Home/Models/Grok 4.6
500K contextMultimodalReasoningResponses API

Grok 4.6 on QuickSilver Pro

Grok 4.6 is xAI's frontier model for coding, knowledge work, STEM, and multimodal analysis. It accepts text and images across a 500K-token context and supports reasoning, streaming, tools, and structured output. QuickSilver Pro charges $2.00 input / $6.00 output per million tokens — the published xAI list price, with no QSP markup.

$2.00 input · $6.00 output per 1M tokens
ByRaullen Chai·Updated

At a glance

Context
500K tokens
Input / 1M
$2.00
Output / 1M
$6.00
Thinks by default
Yes

Frontier coding, knowledge work, STEM, and vision with a 500K-token context.

Pricing comparison ($/1M tokens)

ProviderInputOutputvs QSP
QuickSilver Pro$2.00$6.00
xAI list price (Grok API)$2.00$6.00same

When to use

Use Grok 4.6 for difficult coding tasks, technical research, STEM reasoning, image analysis, and agent workflows that benefit from a large working context. It supports both Chat Completions and Responses through the same OpenAI-compatible QSP endpoint, including streaming, function calling, and JSON Schema output.

When to use something else

For routine chat, extraction, or high-volume automation, a Flash-tier model will usually cost less. For prompts above 200,000 tokens, Grok 4.6 long-context pricing doubles to $4 input and $12 output per million tokens, so use retrieval or prompt compaction when the full 500K context is unnecessary.

Quickstart (curl)

curl https://api.quicksilverpro.io/v1/chat/completions \
  -H "Authorization: Bearer $QSP_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4.6",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

OpenAI-compatible. One-line migration via base_url.

FAQ

For requests up to 200,000 prompt tokens, it costs $2.00 per million input tokens, $6.00 per million output tokens, and $0.50 per million cached-input tokens. Above 200,000 prompt tokens, the rates are $4 input, $12 output, and $1 cached input per million tokens. QuickSilver Pro matches the published xAI rates without a markup.

Yes. It accepts text and image input and supports reasoning, streaming, function calling, and JSON Schema structured output across a 500K-token context.

Set base_url=https://api.quicksilverpro.io/v1, use your QSP API key, and set model="grok-4.6". Both `/v1/chat/completions` and `/v1/responses` are supported.

Grok 4.6 adds image input while retaining a 500K-token context and the reasoning, tools, and structured-output capabilities used by coding and research agents. Grok 4.5 remains available at a lower token price for text-only workloads.

Try Grok 4.6 with double credits — up to $50 in bonus credits

Get API Key