Grok 4.20 Reasoning
Released
2026-03-10
Last refreshed
2026-10-16
Status
Researched 175d ago
ProprietaryCommercial use: restrictedMultimodalRAGAgentsLong contextVisionJSON / Tool use
xAI releases · 19 in the last 12 months · this family litChangelog →
Specifications
- Family
- Grok 4
- Released
- 2026-03-10
- Context
- 1M
- Knowledge cutoff
- 2024-11
- Specialization
- reasoning
- Openness
- Proprietary
- License
- ProprietaryRestricted
- Weights
- Not released
- Code
- Unknown
Created by
Pricing
Output / 1M
$2.50
Input / 1M
$1.25
Cheapest of 2 routes · xAI Console · cache read $0.200
Links
Created by
Pricing
Output / 1M
$2.50
Input / 1M
$1.25
Cheapest of 2 routes · xAI Console · cache read $0.200
Links
About
Grok 4.20 Reasoning is the xAI API reasoning variant launched around March 10, 2026 as grok-4.20-0309-reasoning.
Providers(2)
Compare all 2Compare API pricing across 2 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Batch in / out | Cache | Route |
|---|---|---|---|---|---|
| xAI Console | $1.25 | $2.50 | $1.00 / $2.00 | read $0.200 | Serverless |
| Vercel AI Gateway | $1.25 | $2.50 | - | read $0.200 | Serverless |
Available via routers & gateways(1)
Capabilities
VisionMultimodalReasoningJSON / Tool useStructured Outputs
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Benchmark scores(3)
Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 88.5 | GPQA Diamond (accuracy)Observed 2026-06-07 | — | ||
| 30.0 | HLE for Grok 4 (accuracy)Observed 2026-06-07 | — | ||
| 1432.0 | text creative_writing 2026-10-22Observed 2026-10-22 | Configuration: Grok 4.20 Beta (Reasoning, 0309) Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'Grok 4.20 Beta (Reasoning, 0309)' (category creative_writing in text/latest-00000-of-00001.parquet): rank 59 of 416, rating 1432.0 (95% CI 1425.3-1438.7), 11437 votes. The board entry or catalog model carries a Preview/Beta/Experimental label. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27. | Source Source: LMArena (lmarena.ai), CC BY 4.0 |
Migration checks
No linked migration route is available for this model yet.