The Orchestrator › Models › xAI
xAI: SpaceXAI: Grok 4.6
Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7.
Specifications
| Provider | xAI |
| Model ID | x-ai/grok-4.6 |
| Context window | 500K tokens (500,000) |
| Modalities | text + image + file → text |
| Tokenizer | Grok |
| Router sources | OpenRouter, TrustedRouter |
| Released | 2026-08-12 |
| Tracked since | 2026-11-14 |
| Popularity | #46 by usage · peak 1.8% spend share in an OpenRouter category |
| Reasoning | Mandatory |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | x-ai/grok-4.6 | $2.00 | $6.00 | 500K |
| batch | OpenRouter | x-ai/grok-4.6:batch | $1.60 | $4.80 | 500K |
| standard | TrustedRouter | x-ai/grok-4.6 | $2.11 | $6.33 | 500K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $2.11 | $6.33 | 500K |
| 2026-11-14 | $2.00 | $6.00 | 500K |
Capabilities
Vision (image input)File inputAgentic tool useStructured outputsReasoning (always on)256K+ context windowControllable reasoningNo content storage (attested)Zero data retention
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
include_reasoning, logprobs, max_tokens, reasoning, reasoning_effort, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p