via the haimaker.ai OpenAI-compatible API.
Overview
xAI's Grok, a large language model with real-time knowledge, reasoning, and function calling capabilities.
Features & Capabilities
| Mode | chat |
| Context Window | 1,000,000 tokens |
| Max Output | 1,000,000 tokens |
| Function Calling | Supported |
| Vision | Supported |
| Reasoning | Not supported |
| Web Search | Supported |
| Url Context | Not supported |
API Usage
from openai import OpenAI
client = OpenAI(
base_url="https://api.haimaker.ai/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="xai/grok-4.20-beta-latest-non-reasoning",
messages=[
{"role": "user", "content": "Hello, how are you?"}
],
)
print(response.choices[0].message.content)Frequently Asked Questions
What is the context window of Grok 4.20 Beta Latest Non Reasoning?
Grok 4.20 Beta Latest Non Reasoning (xai/grok-4.20-beta-latest-non-reasoning) has a 1,000,000-token context window and supports up to 1,000,000 output tokens per request.
How much does Grok 4.20 Beta Latest Non Reasoning cost?
Grok 4.20 Beta Latest Non Reasoning is priced at $1.25 per 1M input tokens and $2.50 per 1M output tokens when accessed via the haimaker.ai OpenAI-compatible API.
What features does Grok 4.20 Beta Latest Non Reasoning support?
Grok 4.20 Beta Latest Non Reasoning supports function calling, vision, web search.
How do I use Grok 4.20 Beta Latest Non Reasoning via API?
Send requests to https://api.haimaker.ai/v1/chat/completions with model "xai/grok-4.20-beta-latest-non-reasoning" using any OpenAI-compatible SDK. Authentication uses a Bearer API key from https://app.haimaker.ai.
Use Grok 4.20 Beta Latest Non Reasoning with the haimaker API
OpenAI-compatible endpoint. Start building in minutes.