xAI model product
Grok 3 Mini
Grok 3 Mini is a streamlined version of xAI's Grok 3 model designed for quicker response times.
Updated Oct 23, 2026. Default version: Grok-3 Mini
LLMBoard Score46.6Grok-3 Mini
Coverage0%4 benchmark families
Context window128KTokens
Official input priceN/AOfficial price unavailable
Grok 3 Mini Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Grok 3 Mini Benchmark Results
Benchmark scores for Grok-3 Mini.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAIME 2024 | Score95.80% | Rank01 | Participants54 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score80.40% | Rank11 | Participants76 | Percentile86.67% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score90.80% | Rank47 | Participants122 | Percentile61.98% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score84.00% | Rank78 | Participants256 | Percentile69.80% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,369.57 rating | Rank131 | Participants218 | Percentile40.09% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,363.76 rating | Rank144 | Participants218 | Percentile34.10% | EvidenceA | Evaluated |
Grok 3 Mini Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categoryjapanese | Rank100 | Rating / score1,342.05 | Votes600 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank109 | Rating / score1,334.58 | Votes600 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank111 | Rating / score1,335.09 | Votes296 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank117 | Rating / score1,355.98 | Votes1,571 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank120 | Rating / score1,391.13 | Votes1,088 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank121 | Rating / score1,380.59 | Votes394 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank122 | Rating / score1,394.53 | Votes911 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank122 | Rating / score1,390.15 | Votes956 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank126 | Rating / score1,406.68 | Votes911 | ObservationsN/A | Result date |
| Arenatext | Categorycreative writing | Rank127 | Rating / score1,341.54 | Votes2,574 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank127 | Rating / score1,349.44 | Votes416 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank129 | Rating / score1,371.72 | Votes3,229 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank129 | Rating / score1,320.59 | Votes296 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank130 | Rating / score1,374.56 | Votes7,273 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank130 | Rating / score1,335.63 | Votes2,849 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank131 | Rating / score1,381.53 | Votes2,582 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank131 | Rating / score1,345.95 | Votes3,420 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank131 | Rating / score1,356.73 | Votes4,156 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank131 | Rating / score1,369.57 | Votes15,594 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank132 | Rating / score1,335.25 | Votes11,115 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank132 | Rating / score1,389.26 | Votes968 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank133 | Rating / score1,352.07 | Votes8,466 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank133 | Rating / score1,343.79 | Votes1,571 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank134 | Rating / score1,370.60 | Votes394 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank135 | Rating / score1,386.76 | Votes870 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank135 | Rating / score1,379.12 | Votes7,123 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank135 | Rating / score1,357.15 | Votes275 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank135 | Rating / score1,385.94 | Votes968 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank135 | Rating / score1,353.24 | Votes1,630 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank135 | Rating / score1,384.83 | Votes1,088 | ObservationsN/A | Result date |
Grok 3 Mini Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.30 input, $0.50 output per 1M via Helicone
- Tracked offerings
- 2
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderHelicone | Provider model IDgrok-3-mini | Regionglobal | Input / 1M$0.30 | Output / 1M$0.50 | Context131.1K | Updated |
| ProviderPoe | Provider model IDxai/grok-3-mini | Regionglobal | Input / 1M$0.30 | Output / 1M$0.50 | Context131.1K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Grok 3 Mini Runtime Performance
Provider-specific output speed and catalog latency for Grok-3 Mini. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderxAI | Output Speed100.00 tok/s | Catalog Latency0.70 s | Max Input128K | Max Output8K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Grok 3 Mini Specifications
Technical details for the model's default version.
- Version
- Grok-3 Mini
- Released
- Feb 17, 2025
- Knowledge cutoff
- Nov 17, 2024
- Parameters
- N/A
- Context window
- 128K
- Max output
- 8K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Grok 3 Mini Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGrok-3 Mini | Released | LLMBoard46.65 | ParametersN/A | Context128K | Max output8K | Open weightsNo | LicenseProprietary |
Models similar to Grok 3 Mini
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
XA
Grok 4.1
xAI
XA
Grok 4.1 Thinking
xAI
XA
Grok 4 Fast
xAI
XA
Grok 3
xAI
XA
Grok 4
xAI
XA
Grok 4.3
xAI
What is Grok 3 Mini?
Key information about Grok 3 Mini and its available data.
Grok 3 Mini is an llm from xAI and a lighter version of the Grok 3 model. It is intended for use cases that prioritize speed over the full model's capabilities.
Data as of 2026-10-22.
FAQ
Common questions about Grok 3 Mini.
When was Grok 3 Mini released?
Grok 3 Mini's default version was released on Feb 17, 2025.
How much does Grok 3 Mini cost?
No official standard PAYG price is currently available for Grok 3 Mini. The lowest tracked third-party offer starts at $0.30 input and $0.50 output via Helicone.
Who created Grok 3 Mini?
Grok 3 Mini was created by xAI.
What is the context window for Grok 3 Mini?
The default version has a 128K token context window.
Is Grok 3 Mini open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Grok 3 Mini?
2 provider offerings are linked to the default version.