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 / $6.00 output per million tokens — the published xAI list price, with no QSP markup.
At a glance
Frontier coding, knowledge work, STEM, and vision with a 500K-token context.
Pricing comparison ($/1M tokens)
| Provider | Input | Output | vs QSP |
|---|---|---|---|
| QuickSilver Pro | $2.00 | $6.00 | — |
| xAI list price (Grok API) | $2.00 | $6.00 | same |
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.