MODEL PROOF
Grok 4.20
NOT INDEPENDENTLY RATED
No independent LMArena score is published for this model.
Base context tier shown; inspect the complete context ladder below.
- Independent LMArena score
- Not independently rated
- Context window
- 2M
- Maximum output
- 1.8M
- Input modalities
- text, image, file
- Output modalities
- text
- Published input price
- $1.25 / 1M tokens
- Published output price
- $2.50 / 1M tokens
- Pricing kind
- fixed
- Context tiers
- Tiered by context
Inspect complete billing conditions and endpoint terms below.
Price from xAI: the cheapest offer that is serving, at standard delivery and at the maker’s precision or better, at its standard rate.
Every price dimension · USD per million tokens
| Input | $1.25/M |
|---|---|
| Output | $2.50/M |
| Cached input | $0.200/M |
| Cache write | Unknown/M |
| Cache write 1h | Unknown/M |
| Reasoning | Unknown/M |
| Web search | $0.005/call |
The headline rate does not apply to a long-context workload.
Complete context ladder · 1 tier
| More than 200,000 tokens | $2.50/M in (2×) $5.00/M out $0.400/M cached input Unknown/M cache write |
|---|
Who sells it
The same weights, different shops. Cheapest is not like-for-like when serving precision differs.
4 provider offers · rates, limits and conditions
Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test.
| Seller | Input | Output | Precision | Uptime (1d) |
|---|---|---|---|---|
| xAIxai/zdr Endpoint terms
| $1.25 | $2.50 | undeclared | 99.72% |
| xAIxai Endpoint terms
| $1.25 | $2.50 | undeclared | 99.71% |
| xAIxai/zdr/priority Endpoint terms
| $2.50 | $5.00 | undeclared | 99.93% |
| xAIxai/priority Endpoint terms
| $2.50 | $5.00 | undeclared | 100.00% |
Independent scores
No independent benchmark has measured this model. Unrated is not a score of zero.
Best rankings by task
- Htmlslides #11 1180
- Web apps #27 1137
- ASCII art #28 1186
- Godot games #31 1089
- Full-stack apps #34 1052
- Native Android apps #35 1060
- SVG #37 1164
- Mobile apps #41 1086
Per-task Elo and rank from Design Arena, via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list.
Capability
| Context window | 2M |
|---|---|
| Max output | 1.8M |
| Input modes | text, image, file |
| Tool use | yes |
| Reasoning | optional |
| Knowledge cutoff | 2025-09-01 |
| Open weights | no |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-10-06 |
| Quality data | unrated |
| Cross-checked | vendor page |
Our take
editorial — not a measurementConsider this Grok for large-document evaluations, but price the actual prompt length: the accepted table includes a context threshold. A large window does not establish retrieval quality, and the model number does not establish a measured ranking. Treat multi-agent or other named variants as separate identities until their capability and offer conditions are checked.
Strengths
- The accepted record provides separate context and output limits
- Tool use and a context-tier price table are listed
Weaknesses
- A base-rate estimate can understate the cost of a long prompt
- Variant names do not establish identical capability or terms
Reach for it when
- Large-document and retrieval evaluations
- Workloads with explicit prompt-size assumptions
Avoid it if
- You assume the base rate applies across the entire window
- You need an independent quality result that is not in the current proof
Sources: docs.x.ai
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...
Questions this page answers
What does Grok 4.20 cost?
$1.25/M in, $2.50/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does Grok 4.20 have an independent quality score?
Grok 4.20 has no independent quality score in this catalogue. Unrated is not a score of zero.
What beats Grok 4.20?
Grok 4.20 has no independent quality score. Unrated is not a score of zero.
Does this page use Artificial Analysis scores for Grok 4.20?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
Does a missing score mean Grok 4.20 scored zero?
Unrated is not a score of zero.
MODEL MONUMENT
Save or share this proof
Badge
The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not.
[](https://undominated.ai/models/x-ai__grok-4.20/)<a href="https://undominated.ai/models/x-ai__grok-4.20/"><img src="https://undominated.ai/badge/x-ai__grok-4.20.svg" alt="Grok 4.20 — Undominated.ai dominance verdict" height="36"></a>Direct file: https://undominated.ai/badge/x-ai__grok-4.20.svg — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never
older than the last deploy.
