Grok 4.6 is an xAI text reasoning model available through Chat Completions with streaming, JSON objects, tool calling, and four reasoning effort levels.
Provider: Grok
Category: text generation
Endpoint: /v1/chat/completions
Status: Available
Cost: --
Grok 4.6 is an xAI text reasoning model available through Chat Completions with streaming, JSON objects, tool calling, and four reasoning effort levels.
API access
Endpoint
POST /v1/chat/completions
Base URL
https://api.hiapi.ai
OpenAI Chat Completions compatible. Use one HiAPI key across all available models.
Input price
1,680 Credits
/ 1M tokens · Total input ≤ 200,000 tokens
Output price
5,040 Credits
/ 1M tokens · Total input ≤ 200,000 tokens
Context
-
context window
Max output
-
output tokens
Ask a question to stream the answer and inspect token usage, latency, and estimated cost.
Call Grok 4.6 with the OpenAI-compatible Chat Completions format. Copy a ready-to-use cURL, Python, or Node.js example below.
/v1/chat/completionscurl -X POST "https://api.hiapi.ai/v1/chat/completions" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-4.6",
"messages": [
{
"role": "user",
"content": "A cat walking on the beach at sunset"
}
],
"stream": false,
"reasoning_effort": "high"
}'Tip: Replace YOUR_API_KEY with your actual API key from the API Keys page.
Compatible with the OpenAI Chat Completions format. Set the base URL, API key, and model name to get started.
Billing follows the input, output, and cache token categories actually reported in usage. All prices below are shown per 1 million tokens.
Total input ≤ 200,000 tokens
Prompts and context sent to the model
Responses and reasoning generated by the model
The tier is selected by total input tokens per request, including cache reads and writes. Above the threshold, that tier applies to all input, output, and cache tokens in the request, not only the excess.
| Token type | Total input ≤ 200,000 tokens | Total input > 200,000 tokens |
|---|---|---|
| Input | 1,680 Credits | 3,360 Credits |
| Output | 5,040 Credits | 10,080 Credits |
| Cache read | 420 Credits | 840 Credits |
All prices are per 1 million tokens.
These specifications reflect the current public HiAPI text request contract. Undisclosed capabilities are not inferred by the page.
Grok 4.6 is an xAI text reasoning model available through Chat Completions with streaming, JSON objects, tool calling, and four reasoning effort levels.
HiAPI exposes this model through /v1/chat/completions. Test prompts and parameters in the Playground, then use the same HiAPI API key in your server application.
The Playground and API share the same model ID, so three steps take a tested prompt into production.
Step 1
Test the system prompt, output length, and model-supported reasoning options in the Playground.
Step 2
View an existing key or create another after signing in; one key works across all available models.
Step 3
Send requests to /v1/chat/completions and track cost with the usage object.
Grok 4.6 is an xAI text model exposed by HiAPI through Chat Completions for text input and text output.
Use POST /v1/chat/completions with model=grok-4.6.
Use reasoning_effort=low, medium, high, or xhigh. The default is high, and reasoning tokens count as output tokens.
Yes. Use stream=true, response_format.type=json_object, and tools/tool_choice. Tool continuation must replay the assistant tool call and matching tool result.
They are not part of the initial HiAPI public contract; use text messages with Chat Completions.
Input, output, and cached input use live rates on the model and pricing pages; reasoning counts as output. The initial release does not promise use above 200K until long-context verification is complete.