x-ai
SpaceXAI: Grok 4.20
x-ai/grok-4.20
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
OpenRouter’s catalog lists x-ai/grok-4.20 as a text-output model from x-ai that accepts text, image, and file inputs, exposes tool calling and structured-output controls, and provides a very large context window. The catalog describes it as a fast reasoning model with strong prompt adherence and agentic tool use; these are source-reported claims, not independently verified here. Arena measurements supplied by the catalog suggest category-dependent performance. Only OpenRouter evidence was available; no independent model card was included in this source pack.[1]
Strengths
- Catalog-reported multimodal inputs: text, images, and files can be supplied, with text output.[1]
- A listed two-million-token context window may suit long documents and extended agent histories.[1]
- Tool calling, tool choice, structured outputs, response format, seed, and optional reasoning controls are listed.[1]
Limitations
- Only OpenRouter catalog evidence was supplied; an independent model card was not available in this source pack.[1]
- Reported speed, hallucination resistance, and prompt adherence remain catalog claims; real workload validation is still needed.[1]
- Arena measurements vary widely by category, so the supplied results do not establish uniformly strong performance.[1]
Where to use it
- Potentially useful for agentic workflows that need tool invocation and structured text responses; validate orchestration reliability.[1]
- Worth testing for multimodal document or image understanding where text-only output is sufficient.[1]
- Candidate for long-context summarization or visual and design-oriented assistance, with category-specific evaluation before rollout.[1]
Sources
- [1] OpenRouter catalog · SpaceXAI: Grok 4.20Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...
Specifications
- Model ID
- x-ai/grok-4.20
- Canonical ID
- x-ai/grok-4.20-20260309
- Creator
- x-ai
- Added to OpenRouter
- 31.03.2026
- Context length
- 2,000,000
- Modality
- text+image+file->text
- Input modalities
- text, image, file
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $1.25 / out $2.5
- Knowledge cutoff
- 01.09.2025
- 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 | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| 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 |
|---|---|---|---|---|
| Design Arena | agents · androidnativewin rate 35% · rank 39 | 1,036Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · fullstackwin rate 41.1% · rank 36 | 1,032Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · godotgamedevwin rate 38.5% · rank 29 | 1,089Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · htmlslideswin rate 45.7% · rank 3 | 1,180Elo | SS — top 10% of the cohort | 13.11.2026 |
| Design Arena | agents · mobileappswin rate 45.4% · rank 46 | 1,084Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · webappswin rate 49.7% · rank 33 | 1,126Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · 3dwin rate 52.3% · rank 59 | 1,176Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · asciiartwin rate 48.3% · rank 33 | 1,170Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 52% · rank 60 | 1,211Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · datavizwin rate 52% · rank 54 | 1,215Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 50.4% · rank 64 | 1,183Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 52.4% · rank 46 | 1,154Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 49.4% · rank 66 | 1,192Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 52.1% · rank 59 | 1,222Elo | BB — next 30% 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 | 2,000,000 | $1.25 | $2.5 | — | — | 100% |
| xAI | 2,000,000 | $1.25 | $2.5 | — | — | 100% |
| xAI | 2,000,000 | $2.5 | $5 | — | — | — |
| xAI | 2,000,000 | $2.5 | $5 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.