All models
Text & reasoningStable
SpaceXAI
Grok 4.6
SpaceXAI's frontier text-and-image model for coding, agentic tasks, and knowledge work, with direct web, X, and code tools.
Plain-English overview
What Grok 4.6 actually is
Grok 4.6 provides configurable reasoning, a 500K context window, and tool access that includes web search, X search, and code execution. It supports both Responses and Chat Completions-style integrations.
The published base price applies below a 200K-prompt threshold. Large-context agent loops should use stable conversation routing and caching where possible, because cache misses and long-context pricing can change the economics.
Good fit for
- Coding agents with live web or X context
- Tool-heavy knowledge workflows
- Teams already building on OpenAI-compatible APIs
Category comparison
The facts that matter for text models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Context windowMaximum combined prompt and working context documented by the provider.
- 500K tokens
- Maximum outputProvider-published response limit, where available.
- No published text cap
- Input priceCurrent standard list price per million input tokens unless noted.
- $2 / 1M
- Output priceCurrent standard list price per million output tokens unless noted.
- $6 / 1M
- InputsMedia types accepted by the listed model endpoint.
- Text, image
- Tools & agentsSelected native tools and agent-building capabilities, not an exhaustive list.
- Functions, web/X search, code execution
API and provider access
Where to get Grok 4.6
Availability
Regions and access stage
Direct API access runs in published US clusters and the model is also listed through model gateways.
Direct model documentation lists us-east-1 and us-west-2; gateway and account availability varies.
Check live availabilityData and training
The route matters.
SpaceXAI says API inputs and outputs are never used for training without explicit permission. Requests are encrypted and retained for 30 days by default; team-level zero data retention is available with feature tradeoffs.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Grok 4.6 FAQ
What is Grok 4.6?
SpaceXAI's frontier text-and-image model for coding, agentic tasks, and knowledge work, with direct web, X, and code tools. Grok 4.6 provides configurable reasoning, a 500K context window, and tool access that includes web search, X search, and code execution. It supports both Responses and Chat Completions-style integrations.
When was Grok 4.6 released?
Grok 4.6 was released on August 12, 2026 according to the cited provider materials.
Where can I access Grok 4.6?
Direct API access runs in published US clusters and the model is also listed through model gateways. The access routes listed in this guide are SpaceXAI, OpenRouter.
How much does Grok 4.6 cost?
$2 input · $6 output / 1M tokens. Price shown for prompts below 200K tokens. SpaceXAI lists higher long-context rates once that threshold is reached.
Where is Grok 4.6 available?
Direct API access runs in published US clusters and the model is also listed through model gateways. Direct model documentation lists us-east-1 and us-west-2; gateway and account availability varies.
Is my Grok 4.6 API data used for training?
SpaceXAI says API inputs and outputs are never used for training without explicit permission. Requests are encrypted and retained for 30 days by default; team-level zero data retention is available with feature tradeoffs. The policy belongs to the provider route and account terms, so verify it again before production use.
Research trail
Sources for this guide
Keep comparing
More text & reasoning models
OpenAI · Stable
GPT-5.6 Sol
OpenAI's flagship general model for difficult coding, analysis, and professional work, with a very large context window and a broad native tool set.
Read guideAnthropic · Stable
Claude Fable 5.1
Anthropic's frontier model for ambitious, long-running agentic and coding work, with strong vision and enterprise marketplace availability.
Read guideGoogle · Stable
Gemini 3.8 Flash
Google's stable, high-efficiency multimodal model for agents, software work, and large mixed-media inputs at an introductory Flash-tier price.
Read guide