xAI / xai/grok-4.6
Grok 4.6 - access through LLMTR
xAI's flagship model for long coding sessions, multi-step agent flows, and heavy research work. It reads text and images together and fits production pipelines through tool calling and schema-constrained output. Thinking depth is tunable across low, medium, high, and xhigh so you can trade speed for depth; high is the default.
Technical specifications
| Canonical ID | xai/grok-4.6 |
|---|---|
| Provider | xAI |
| Context window | 500,000 tokens |
| Operations | RESPONSES |
| Modalities | text, image |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| RESPONSES | INPUT_TEXT | PER_1M_TOKENS | $2.00 |
| RESPONSES | CACHE_READ | PER_1M_TOKENS | $0.500000 |
| RESPONSES | OUTPUT_TEXT | PER_1M_TOKENS | $6.00 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions \
-H "Authorization: Bearer llmtr-your_key" \
-H "Content-Type: application/json" \
-d '{"model":"xai/grok-4.6","messages":[{"role":"user","content":"Hello"}]}'
Related models
- Grok 4.5 xai/grok-4.5
- Grok 4.3 xai/grok-4.3
- Grok Imagine Video 1.5 xai/grok-imagine-video-1.5
- Grok 4.20 Multi-Agent xai/grok-4.20-multi-agent
- Grok 4.20 Reasoning 0309 xai/grok-4.20-0309-reasoning
- Grok 4.20 Non-Reasoning 0309 xai/grok-4.20-0309-non-reasoning
- Grok Imagine Image xai/grok-imagine-image
- Grok Imagine Image Quality xai/grok-imagine-image-quality