x-ai
SpaceXAI: Grok 4.6
x-ai/grok-4.6
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Grok 4.6 (x-ai/grok-4.6) is a text-output model that, according to the OpenRouter catalog, accepts text, image, and file inputs within a 500,000-token context window. The catalog reports always-on reasoning with a high default effort and selectable effort levels, plus tool calling and structured output support. x-ai's catalog description claims frontier performance on coding, knowledge work, and STEM, though no independent model card was available in this source pack. The catalog notes it is succeeded by Grok 4.7.[1]
Strengths
- Accepts text, image, and file inputs and returns text, within a 500,000-token context window reported by the OpenRouter catalog.[1]
- Reasoning is enabled by default at high effort, with additional selectable effort levels, per the catalog's configuration fields.[1]
- The catalog lists support for tool calling, structured outputs, and common sampling controls such as temperature, top_p, and seed.[1]
Limitations
- All evidence comes from the OpenRouter catalog only; no independent model card was available in this source pack, so capabilities are provider-reported rather than independently verified.[1]
- The catalog marks reasoning as mandatory, meaning it cannot be fully disabled; only the effort level is adjustable.[1]
- Knowledge cutoff, licensing terms, and hardware requirements are not specified in the supplied evidence, and real-world behavior on your specific workloads should be validated before adoption.[1]
Where to use it
- A reasonable candidate to evaluate for coding and agentic workflows, given catalog-reported tool support and the vendor's stated focus on coding; confirm on your own tasks first.[1]
- Document and image understanding workloads may be worth testing, since the catalog reports multimodal inputs and a long context window.[1]
- Complex analysis or STEM-oriented tasks where always-on reasoning at adjustable effort is acceptable, per the catalog's reasoning configuration.[1]
Sources
- [1] OpenRouter catalog · SpaceXAI: Grok 4.6Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).
Specifications
- Model ID
- x-ai/grok-4.6
- Canonical ID
- x-ai/grok-4.6-20260810
- Creator
- x-ai
- Added to OpenRouter
- 12.08.2026
- Context length
- 500,000
- Modality
- text+image+file->text
- Input modalities
- text, image, file
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $2 / out $6
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | BB — next 30% of the cohort | reasoning: mandatory · default high · efforts: xhigh, high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | SS — top 10% of the cohort | — |
| Agents | SS — top 10% of the cohort | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · default high · efforts: xhigh, high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | input: file |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 31 | BB — next 30% of the cohort | 13.11.2026 |
| Artificial Analysis | Coding index | 75.9 | SS — top 10% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 52.5 | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · agenticgamedevwin rate 47.2% · rank 10 | 1,157Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · androidnativewin rate 61% · rank 3 | 1,280Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · blender3dwin rate 42.9% · rank 10 | 1,148Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · codetovideowin rate 47.3% · rank 13 | 1,140Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · fullstackwin rate 54.7% · rank 9 | 1,242Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | agents · godotgamedevwin rate 53.2% · rank 4 | 1,256Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · htmlslideswin rate 60% · rank 6 | 1,144Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | agents · mobileappswin rate 54.9% · rank 13 | 1,226Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | agents · pdfwin rate 59.3% · rank 10 | 1,237Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | agents · python-pptxslideswin rate 52.8% · rank 12 | 1,200Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · spreadsheetwin rate 52.8% · rank 14 | 1,168Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · webappswin rate 55.5% · rank 14 | 1,231Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · 3dwin rate 51.8% · rank 29 | 1,257Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · asciiartwin rate 56.8% · rank 13 | 1,268Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 51.9% · rank 22 | 1,281Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · datavizwin rate 51.5% · rank 17 | 1,282Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 53% · rank 23 | 1,282Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 47.6% · rank 23 | 1,221Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 52.6% · rank 25 | 1,285Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 51.4% · rank 26 | 1,278Elo | AA — next 20% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| xAI | 500,000 | $2 | $6 | — | — | 100% |
| xAI | 500,000 | $2 | $6 | — | — | 100% |
| xAI | 500,000 | $2.2 | $6.6 | — | — | 100% |
| Amazon Bedrock | 500,000 | $2.2 | $6.6 | — | — | — |
| xAI | 500,000 | $4 | $12 | — | — | — |
| xAI | 500,000 | $4 | $12 | — | — | — |
Provider data retrieved: 13.11.2026