Specification

Family: Grok
Source:xAI — docsT1observed 1 h agohigh
Release date: 31 Mar 2026
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
Status: deprecated
Source:Artificial AnalysisT2observed 1 h agomedium
Openness: proprietary
Source:Artificial AnalysisT2observed 1 h agomedium
Context window: 1M tokens
Source:xAI — docsT1observed 1 h agohigh
Max output: 1.8M tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
Knowledge cutoff: Sept 2025
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
Modalities: image, text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
Input modalities: text, image
Source:xAI — docsT1observed 1 h agohigh
Output modalities: text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
Tokenizer: Grok
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
API model id: grok-4.20-0309-reasoning
Source:xAI — docsT1observed 1 h agohigh
Official page: docs.x.ai/developers/models/grok-4.20-0309-reasoning
Source:xAI — docsT1observed 1 h agohigh
Batch api: Yes
Source:xAI — docsT1observed 1 h agohigh
File input: Yes
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
Aa median output tokens per second: 101.1
Source:Artificial AnalysisT2observed 1 h agomedium
Openrouter id: x-ai/grok-4.20
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
Regions: us-east-1, us-west-2
Source:xAI — docsT1observed 1 h agohigh
Supported parameters: include_reasoning, logprobs, max_tokens, reasoning, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_logprobs, top_p
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

24

Source tiers

T1T27 / 17

Freshest observation

1 h ago

Conflicts

1 flagged

Relations

Available through: xAI API
Developed by: xAI
Evaluated on: GPQA, Humanity's Last Exam, IFBench, MMMU-Pro, τ²-bench, Terminal-Bench, Artificial Analysis Intelligence Index

Identity

artificial_analysis: grok-4-20
openrouter: x-ai/grok-4.20
xai_model_id: grok-4.20-0309-reasoning

Also known as: Grok 4.20 0309 v2, grok-4.20, grok-4.20-0309, grok-4.20-0309-reasoning, grok-4.20-beta, grok-4.20-beta-0309, grok-4.20-beta-0309-reasoning, grok-4.20-beta-latest, grok-4.20-beta-latest-reasoning, grok-4.20-beta-reasoning, grok-4.20-experimental-beta-0304, grok-4.20-experimental-beta-0304-reasoning, grok-4.20-experimental-beta-latest, grok-4.20-experimental-beta-reasoning-latest, grok-4.20-reasoning, grok-4.20-reasoning-gv2, grok-4.20-reasoning-latest, SpaceXAI: Grok 4.20, x-ai/grok-4.20

slug grok-4.20

Modelgrok-4.20-0309-non-reasoningxAI
ModelGrok 4.3xAI
ModelGrok Build 0.1xAI
ModelGrok 4.5xAI
ModelGrok 4.6xAI
ModelClaude Haiku 4.5Anthropic
Modelgpt-5.6-terraOpenAI
ModelGemini 3.1 Pro PreviewGoogle

Compare

Open compare →

Modalities

Modalities: imagetext
Input: textimage
Output: text

Capabilities

Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Yes
OpenRouter public model & pricing listing · T2
Vision
Yes
OpenRouter public model & pricing listing · T2
Audio
Unavailable
Fine-tuning available
Unavailable

Context window: 1M tokens
Source:xAI — docsT1observed 1 h agohigh
Max output: 1.8M tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
Knowledge cutoff: Sept 2025
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
Tokenizer: Grok
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium

Benchmark results
Benchmark	Score	Metric	Config	Evaluated	Source
τ²-bench	92.98%	pass^1	aa_slug=grok-4-20 · evaluator=Artificial Analysis · index_version=4.3	—	artificialanalysis.aiT2
Artificial Analysis Intelligence Index	25.66	index	aa_slug=grok-4-20 · version=4.3 · estimated=true	—	artificialanalysis.aiT2
GPQA	91.11%	accuracy	aa_slug=grok-4-20 · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3	—	artificialanalysis.aiT2
Humanity's Last Exam	34.52%	accuracy	aa_slug=grok-4-20 · evaluator=Artificial Analysis · index_version=4.3	—	artificialanalysis.aiT2
IFBench	81.22%	accuracy	aa_slug=grok-4-20 · evaluator=Artificial Analysis · index_version=4.3	—	artificialanalysis.aiT2
MMMU-Pro	74.57%	accuracy	aa_slug=grok-4-20 · evaluator=Artificial Analysis · index_version=4.3	—	artificialanalysis.aiT2
Terminal-Bench	37.88%	accuracy	aa_slug=grok-4-20 · variant=hard · evaluator=Artificial Analysis · index_version=4.3	—	artificialanalysis.aiT2

Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.

Current prices

Current prices per 1M tokens
Provider	Input / 1M	Output / 1M	Cached in	Batch in / out	Context	Observed	Source
xAI APIx-ai/grok-4.20	$1.25	$2.5	$0.20	—	2M	1 h ago	openrouter.aiT2
xAI APIgrok-4.20-0309-reasoning	$1.25	$2.5	$0.20	$1 / $2	1M	1 h ago	docs.x.aiT1

USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.

