Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.
- By:
- xAI
- Input:
- Output:
- Context length:
- 500K
- Max output:
- 500K
- Published:
- 2026-08-13
toolsreasoningstructuredOutputstreamingvisioncaching
Providers
Same model, different providers. Automatic routing picks the cheapest healthy one within the same quality tier.
| Provider | ||||
|---|---|---|---|---|
| 30% offx-ai | $2-4$1.4-2.8/1M tokens | $6-12$4.2-8.4/1M tokens | Read$0.5-1$0.35-0.7/1M tokensWrite— | 500K |
Availability
24 hoursSuccess rate of the requests Amux actually sent to each provider. Client errors are excluded from the denominator — a malformed request isn't the provider's fault.
Throughput
24 hoursAverage output speed on streaming requests, in tokens per second (TPS).
Latency
24 hoursAverage time to first token (TTFT) on streaming requests — how long from sending a request to receiving its first token.
Activity
24 hoursToken usage and cost for this model over time, split by the provider that served each request.
Related models
More models from xAI
xAI: Grok 4.5500K contextfrom $1.4 / M tokens1 providerGrok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.
xAI: Grok Build 0.1256K contextfrom $0.8 / M tokens1 providerGrok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding agents, tool use, and multi-step development tasks. The model powers SpaceXAI’s Grok Build CLI and features a 256K context window with no text output limit, making it well suited for long-horizon coding and automation workflows. Currently in early access.
xAI: Grok 4.31M contextfrom $0.875 / M tokens1 providerGrok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy. Reasoning can be configured between none/low/medium/high (default low) effort levels.