Available through 1

xAI API

Price history

Input price · USD / 1M tokens

Output price · USD / 1M tokens

xAI API

No hardware estimate available

Estimates need a parameter count; this model has none recorded from a source.

No lineage recorded

Lineage comes from explicit `derived_from`, `fine_tuned_from`, `distilled_from` and `quantized_from` relations stated by sources.

Papers 0

No papers linked yet.

Repositories 0

No repositories linked yet.

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history

16 claims · 16 properties

Release daterelease_date1

Claim history for Release date
Value	Valid from → to	Status	Source	Confidence	Extractor
31 Mar 2026	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Context windowcontext_length1

Claim history for Context window
Value	Valid from → to	Status	Source	Confidence	Extractor
2M tokens	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Max outputmax_output_tokens1

Claim history for Max output
Value	Valid from → to	Status	Source	Confidence	Extractor
1.8M tokens	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Knowledge cutoffknowledge_cutoff1

Claim history for Knowledge cutoff
Value	Valid from → to	Status	Source	Confidence	Extractor
Sept 2025	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Modalitiesmodalities1

Claim history for Modalities
Value	Valid from → to	Status	Source	Confidence	Extractor
image, text	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Input modalitiesmodalities_input1

Claim history for Input modalities
Value	Valid from → to	Status	Source	Confidence	Extractor
image, text	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
Value	Valid from → to	Status	Source	Confidence	Extractor
text	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Tokenizertokenizer1

Claim history for Tokenizer
Value	Valid from → to	Status	Source	Confidence	Extractor
Grok	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Descriptiondescription1

Claim history for Description
Value	Valid from → to	Status	Source	Confidence	Extractor
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...	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

File inputfile_input1

Claim history for File input
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
Value	Valid from → to	Status	Source	Confidence	Extractor
x-ai/grok-4.20	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Reasoningreasoning1

Claim history for Reasoning
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Structured outputstructured_output1

Claim history for Structured output
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
Value	Valid from → to	Status	Source	Confidence	Extractor
include_reasoning, logprobs, max_tokens, reasoning, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_logprobs, top_p	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Tool callingtool_calling1

Claim history for Tool calling
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Visionvision1

Claim history for Vision
Value	Valid from → to	Status	Source	Confidence	Extractor
Yes	11 Sept 2026 21:10 UTC → current	current	OpenRouter public model & pricing listingT2	medium	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
Benchmark resultModelGrok 4.20xAI
Grok 4.20 scores 37.88% on Terminal-Bench
artificial_analysis
artificialanalysis.ai
11 Sept 2026
Benchmark resultModelGrok 4.20xAI
Grok 4.20 scores 92.98% on τ²-bench
artificial_analysis
artificialanalysis.ai
11 Sept 2026
Benchmark resultModelGrok 4.20xAI
Grok 4.20 scores 74.57% on MMMU-Pro
artificial_analysis
artificialanalysis.ai
11 Sept 2026
Benchmark resultModelGrok 4.20xAI
Grok 4.20 scores 81.22% on IFBench
artificial_analysis
artificialanalysis.ai
11 Sept 2026
Benchmark resultModelGrok 4.20xAI
Grok 4.20 scores 34.52% on Humanity's Last Exam
artificial_analysis
artificialanalysis.ai
11 Sept 2026
Benchmark resultModelGrok 4.20xAI
Grok 4.20 scores 91.11% on GPQA
artificial_analysis
artificialanalysis.ai
11 Sept 2026
Benchmark resultModelGrok 4.20xAI
Grok 4.20 scores 25.66 on Artificial Analysis Intelligence Index
artificial_analysis
artificialanalysis.ai
11 Sept 2026
Listed by providerModelGrok 4.20xAI
xAI API lists Grok 4.20 at $1.25 in / $2.5 out per 1M tokens
xai
docs.x.ai
11 Sept 2026
Context window changedModelGrok 4.20xAI
Grok 4.20: context length changed from 2000000 to 1000000
Context window2M tokens→1M tokensxai
docs.x.ai
11 Sept 2026
Property changedModelGrok 4.20xAI
Grok 4.20: modalities input changed from ["image", "text"] to ["text", "image"]
Input modalitiesimage, text→text, imagexai
docs.x.ai
31 Mar 2026
New modelModelGrok 4.20xAI
New model: Grok 4.20 (xAI)
openrouter
openrouter.ai
11 Sept 2026
Listed by providerModelGrok 4.20xAI
xAI API lists Grok 4.20 at $1.25 in / $2.5 out per 1M tokens
openrouter
openrouter.ai

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
xAI — docs	docs.x.ai/developers/models/grok-4.20-0309-reasoning.md	model_page	T1· Official	1 h ago	1
xAI — docs	docs.x.ai/developers/models	model_docs	T1· Official	1 h ago	1
Artificial Analysis	artificialanalysis.ai/leaderboards/models	leaderboard	T2· Quality secondary	1 h ago	1
OpenRouter public model & pricing listing	openrouter.ai/api/v1/models	catalogue	T2· Quality secondary	1 h ago	2

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.